Applied Soft Computing

Accurate individual cattle identification is crucial for modern precision cattle farming. However, practical applications encounter challenges due to factors such as shooting distance and angles, cattle movements, weather conditions, and cattle ...

• Face recognition in uncontrolled scenes was proposed to identify individual cows.
• Embedding enhancement module enhanced recognition accuracy for low-recognizable faces.
• Embedding optimization module improved robustness to face ...

This review paper provides a detailed evaluation of the existing landscape and future trends in applying machine learning and deep learning approaches for predicting concrete strength in construction engineering. The study contextualizes the ...

• Thorough review of on the use of ML and DL in concrete strength prediction is offered.
• Critical insights and patterns in the prediction using ML and DL are identified.
• Research directions in ML for concrete strength prediction are ...

In healthcare monitoring, the quality of medical services and patient outcomes are significantly influenced by the unnatural variations emphasizing the importance of effective control and monitoring strategies. In such scenarios the quality is ...

• Innovative fuzzy control charts, including FMACC, FWMACC, and FMRCC, are proposed for individual measurements in health monitoring.
• The proposed control charts use fuzzy control rules to detect small shifts in complex medical data.

The traditional optimal power flow problem (OPF) usually centers on thermal generators, which have limited fuel for power generation, while emissions from the network system are commonly overlooked. However, the rising appreciation of renewable ...

• Introduction of a novel MG-Jaya Algorithm to solve the Multi-objective OPF (MOOPF) problem.
• Addressing the MOOPF Problem that involves RES, considering the different constraints.
• Memory-Based Strategy integration enhances ...

Nowadays, predicting user retweeting behavior in microblogging networks has gained considerable attention. Solving this problem allows for understanding the underlying mechanism of information diffusion and analyzing diffusion's evolution ...

• predicting user retweeting behavior in microblogging networks has gained much attention in recent years.
• Many factors affect user retweeting behavior, but the effect of indirect social influence strength has not been considered in ...

Autonomous underwater vehicles (AUVs) are rapidly advancing in ocean exploration. High-performance path planning techniques are essential for AUVs. Path planning for AUVs is a multi-faceted challenge, necessitating careful consideration of safety,...

• A multiple swarm co-evolutionary algorithm (MCO) is proposed for AUV path planning.
• A co-evolution mechanism is designed to balance the exploratory and exploitation capabilities.
• Dynamic optimal particles are designed for ...

The utilization of flexible job shops is on the rise, driven by the decreasing life cycle of consumer products. In dynamic flexible job shops, the occurrence of disruptive events like machine breakdown, tool wear, and new job arrivals is common, ...

• Introduced a comprehensive mathematical model for MODFJSP, defining three optimization objectives and constraints.
• Developed MOBWSA inspired by black widow spider’s mating behavior, incorporating superior evolutionary processes.
• ...

The metaverse, a virtually shared digital world where individuals interact, create, and explore, has witnessed rapid evolution and widespread adoption. Communication between avatars is crucial to their actions in the metaverse. Advances in ...

• Metaverse: Evolving rapidly, avatars' communication is pivotal in this digital realm.
• Significant natural language processing advances enhance metaverse conversation, elevating user experience.
• Deep learning-powered VSR ...

Multimodal Multi-Objective Problems (MMOPs) are frequently encountered in the real world. Traditional Multimodal Multi-Objective Evolutionary Algorithms (MMEAs) often find multiple Pareto optimal solutions with the same objective values. However, ...

• An effective multimodal multi-objective optimization algorithm is designed.
• Applying SOM neural networks to Multimodal Multi-Objective Evolutionary Algorithms.
• A Coevolutionary mechanism is designed to guide populations away from ...

The presence of a large amount of quality-related but hard-to-measure variables usually makes effective monitoring of industrial processes difficult, and even impossible. Soft computing techniques and digital twins can revolutionize standard ...

