Expert Systems with Applications: An International Journal

Drug–target interaction (DTI) prediction can reveal new drug targets and assist in drug repositioning. It can also help identify the most potential candidate drugs for specific targets, advancing new drug discovery. Graph Convolutional Networks (...

The problem of autonomous navigation has attracted significant attention from robotics research community in the last few decades. In this paper, we address the problem of low data utilization due to the large amount of episode experience value ...

Most approaches used in social recommender systems concentrate mostly on positive relationships within the social network, frequently ignoring the insightful information that negative relationships can offer. A more thorough understanding of user ...

Global farming methods have improved owing to supply demand, human resource shortages, and seasonal fluctuations. Integrating automated mechanics, smart controllers, and artificial intelligence has become imperative to tackle these problems. ...

Traditional researches predominantly rely on static protein network models, which present highly averaged and idealized representations of protein networks. However, these models fail to accurately capture the dynamic character of protein ...

• Establish a knowledge graph using dynamic network features.
• Filter active and co-expression genes in dynamic protein–protein interaction network.
• Combine dynamic network with R-GCN to reconstruct protein–protein interaction ...

Bearing fault diagnosis is of great importance to ensure the safe and stable operation of mechanical equipment. The actual collected bearing fault signals are susceptible to strong noise interference and bearing samples for each fault state may ...

• A novel scheduling framework for closed-loop manufacturing-remanufacturing is proposed.
• A scenario-based chance-constrained optimization is proposed for the multiple uncertainty.
• A sequential optimization algorithm is designed to ...

To facilitate sustainability by extending the life-cycle and residual value of production materials, a collaborate scheduling scheme for closed-loop manufacturing system with disturbance uncertainty is studied. Based on the features of the closed-...

The growth of Artificial Intelligence applications requires to develop risk management models that can balance opportunities with risks.

We contribute to the development of Artificial Intelligence risk models proposing a Rank Graduation Box (RGB),...

• A new toolkit for evaluating the trustworthiness condition of AI systems.
• Our method is based on the use of the Lorenz and concordance curves.
• The metrics provide a measure of the compliance AI applications as a percentage.
• The ...

In multi-label learning, addressing the class imbalance issue is of paramount importance. Oversampling methods are preferred as they offer a more general solution independent of the model choice, i.e., they alleviate the imbalance of datasets by ...

• Retrieving adaptive and solid neighborhood for multi-label data.
• Emphasizing boundary areas of highly imbalanced labels.
• Exploiting label correlations to guide the label assignment.
• Better performances than 8 baselines with 5 ...

In cricket’s dynamic environment, bowlers’ performances are a key factor in determining success. In this dynamic sport, our study explores the field of bowler performance predictive analytics to enable decision-makers and strategists. Using ...

• An novel link prediction framework based on entity-relation-level GAT.
• Locally topological structures with relational features are hierarchically embedded.
• The attention mechanism is used for the potential semantic information.

Limited by the sufficiency and timeliness of information obtained, the connections among entities of knowledge graphs need to be updated continuously. Therefore, how to infer the possibility of linking between two unlinked entities with known ...

Timely and reliable estimation of the upstream process condition in flotation process is significant for whole flotation operations. An upstream process condition monitoring model based on feature performance evaluation and parameter-mapped ...

Attention mechanisms improve the performance of models by selectively processing relevant information. However, existing attention mechanisms for CNNs do not utilize the high-order semantic similarity between different channels in the input when ...

• The proposed SHRA Module explore the high-order similarity among nodes via hypergraph learning.
• A structure-sharing hypergraph convolution (SHGCN) is performed to reason the attention coefficients.
• The hypergraphs are combined in a ...

This paper presents a method for identifying fraudulent fund transfers using real bank data, analyzing customer information, transactional activities, and customer relationships. The preprocessing step transforms high-dimensional, irregular ...

Display Omitted

• A fraud detection algorithm handling irregular transactions and customer relations.
• Fusions of variational self-attention-based autoencoders and graph neural networks.
• Neighborhood sampling with mini-batch training for efficient ...

Forming robot clusters is a common means to improve work efficiency and ensure personnel safety in intelligent logistics warehousing. However, designing a reasonable charging sequence and time for each robot in the cluster poses a major challenge ...

