Information Sciences最新文献

We consider a long-standing yet hard and largely open machine learning problem of anomaly areas detection in multimodal 3D images. Purely data-driven methods often fail in such tasks because rarely incorporating domain-specific knowledge into the algorithm and do not fully utilize information from multiple modalities. We address these issues by proposing a novel framework with data fusion technology to leverage domain-specific knowledge and multimodal labeled data, as well as employ the power of randomized learning techniques. To demonstrate the proposed framework efficiency, we apply it to the challenging task of detecting subtle pathologies in MRI scans. A distinct feature of the resulting solution is that it explicitly incorporates evidence-based medical knowledge about pathologies into the feature maps. Our experiments show that the method is capable of achieving lesion detection in 71% of subjects by using just one such feature. Integrating information from all feature maps and data modalities enhances detection rate to 78%. Using stochastic configuration networks to initialize the weights of the classification model enables to increase precision metric by 18% as compared to deterministic approaches. This demonstrates the possibility and practical viability of building efficient and interpretable randomised algorithms for automated anomaly detection in complex multimodal data.

In model-based reinforcement learning, the conventional approach to addressing world model bias is to use gradient optimization methods. However, using a singular policy from gradient optimization methods in response to a world model bias inevitably results in an inherently biased policy. This is because of constraints on the imperfect and dynamic data of state-action pairs. The gap between the world model and the real environment can never be completely eliminated. This article introduces a novel approach that explores a variety of policies instead of focusing on either world model bias or singular policy bias. Specifically, we introduce the Multi-Step Pruning Policy (MSPP), which aims to reduce redundant actions and compress the action and state spaces. This approach encourages a different perspective within the same world model. To achieve this, we use multiple pruning policies in parallel and integrate their outputs using the cross-entropy method. Additionally, we provide a convergence analysis of the pruning policy theory in tabular form and an updated parameter theoretical framework. In the experimental section, the newly proposed MSPP method demonstrates a comprehensive understanding of the world model and outperforms existing state-of-the-art model-based reinforcement learning baseline techniques.

In multi-objective evolutionary algorithms, one of the focal points is finding a balance between diversity and convergence. In decomposition-based algorithms, the role of weight vectors is crucial. Despite numerous studies dedicated to these aspects, there is a scarcity of utilizing transfer learning algorithms for dual-operator feature fusion and employing neural networks for accurate partitioning of the objective space population. To address the aforementioned issues, this paper proposes the following improvements: (1) Implementing a Balanced Distribution Adaptation (BDA) transfer learning algorithm to achieve dual-operator feature fusion, resulting in a transfer population guiding the adaptive adjustment of weight vectors. (2) Integrating the BDA algorithm with multi-objective algorithms requires labeling the data, a challenge in the multi-objective evolutionary algorithm. To tackle this issue, non-dominated sorting is introduced as a bridge connecting the BDA and multi-objective evolutionary algorithms. This serves as a method to combine the advantages of decomposition-based and Pareto-dominance principle-based multi-objective algorithms. (3) To overcome the impact of traditional Euclidean distance on population sparsity, a neural network is employed to determine the population's distribution in the objective space accurately. This ensures the precise identification of individuals to be removed from the current population and the areas where additions are needed. In order to fully validate the effectiveness of the proposed algorithm, four different sets of experiments are conducted in the experimental section, where three sets of benchmarking problems are compared to a variety of algorithms that have received much attention in recent years, as well as ablation experiments.

Z. Pawlak first proposed the rough set (RS) in 1982. For over forty years, scholars have developed a large number of RS models to solve various data problems. However, most RS models are designed based on inherent rules, and their mathematical structures are similar and complex. For this reason, the efficiency of RS methods in analyzing data has not been significantly improved. To address this issue, we propose some new rules to simplify traditional RS models. These simplified RS models, which are equivalent to traditional RS models, can mine data more quickly. In this paper, we take Pawlak RS as an example to compare the computational efficiency between the simplified Pawlak RS (SPRS) and the traditional RSs. Numerical experiments confirm that the computational efficiency of the SPRS is not only far superior to that of traditional Pawlak RS (TPRS), but also higher than that of most existing RSs.

Drug repositioning (DR) is crucial for identifying new disease indications for existing drugs and enhancing their clinical utility. Despite the effectiveness of various artificial intelligence techniques in discovering novel drug-disease associations (DDAs), many algorithms primarily focus on incorporating biological knowledge of drugs and diseases into DDA networks, often overlooking the rich connectivity patterns inherent in heterogeneous biological networks. In this study, we leveraged diverse connectivity patterns to gain new insights into the regulatory mechanisms of drugs acting on target proteins in diseases. We defined a set of meta-paths to reveal different regulatory mechanisms, each corresponding to distinct connectivity patterns. For each meta-path, we constructed a regulation graph through random-walk sampling of its instances in the network and obtained drug and disease embeddings through regulation-aware graph representation learning. Subsequently, we proposed a novel multi-view attention mechanism to enhance drug and disease representations. The task of predicting DDAs was accomplished using the XGBoost classifier based on the final representations of drugs and diseases. The experimental results demonstrated the superior performance of our method, RGLDR, on three benchmark datasets under ten-fold cross-validation, outperforming state-of-the-art DR algorithms across several evaluation metrics. Furthermore, case studies on two diseases indicated that RGLDR is a promising DR tool that leverages meaningful connectivity patterns for improved efficacy.

