Information Sciences: an International Journal

Bio-inspired computing is an appropriate platform for developing artificial intelligent machines based on the behavioral and functional principles of the brain. Bio-inspired machines have been proven to play a significant role in the ...

• Evaluation of the no-stationarity data distribution in federated learning scenarios.

Transferring data across nodes could raise concerns about data security and privacy. Federated learning is a tech- nological remedy for these problems. However, in a real federated scenario, there are two main ...

It is well-known that, the classical gradient-descent-based neural network (CGNN) model is used widely for the time-invariant problem solving. However, it is an extremely common problem for the time varying cases in the practical ...

In the real word, due to the existence of uncertainty in decision-making information, it is often difficult to accurately evaluate utility values of alternatives. Recently, a series of discrete choice models based on fuzzy subjective ...

Graph-based unsupervised feature selection algorithms have been shown to be promising for handling unlabeled and high-dimensional data. Whereas, the vast majority of those algorithms usually involve two independent processes, i.e., ...

Unsupervised Domain Adaptation (UDA) is a popular machine learning technique to reduce the distribution discrepancy among domains. In previous UDA methods, only convolutional neural networks (CNNs) or vision transformers (ViTs) are ...

With federated learning, one of the most notable features is that it can update global model parameter without using the users’ local data. However, various security and privacy problems still exist in the process of federated ...

Extreme Multi-label Text Classification (XMTC) is a key task of finding the most relevant labels from a large label set for a document. Although some deep learning-based methods have shown great success in XMTC, they still suffer from ...

• A 14-layer model with high predictive performance is proposed.
• The model fuses ...

The most widely used model in stock price forecasting is the long short-term memory network (LSTM). However, LSTM has its limitations, as it does not recognize and extract features well and has a representational bottleneck. ...

A learner model with fast learning and compact architecture is expected for industrial data modeling. To achieve these goals during stochastic configuration networks (SCNs) construction, we propose an improved version of SCNs in this ...

• We propose a multi-task adaptive recurrent graph attention network to predict travel demand.

Accurate travel demand forecasting at the regional level benefits to urban traffic management and service operations. Irregular regions can be naturally represented by graphs, and thus, graph neural network (GNN) is rapidly becoming ...

Advances in recent techniques for scientific data collection in the era of big data allow for the systematic accumulation of large quantities of data at various data-capturing sites. Similarly, exponential growth in the development of ...

• Explainable framework for meta-learning.
• Efficiency and high causality.

With the growing convergence of artificial intelligence and daily life scenarios, the application scenarios for intelligent decision methods are becoming increasingly complex. The development of various machine learning algorithms has ...

The performance of differential evolution (DE) significantly depends on the settings of mutation strategies and control parameters. Inappropriate settings may cause an imbalance between exploration and exploitation of the algorithm, ...

Multi-label learning aims to solve classification problems where instances are associated with a set of labels. In reality, it is generally easy to acquire unlabeled data but expensive or time-consuming to label them, and this ...

• SADE-MI for mixed-integer expensive constrained optimization problems is proposed.

Many Surrogate-Assisted Evolutionary Algorithms (SAEAs) have been developed for expensive constrained optimization problems (ECOPs) with continuous variables. However, there exist some ECOPs that contain mixed-integer variables in real ...

Previous years, people deeply discussed the cross-migrativity properties of the same binary operators, like two overlap functions. Based on the previous works, we extend the study of the cross-migrativity about two same operators to ...

• New non-iterative reasoning algorithm for Fuzzy Cognitive Maps (FCMs) is developed.

A Fuzzy Cognitive Map (FCM) is a causal knowledge graph connecting concepts using directional and weighted connections making it an effective approach for reasoning and decision making. However, the modelling and reasoning capabilities ...

An automated theorem proving (ATP) system's capacity for reasoning is significantly influenced by the inference rules it uses. The recently introduced standard contradiction separation (S-CS) inference rule extends binary resolution to ...

• An experimental analysis on effect of inconsistency rate on prediction accuracy (PA) is conducted.

An experiment was conducted to investigate the effect of the inconsistency rate (IR) of granulated datasets on classification performance. Unsupervised (equal-width interval, EWI) and supervised (minimum description length, MDL) ...

• Integrated Stratified LBWA and Fuzzy Rough Hamacher Combined Compromise Solution is proposed.

The Integration of Unmanned Aerial Vehicles (UAVs) into transportation systems has numerous benefits, ranging from the ability to record real-time data to having high mobility and broad vision. Because of the increasing levels of ...

• A novel framework named Event-Aware Graph Attention Fusion Network is proposed.

Accurate road traffic speed prediction has a critical role in intelligent transportation systems and smart cities. This task is very challenging because of the complexity of road network structures, as well as various other ...

• Logic AND operation in FNNs did not depict the uncertainty of pixels in images well.

The clarity of medical images is crucial for doctors to identify and diagnose different diseases. High-resolution images have more detailed information and clearer content than low-resolution images. It is well known that medical ...

• A new separability detection criterion possessing broad applicability is designed.

Problem decomposition plays an important role when applying cooperative coevolution (CC) to large-scale global optimization problems. However, most learning-based decomposition algorithms only apply to additively separable problems, ...

• Both spatial and temporal features of roads are integrated for link anomaly detection;

Road anomaly detection aims to find a small group of roads that are exceptional with respect to the rest of the physical links in a transportation network, posing great challenges for spatial data mining and urban infrastructure ...

Entropy regularization is an important approach to improve exploration and enhance policy stability for reinforcement learning. However, in previous study, entropy regularization is applied only to action spaces. In this paper, we ...

• A new supervised fuzzy measure learning algorithm is proposed for combining classifiers.

Fuzzy measure-based aggregations allow taking interactions among coalitions of the input sources into account. Their main drawback when applying them in real-world problems, such as combining classifier ensembles, is how to define the ...

With the ubiquitous of GPS-equipped devices, spatial crowdsourcing (SC) technology has been widely utilized in our daily life. As a novel computing paradigm, it hires mobile users as workers who physically move to the location of the ...

A common approach to constructing fuzzy rough sets (FRSs) is using t-norms. Furthermore, establishing multi-granulation fuzzy rough sets (MGFRSs) is also usually undertaken by means of t-norms. However, most of these sets cannot ...