Expert Systems with Applications: An International Journal

We present a study of an artificial neural architecture that predict human ocular scanpaths while they are free-viewing different images types. This analysis is made by comparing different metrics that encompass scanpath patterns, these metrics ...

Implementing Integrated Management Systems (IMS) has become a prerequisite for transforming businesses into more competitive and sustainable enterprises. However, the various barriers impede the effective implementation of IMS. Although prior ...

• Proposing a multi-objective boxing match algorithm as human-based algorithm.
• Simulating the boxer’s behavior to attract a good support from his coach and fans.
• Validating the proposed algorithm to solve multi-objective optimization ...

In the last two decades, due to having fast computation after inventing computers and also considering real-world optimization problems, research on developing new algorithms for problem having more than one objective have been one of the ...

In this study, we attempt to present a three-way multi criteria decision-making (MCDM) technique with fuzzy soft dominance degree relation based on additive consistency to simultaneously choose the best alternative, rank alternatives, and ...

• Using fuzzy soft dominance degree relations, the three-way decision model is presented.
• Using θ-similarity classes, we suggest an optimization strategy to attain the best cost-sensitive granularity selection.
• An efficient method to ...

In the process of disassembly, it is difficult for workers who have been in working condition for a long time to ensure the high-quality completion of the tasks they undertake, which will lead to the reduction of disassembly profit. Providing ...

With the development of economic globalization, distributed hybrid flow shop scheduling problem (DHFSSP) has become prevalent in realistic manufacturing systems. Moreover, to accord with the actual production scenarios and satisfy the requirement ...

• This paper first investigates DAHFSSP-DRC with minimization TTD.
• A MILP model and a KBIG are proposed for DAHFSSP-DRC.
• The importance level of different knowledge is considered in KBIG.
• Experimental results prove the ...

Point cloud classification has emerged as a vital research area in several emerging applications, including robotics and autonomous driving. However, discriminative feature learning has long been a challenging issue owing to the irregularity and ...

• A novel hierarchical local–global framework is proposed for 3D point clouds.
• LFE block contains parallel Transformer branch and SMLP branch.
• LFE block can learn local high-dimensional semantic features of each point.
• GFE block ...

The optimal power flow (OPF) is one of the most noticeable and integral tools in the power system operation and control and aims to obtain the most economical combination of power plants to exactly serve the total demand of the system without any ...

Pre-trained Language Models (PLMs) have demonstrated remarkable performance in Natural Language Understanding (NLU) tasks, with continuous prompt-based fine-tuning further enhancing their capabilities. However, current methods rely on hand-...

K-anonymity is a widely used privacy-preserving technique which defends against linking attacks by suppression and generalization. The existing k-anonymity algorithms prevent attackers from illegally obtaining private information by constraining ...

• A hierarchical decision table for k-anonymity by sensitive decision is constructed.
• Multi-level personalized k-anonymity by sequential three-way decisions is proposed.
• Three practical algorithms of the proposed model and the ...

Psychological and neurological studies earlier suggested that a personality type can be determined by the whole face as well as by its sides. This article discusses novel research using deep neural networks that address the features of both sides ...

• An efficient EmoFormer cross-hemiface attention approach for Big five assessment.
• A novel emotional mid-level feature extractor for personality traits assessment.
• A novel cross-hemiface attention fusion strategy for personality ...

Extracting valuable insights from vast amounts of unstructured digital text presents significant challenges across diverse domains. This research addresses this challenge by proposing a novel pipeline-based system that generates domain-agnostic ...

Due to uncertain production conditions and external disturbances, there are a lot of noise in the industrial process dataset. Traditional denoising models can only solve a single noise problem. However, the noise in industrial process data has ...

• A feature selection method based on binary dandelion algorithm is proposed.
• The algorithm applies a sine-cosine operator and a restart strategy.
• Mutual information and quick bit mutation improve the performance of the algorithm.

Feature selection (FS) is an important data preprocessing technology for machine learning and data mining. Metaheuristic algorithm (MH) has been widely used in feature selection because of its powerful search function. This paper presents an ...

• Classification of wheat flour varieties by FT-MIR spectroscopy and chemometrics.
• FT-MIR spectral data were investigated using unsupervised and supervised models.
• LDA, SVM and ANN models showed the best results in wheat flour ...

Wheat varieties are grown in many countries throughout the world to produce grain and flour for foods, an outstanding and remarkable foodstuff that fulfills human nutritional needs. Methodologically, there is little known about how to distinguish ...