• GRACCF, with AC for the first time, is applied in a real-world scenario.
• B-HCCA is designed to address heterogeneous continuous assignment conflicts.
• Compared with some algorithms, B-HCCA reduces redundant charging by 80%.
• ...

The practical application of supervised stereo matching methods is often limited by the requirement of obtaining ground-truth disparity maps in advance. To address this issue, we introduce a novel unsupervised stereo matching method based on the ...

The prediction of Dissolved Oxygen (DO) in oceans is crucial for the survival of marine life and the management of marine farms. However, due to the inherent instability and uncertainty of DO, prediction models frequently necessitate parameter ...

Display Omitted

• A long-term DO prediction model for marine ranches based on Transformer.
• An Uncertainty-aware Attention Mechanism is proposed.
• A multi-scale latent correlation decomposition strategy is introduced.
• An adaptive hyperparameter ...

The rapid development of electronic commerce has increased demands for order fulfillment efficiency, making this a crucial challenge for warehouse systems. The study proposes a novel fishbone robotic mobile fulfillment system (FRMFS) to optimize ...

• Fishbone robotic mobile fulfillment systems (FRMFS) are proposed.
• Comparison of FRMFS with RMFS is provided.
• High order fulfillment efficiency can be achieved with the proposed FRMFS.
• An in-depth analysis of various layout ...

With the rapid development of internet of things (IoT), the scale of wireless sensor networks (WSNs) is gradually expanding, and it is necessary to study the energy saving and balancing algorithm for WSNs in multi-sensor nodes and large ...

Anomaly detection on attributed networks is widely used in the real world, such as in spam, and fraud detection. Due to the scarcity of anomaly data in the real world, anomaly detection methods typically use unsupervised techniques to detect ...

• A new anomalies injection method: dimension-based anomalies injection is proposed.
• An efficient loss function and attribute reconstruction method are proposed.
• A new anomaly detection method is proposed with dimension-based feature ...

Session-based recommendation (SBR) predicts the next item clicked by anonymous users based on the given sessions. Nowadays, numerous SBR models merge global information for representation enhancement, potentially leading to redundancy issues that ...

Traditional time series (TS) forecasting models are based on fixed, static datasets and lack scalability when faced with the continuous influx of data in real-world scenarios. Real-time online learning of data streams is crucial for improving ...

A sparse compressed deep echo state network (SCDESN) incorporating sparse input units, compressed sampling and principal component analysis (PCA) units is proposed in this paper, and theoretically proved the sufficient and necessary conditions to ...

Knowledge Tracing (KT) is a method that seeks to forecast students’ future performance based on their historical interactions with intelligent tutoring systems. Various KT techniques have been developed from distinct perspectives, such as ...

• We construct a tripartite heterogeneous graph of concepts–questions–students.
• We topologize to connect temporal and structural information in the KT process.
• We use two GCN networks to model clustering effect and group effect.
• ...

As the volume of research proposals increases and the interdisciplinary nature of research fields exacerbates the complexity of manual proposal grouping, the grouping of research proposals becomes increasingly vital in funding agencies’ ...

Electric Vehicle (EV)-based parcel delivery is getting much more popular these days due to EVs being eco-friendly and sustainable. One well-known problem in the literature to study last-mile delivery via EVs is the Electric Vehicle Routing ...

• Prize-collecting Electric Vehicle Routing Problem with Time Windows is studied.
• The aim is to minimize EVs’ route and usage costs while maximizing collected prizes.
• PC-EVRP-TW is mathematically modeled using Mixed-integer Linear ...

As a core paradigm of the evidential clustering algorithm, evidential c-means (ECM) offers a more flexible credal partition to characterize uncertainty and imprecision in cluster assignment, which generalizes hard and fuzzy partitions. ...

• The paper presents evidential c-means algorithms with feature-weight learning.
• The algorithms introduce vector and matrix feature-weight learning.
• The algorithms create credal partition to represent uncertainty and imprecision.

Fog computing offers the benefit of low-latency computing thereby improving the Quality of Service (QoS) of low-latency applications. Hence, it is essential to distribute the applications in a balanced way across the different fog nodes, however, ...

With the rapid development in society, intermediaries play an increasingly important role in person-position matching decision-making. To obtain reasonable enterprise-intermediary matching and enterprise-candidate matching schemes under multiple ...