Information Sciences: an International Journal

The focus of our work is the ad hoc table retrieval task, which aims to rank a list of structured tabular objects in response to a user query. Given the importance of this task, various methods have already been proposed in the ...

• H ∞ stabilization problem for memristive neural networks with delays and disturbances is investigated.

This work explores memristive neural networks’ (MNNs) stability and stabilization problems by considering the time-varying delay and external disturbance. First, the MNNs were transformed into a tractable model by defining the logical ...

• Differential evolution with adaptive mutation strategy based on landscape information is proposed.

Differential evolution (DE) is the most efficient evolutionary algorithm widely used to solve continuous or discrete numerical optimization problems. However, the performance of DE highly depends on the choice of mutation strategy. In ...

As a first attempt, the L 2 - L ∞ state estimation issue of the high-order inertial neural networks with time-varying delay is put forward in this paper. A more direct method, non-reduced order method, is adopted here rather than ...

As one of the prevalent topic mining methods, neural topic modeling has attracted a lot of interests due to the advantages of low training costs and strong generalisation abilities. However, the existing neural topic models may suffer ...

An adaptive fuzzy output tracking control scheme is presented for a class of strict-feedback systems with an unknown control gain in this paper. An ideal controller that can achieve finite-time stabilization of the filtered tracking ...

PageRank is a classic measure that effectively evaluates the importance of nodes in large graphs. It has been applied in numerous applications spanning data mining, Web algorithms, recommendation systems, load balancing, search and ...

Pareto dominance-based multi-objective evolutionary algorithms (PDMOEAs) encounter scalability issues due to the lack of selection pressure as the dimensionality of objective space increases. In addition, PDMOEAs combat difficulties in ...

• Both the sliding variables of linear and integral-type are designed depending on the singular matrix of the singular MJS, based on which the uniformly ...

This paper is concerned with the problems of dynamic practical-sliding-mode control (SMC) and estimation of unknown functions for singular Markovian jump systems (MJSs) with system perturbations, by using an ellipsoidal-type interval ...

Q-learning (QL) is a popular method for control problems, which approximates the maximum expected action value using the maximum estimated action value, thus it suffers from positive overestimation bias. Various algorithms have been ...

• Context-enhanced mechanism fosters sentence embeddings learning in closed domains.

Sentence representation approaches have been widely used and proven to be effective in many text modeling tasks and downstream applications. Many recent proposals are available on learning sentence representations based on deep neural ...

With the continuous expansion of Internet of Things (IoT) devices, edge computing mode has emerged in recent years to overcome the shortcomings of traditional cloud computing mode, such as high delay, network congestion, and large ...

Knowledge distillation (KD) transfers knowledge from a heavy teacher network to a lightweight student network while maintaining the student’s performance closely to that of the teacher. However, the large gap between the teacher and ...

• Landscape analysis is extended to constrained multiobjective optimization.
• New ...

Despite the increasing interest in constrained multiobjective optimization in recent years, constrained multiobjective optimization problems (CMOPs) are still insufficiently understood and characterized. For this reason, the selection ...

The backpropagation (BP) neural network has been widely used in many fields. However, it is still a great challenge to design the architecture and obtain optimal parameters for BP neural networks. For improving the generalization ...

• Presenting an approach to dynamically adjusting the grouping of decision variables when the number of decision variables changes.

Multi-objective optimization problems (MOPs) with changing decision variables exist in the actual industrial production and daily life, which have changing Pareto sets and complex relations among decision variables and are difficult to ...

• MEMD- LSTM model for multi-step ahead stock price forecasting was built.
• Multi-...

Accurate and reliable multi-step-ahead forecasting of stock price indexes over long-term future trends is challenging for capital investors and decision-makers. This study developed a hybrid stock price index forecasting modelling ...

In label distribution learning, high dimensionality is one of the most prominent characteristics of the data, which increases the model complexity and computational cost. Feature selection is an efficient technique to mitigate the “...

This paper considers the distributed prescribed-time optimization problem of multi-agent systems (MASs). Considering the strongly convex function of time-invariant for each agent, the two-stage distributed prescribed-time optimization ...

This study deals with the peak-to-peak fuzzy filtering problem for a class of nonlinear discrete-time systems with analog fading channels and communication protocol, in which the nonlinear system is modeled by the Takagi-Sugeno fuzzy ...

The present work is devoted to studying the synchronization problem of multi-weighted coupled Cohen-Grossberg neural networks (CCGNNs) and multi-weighted delayed coupled Cohen-Grossberg neural networks (DCCGNNs). First, we investigated ...

• Asynchronous sequential machines are vulnerable to permanent sensor faults.
• ...

This paper presents fault diagnosis and fault-tolerant corrective control for a class of asynchronous sequential machines (ASMs). In the considered problem setting, a permanent fault may occur to the sensor in the feedback channel so ...

The novel coronavirus disease 2019 (COVID-19), caused by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), has unique epidemiological characteristics that include presymptomatic and asymptomatic infections, resulting in a ...

Pairwise relational information is a useful way of providing partial supervision in domains where class labels are difficult to acquire. This work presents a clustering model that incorporates pairwise annotations in the form of must-...

Feature embedding methods have been proposed in the literature to represent sequences as numeric vectors to be used in some bioinformatics investigations, such as family classification and protein structure prediction.

...

In the field of time series forecasting, deep learning and dynamics-based methods are two main research directions. The former focuses on the temporal information of the data while the latter emphasizes on the spatial information of ...

Data collected from industrial sites commonly contains outliers or noise that obey unknown distributions, making it challenging to establish an accurate data-driven model. Therefore, this paper proposes a novel robust stochastic ...

The formation of deep learning architectures is challenged in several aspects, among the major and fundamental steps to develop an effective image parsing network is feature selection. In addition, the exploration of context ...