• A novel soft sensor framework is proposed to enable multi-variable prediction and digital twins.
• The Fourier amplitude sensitivity test is used to select optimal auxiliary variables.
• A Probabilistic regularization method is learned ...

Feature selection is a key technique for data dimensionality reduction, and there are many challenges in facing the exponential expansion phenomenon of high-dimensional decision space. In order to improve the quality of feature selection, we ...

• Proposed quadratic interpolation mechanism with memory information interaction.
• A reverse correction mechanism is proposed to resolve invalid probability flips.
• An improved discrete whale optimization algorithm is proposed.
• The ...

The 0–1, Multidimensional Knapsack Problem (MKP) is a classical NP-hard combinatorial optimization problem with many engineering applications. In this paper, we propose a novel algorithm combining evolutionary computation with the exact algorithm ...

• We propose an efficient and practical algorithm for solving the 0–1 Multidimensional Knapsack Problem in this paper.
• The algorithm takes advantages of Evolutionary Computation and Large Neighborhood Search.
• It works well in solving ...

Autonomous bulldozers encounter critical challenges in dynamic path planning in complex construction environments such as dynamic obstacles and narrow passages. Bio-inspired neural networks (BINN) are commonly employed for real-time path planning ...

• An activity-value-optimised Bio-inspired Neural Networks is proposed for autonomous bulldozers dynamic path planning.
• An adaptive cell decomposition method is proposed to model the environment with low computational effort.
• A path ...

A basic task of Pawlak conflict analysis is to cluster agents based on their attitudes towards various issues. When ratings of agents are imprecise and uncertain, for example, as represented by a Pythagorean fuzzy situation table, single-measure ...

• Provide the trisection-fusion method of three-way conflict analysis.
• Develop the fusion-trisection method of three-way conflict analysis.
• Illustrate the effectiveness of two multi-measure based methods.

Converting greenhouse gases into value-added chemical compounds has been widely studied in chemical science and engineering for sustainable industry. In particular, nonoxidative coupling of methane (NOCM) that transforms methane into useful ...

• AI-based method to optimize engineering conditions for green chemistry.
• Active learning with metaheuristics-guided data generation.
• 68.84% reduced error in predicting methane conversion performance.
• Data-agnostic criterion for ...

Determining the correct mushroom species with the necessary ecological characteristics is critical to continue mushroom production, which is essential in gastronomy. The mushroom farmers and collectors technique may help identify toxic mushrooms ...

• The proposed model automatically detects mushroom species.
• Grad-CAM, LIME, and Heatmap methods based on CNN architectures are used to visualize mushroom images.
• The ASO algorithm has been successfully applied to residual block-...

When handling global optimization problems by metaheuristic algorithms (MAs), an important yet difficult assignment is to keep a tradeoff between the swarm’s diversity and convergence. Hence, this paper develops an enhanced sine cosine algorithm ...

• A SCA algorithm with elite pool strategy is raised.
• It has good potential to handle real-world engineering problems.
• The developed model is more effective than other popular algorithms.

Although the advancement of technology has made data processing quite easier, it is still an enormous task, especially if the volume is large and can affect the learning capability of the classifier. Instance Reduction techniques can be employed ...

• A novel approach for instance reduction by hybridization with optimization algorithms to reduce storage requirements.
• Combination of Elitist and Min-Max Ant Systems is adopted.
• New hyperparameters are introduced to enhance the ...

This survey paper presents an overview of recent application of mat-heuristics on combinatorial optimisation problems (COPs) from 2018 to 2024. In this review, we categorise the mat-heuristics into six categories based on three integration types (...

• We systematically categorise mat-heuristics into six categories based on the combinations of integration types and approaches.
• We analyse solution methodologies employing mat-heuristics for various COPs in terms of mechanism and their ...

Currently, it has become very relevant that machine learning techniques can provide an explanation of the results they generate, which is even more relevant in certain domains, called critical, such as health and energy, among others. For this ...