Knowledge Graph (KG) is an essential research field in graph theory, but its inherent incompleteness and sparsity influence its performance in several fields. Knowledge Graph Reasoning (KGR) aims to ameliorate those problems by mining new knowledge from subsistent knowledge. As one of the downstream tasks of KGR, link prediction is of great significance for improving the quality of KG. Recently, the Graph Neural Network (GNN)-based method became the most effective way to achieve the link prediction task. However, it still suffers from problems such as incomplete neighbor and relation-level information aggregation and unstable learning of the entity's features. To improve those issues, a Hierarchical and Interlamination Graph Self-attention Mechanism-based (HIGSM) plug-and-play architecture is proposed for KGR in this paper. It is composed of three-level layers: feature extractor, encoder, and decoder. The feature extractor makes our architecture more effective and stable for the retrieval of new features. The encoder is equipped with a two-stage encoding mechanism accompanied by two mixture-of-expert strategies, which enables our architecture to capture more practical reasoning information to improve prediction accuracy and generalization of the model. The decoder can use existing KGR models and compute the scores of triples in KG. The extensive experimental results and ablation studies on four KGs unambiguously demonstrate the state-of-the-art prediction performance of the proposed HIGSM architecture compared to current GNN-based methods.

The hesitant fuzzy linguistic term set (HFLTS) is an efficient tool for modeling linguistic information in multi-criteria decision making (MCDM), and the entropy measure of HFLTS, as a substantial representation of uncertainty, merits additional investigation. This article aims to exploit a general framework to facilitate the construction of entropy measure for multigranular unbalanced HFLTS. An axiomatic definition of the entropy for HFLTSs that considers both types of uncertainty (fuzziness and hesitation) is presented, with the entropy measure subsequently derived from distance-based mapping. From this definition, several deduced results have been developed for the mapping that depicts the entropy expression in order to get such functions with ease. Whereafter, a MCDM weight-determining model for multigranular unbalanced linguistic information without preset weights is devised, and an empirical application of the suggested model in MCDM is illustrated. Ultimately, comparisons and analyses with existing studies are conducted to demonstrate the advantages of the proposed work.

Community discovery plays an essential role in analyzing and understanding the behavior and relationships of users in social networks. For this reason, various algorithms have been developed in the last decade for discovering the optimal community structure. In social networks, some individuals have special characteristics that make them well-known by others. These groups of users are called leaders and often have a significant impact on others, with an exceptional ability to build communities. In this paper, we propose an efficient method to detect communities in social networks using the concept of leadership (LeaDCD). The proposed algorithm mainly involves three phases. First, based on nodes' degree centrality and maximal cliques, some small groups of nodes (leaders) considered as seeds for communities are discovered. Next, unassigned nodes are added to the seeds through an expansion process to generate the initial community structure. Finally, small communities are merged to form the final community structure. To demonstrate the effectiveness of our proposal, we carried out comprehensive experiments on real-world and artificial graphs. The findings indicate that our algorithm outperforms other commonly used methods, demonstrating its high efficiency and reliability in discovering communities within social graphs.

Platooning of vehicular systems is an effective technique for enhancing transportation efficiency. As the scale of the vehicular platoon systems increases, disturbances on individual vehicles can affect the whole platoon through their connections. Besides, excessive vehicles impose a significant burden on communication devices. Towards this end, this work investigates the distributed platoon control problem of connected vehicular systems subject to disturbances by employing a resource-efficient communication mechanism. The proposed adaptive event-triggered mechanism (AETM) avoids periodic data transmission and reduces communication burden among vehicles. Besides, the AETM regulates the triggered threshold dynamically via the perception of spacing errors and avoids continuous inter-vehicle communication. Next, an AETM-based finite-time extended state observer (AFESO) is designed to alleviate the impact of the external disturbances. Then, an adaptive event-triggered distributed sliding mode control (DSMC) framework is developed to guarantee platoon stability. It is approved that, under the proposed control method, the closed-loop system subject to the disturbances satisfies the $L_2$ input-to-output string stability ($L_2$-IOSS). The salient feature of the AETM-based DSMC is that the AETM can effectively reduce communication consumption, while DSMC mitigates the performance degradation caused by triggering errors and disturbances. Finally, numerical simulations demonstrate the effectiveness of the proposed algorithm.

A Temporal Knowledge Graph (TKG) is designed for the effective modelling of the temporal relationships and dynamics of entities, events and concepts. Owing to its temporal attributes, a TKG offers greater benefits for reasoning than a static knowledge graph (KG). However, existing approaches for TKG reasoning do not consider coherent relationships between numerous facts, a term borrowed from specific parlance reflecting the interaction between objectives, such as observation and removal agents. This characteristic suggests that the model can obtain more insights from simultaneous coherent relationships. To address this problem, we develop a label-based process to construct a TKG from temporal event data in these domains. Based on the process, we build a specific TKG called Simulated Agent Interaction Knowledge Graph (SAIKG). In addition, we propose a novel TKG reasoning mechanism, termed the Coherence Mode. It is premised on an event coherence manner, enabling the prediction of unknown facts. Extensive experimental studies on different datasets demonstrate the effectiveness of the Coherence Mode integrated with typical models.