Structural system identification (ID) is an important tool for many structural and infrastructure applications, such as structural health monitoring and structural model updating. A novel physics-guided generative adversarial network (PG-GAN) is ...

For preventing landslide disasters caused by the slope collapse, it is crucial to research on the investigation of slope stability. For the very complex influence factors on the slope stability, nowadays, the studies on slope stability by using ...

As a fundamental spatiotemporal sequence forecasting problem, traffic prediction is pivotal in transportation management and urban computing. Nonetheless, the intricate and dynamic nature of spatiotemporal correlations presents significant ...

Renewable energy sources are progressively assuming a pivotal role in shaping our future, and wave energy stands out as a promising avenue due to its substantial potential and minimal ecological impact. Consequently, extensive research has been ...

• An improved algorithm applied to WEC layout optimization is proposed.
• A triple-layered information chaos improvement strategy is proposed.
• Compared four DE series algorithms and proved the strategy is powerful.
• Collected data ...

The increase in data variability and quantity makes it urgent for learning complex multivariate probability distributions. The state-of-the-art Tree Augmented Naive Bayes (TAN) classifier uses maximum weighted spanning tree (MWST) to graphically ...

• We extend TAN to identify the high-dependence relationships.
• Causal semantics are described in the form of DAG.
• Ensemble learning helps improve the topology robustness.

• Create proprietary database for immersed tunnel fires and made it publicly available.
• Propose fire location prediction model for extra-wide immersed tunnels.
• Design 6 immersed tunnels fire location detection models.

The confined spaces of extrawide immersed tunnels presents a significant challenge to the effective implementation of firefighting strategies in the event of a fire. In such an event, it is crucial to accurately and promptly identify the fire ...

Long-term time series forecasting has received a lot of popularity because of its great practicality. It is also an extremely challenging task since it requires using limited observations to predict values in the long future accurately. Recent ...

A deep hierarchical echo state network (DHESN) is designed for rectifying the shortcomings of the shallow coupled structure with less reservoir dynamics. This design is with reference to algal bloom which is a complex ecological phenomenon. ...

The joint selective maintenance and repairperson assignment problem with uncertain duration of maintenance actions is studied in this paper. This problem arises in mission-oriented assets that perform sequences of missions interspersed with ...

• A large-scale JSM-RAP with maintenance action duration uncertainty is studied.
• Piecewise-linear approximation is used to linearize the nonlinear objective function.
• Distributionally robust chance constraints with a Wasserstein ...

Electroencephalography (EEG) is capable of capturing the evocative neural information within the brain. As a result, it has been increasingly used for identifying neurological disorders, such as depression. In recent years, researchers have ...

The enhanced answer evaluation system is a cutting-edge automated tool that evaluates subjective answers in various contexts, such as educational assessments, surveys, and feedback forms. The proposed system leverages Natural Language Processing (...

• Evaluation using a three-pronged approach of Keyword, Semantic & NER scoring.
• Semantic scores enhance similarity matrix grading and impact evaluation.
• NER scores address proper noun issues.
• Deep Neural Network predicts actual ...

Person re-identification (Re-ID) technology plays an increasingly crucial role in intelligent surveillance systems. Widespread occlusion significantly impacts the performance of person Re-ID. Occluded person Re-ID refers to a pedestrian matching ...

• Summarize the visual transformer-based approach for occluded person Re-ID.
• Classify state-of-the-art approaches scientifically, comprehensively.
• Incorporate 3D person Re-ID & multimodal person Re-ID: Advancing the field.
• ...

The decomposition-based multi-objective evolutionary algorithm (MOEA/D) has been shown to effectively solve real-world multi-objective optimization problems (MOPs). The uniformly distributed weight vectors guide the population to continuously ...

• Using a nonlinear control function to balance exploration and exploitation.
• Applying a new matching pattern to reduce waste of computing resources.
• Improving offspring quality by a stable-state neighborhoods adjustment strategy.

The multi-layer perceptron (MLP) is a highly popular artificial neural network used for classification across various applications. Swarm intelligence algorithms, such as the grey wolf optimizer, battle royale optimizer, sine cosine algorithm, ...

• A reliable and efficient GWO variant for training MLP classifiers is proposed.
• The competing wolf leaders mechanism provides a flexible social leadership hierarchy.
• A population diversity-enhanced initiation method improves the ...