• Analyze the explainability of LAMDA and Fuzzy Cognitive Maps.
• An explainability method based on causal inference for fuzzy cognitive maps.
• An explainability method based on the degrees of membership of variables to classes.
• ...

Having effective learning and retrieval phases of satisfiability logic in Discrete Hopfield Neural Network models ensures optimal synaptic weight management, which consequently leads to the production of optimal final neuron states. However, the ...

• A novel logical rule as output symbols of DHNN was proposed.
• HDEA was utilized to optimize the learning phase of DHNN.
• A mutation-based retrieval phase of DHNN was proposed.
• The results showed that the proposed model ...

Addressing expensive many-objective optimization problems (MaOPs) is a formidable challenge owing to their intricate objective spaces and high computational demands. Surrogate-assisted evolutionary algorithms (SAEAs) have gained prominence ...

• Article presents ALSAEA, an algorithm for many-objective optimization based on activity level.
• A two-screening strategy is proposed to update the training set.
• ALSAEA introduces an activity level standard, improving the training ...

Data-driven soft sensors have emerged as indispensable tools for predicting quality variables in complex industrial processes because of their cost-effectiveness and ease of maintenance. In particular, soft sensors based on deep learning have ...

• A deep learning method for soft sensor modeling uses a semisupervised pretraining strategy integrating spatiotemporal structure preservation.
• The developed soft sensor is deployed in an industrial scenario where soft sensing technology ...

Autonomous Surface Vessels (ASVs) excel at undertaking hazardous tasks, garnering significant attention recently. Particularly, ASV cooperative defense is a crucial application for protecting harbors and combating smugglers. Here, ASVs intercept ...

• Achieving cooperative defense of ASVs by behavior cloning and reinforcement learning.
• Proposing bi-level controllers for the underactuated ASVs to imitate actions.
• Designing reward with hybrid terms to effectively drive policy ...

In recent years, with the rise of health consciousness, people’s demand for fitness has steadily increased. Utilizing automated human action recognition technology to monitor users’ movements during exercise continuously would help prevent ...

Display Omitted

• Developed a multi-task model using Spatio Temporal Graph Convolutional Networks for gym fitness.
• An automated fitness adviser system is designed to enhance the exercise experience in fitness gyms.
• Integrated Five Primary Kinetic ...

In this paper soft computing fuzzy proposition/rule based adaptive extreme learning is proposed. This article illustrates the impact of agricultural solar panel (AgSP) and its operating condition/state during the farming seasons and hence safety ...

• Operating state of PV energy system is identified using ART-LM for all dust conditions.
• Accurate mismatch extracted by fuzzy rule extreme learning to protect PV energy system panels.
• Fuzzy propositions are confirmed by fractional ...

Graph adversarial Networks (GANs) have shown state-of-the-art results in numerous application domains. While GANs are difficult to be trained to generate distribution from data descriptions. In order to solve this problem, GraphGAN is an ...

• This model addresses the challenges of mode collapse and gradient anomalies.
• Combining generative adversarial networks and evolutionary algorithms.
• This model achieves better experimental results than the original model. model.

Predicting occult lymph node metastasis in non-small cell lung cancer (NSCLC) patients is pivotal for tailoring appropriate surgical and therapeutic interventions. This prognostic factor remains underexplored, largely due to the intricate ...

In this research, we proposed a two-step method called OLNM-Net to enhance the learning and extraction of occult lymph node image features for prediction. The architecture of the OLNM-Net network for NSCLC occult lymph node metastasis ...

With the rapid advancement of deep learning technology, significant achievements have been made in the field of general object detection. However, challenges still remain in the detection of tiny objects. There are two main drawbacks: (1) static ...

• A label assignment strategy is proposed for the framework of tiny object detection.
• A dynamic calculation strategy is presented to determine prior for tiny objects.
• A new Gaussian receptive field distance is designed for tiny ...