Export Citations
Save this search
Please login to be able to save your searches and receive alerts for new content matching your search criteria.
- research-articleFebruary 2024
Convolutional architecture search based on particle swarm algorithm for functional brain network classification▪
Applied Soft Computing (APSC), Volume 149, Issue PBDec 2023https://doi.org/10.1016/j.asoc.2023.111049AbstractThe functional brain network (FBN) classification based on convolutional neural networks (CNN) is of great significance for discovery and diagnosis of brain diseases, and has attracted increasing attention. However, all the CNN architectures of ...
Highlights- As we know, it is the first work that applies PSO-NAS to functional brain network classification.
- This novel individual representation can effectively extract multi-level topological features of brain networks.
- This novel SVM-based ...
- research-articleFebruary 2024
Influence Maximization in social networks using discretized Harris’ Hawks Optimization algorithm
Applied Soft Computing (APSC), Volume 149, Issue PBDec 2023https://doi.org/10.1016/j.asoc.2023.111037AbstractInfluence Maximization (IM) is the task of determining k optimal influential nodes in a social network to maximize the influence spread using a propagation model. IM is a prominent problem for viral marketing and helps significantly in social ...
Highlights- An optimized Local Influence Estimator for Influence Maximization is proposed.
- The expected influence spread is maximized by a set of extracted seed nodes.
- A community structures is employed for narrowing down the search space.
- research-articleFebruary 2024
Semi-disentangled non-negative matrix factorization for rating prediction
Applied Soft Computing (APSC), Volume 149, Issue PBDec 2023https://doi.org/10.1016/j.asoc.2023.111034AbstractRating predictions have been extensively used in evaluation websites for recommendation tasks in recent past. Due to the single data category and the simple way of feature interaction, traditional rating prediction methods do not portray the ...
Highlights- Proposed a Semi-Disentangled NMF model by which splits user- and item-latent embeddings into two blocks: the whiten and blacked blocks. The former enhances the internal interpretability of SDNMF by introducing external prior knowledge, ...
- research-articleFebruary 2024
Interpretable self-organizing map assisted interactive multi-criteria decision-making following Pareto-Race
Applied Soft Computing (APSC), Volume 149, Issue PBDec 2023https://doi.org/10.1016/j.asoc.2023.111032AbstractThe problem-solving task of the multi-criteria decision-making (MCDM) approach involves decision makers’ (DMs’) interaction by incorporating their preferences to arrive at one or more preferred near Pareto-optimal solution(s). The Pareto-Race is ...
Graphical abstractDisplay Omitted
Highlights- Interactive MCDM using iSOM-aided Pareto-Race technique.
- Introducing metrics such as closeness to constraint and robustness in Pareto-Race.
- Visual comprehension of goodness of preferred solution and features in each iteration.
- ...
- research-articleFebruary 2024
An integrated differential evolution algorithm for reconfigurable manufacturing systems
Applied Soft Computing (APSC), Volume 149, Issue PBDec 2023https://doi.org/10.1016/j.asoc.2023.111025AbstractProduct platforms consider an effective strategy to empower mass customization (MC) in a reconfigurable manufacturing system (RMS) to have the capacity to reconfigure the hardware and manage resources at all organisational and functional levels. ...
Highlights- This paper reports an integrated DE for Reconfigurable Manufacturing Systems.
- Enhanced heuristics for product platforms’ formation and assembly line are proposed.
- New efficient package-based mathematical model is introduced.
- ...
-
- research-articleFebruary 2024
Circular economy oriented future building information processing: PSO for CNN approach
Applied Soft Computing (APSC), Volume 149, Issue PBDec 2023https://doi.org/10.1016/j.asoc.2023.111013AbstractWith the acceleration of urbanization, resource depletion is becoming increasingly serious. The innovative strategy of resource utilization is of great significance to the development of new green building. Therefore, this paper combines ...
Highlights- This paper proposes an improved IU-Net model and the full CNN structure is optimized based on PSO.
- This paper analyzes the significance of the IU-Net model of full CNN based on PSO for building information analysis and feature ...
- research-articleFebruary 2024
Fault detection with confidence level evaluation for perception module of autonomous vehicles based on long short term memory and Gaussian Mixture Model
Applied Soft Computing (APSC), Volume 149, Issue PBDec 2023https://doi.org/10.1016/j.asoc.2023.111010AbstractThe reliability of perception is crucial for developing higher levels of autonomy to enhance the safety and performance of fully autonomous vehicles. As a result, fault detection in the perception module is an essential function for autonomous ...
Highlights- Sensor fault detection based on the analytical redundancy.
- Level of failure in the sensors is estimated by a continuous factor.
- Reflect the characteristics of the various sensors and perception algorithms.
- The proposed method ...
- research-articleFebruary 2024
Feedforward neural network-based augmented salp swarm optimizer for accurate software development cost forecasting
Applied Soft Computing (APSC), Volume 149, Issue PBDec 2023https://doi.org/10.1016/j.asoc.2023.111008AbstractThis research proposes the use of feed-forward backpropagation neural networks (FFNN) to develop an accurate cost forecasting model in light of the challenges associated with forecasting software development costs (FSDC). The salp swarm algorithm ...
Highlights- The software development cost forecasting issue is tackled using the FFNN.
- SSA optimizes the FFNN parameters.
- SSA is optimized using two enhancement strategies.
- Enhanced versions of the SSA are evaluated using 19 test ...
- research-articleFebruary 2024
A hybrid electricity load prediction system based on weighted fuzzy time series and multi-objective differential evolution
Applied Soft Computing (APSC), Volume 149, Issue PBDec 2023https://doi.org/10.1016/j.asoc.2023.111007AbstractWith advances in science and technology, the demand for electricity is increasing dramatically. Consequently, reliable short-term power load prediction is critical to ensure the safety, efficiency, and cost-effectiveness of electricity grids. ...
Highlights- Propose a novel hybrid forecasting model based on fuzzy theory.
- Apply fuzzy theory to electricity load forecasting.
- The proposed model outperforms 6 comparison models for power load prediction.
- The proposed hybrid model ...
- research-articleFebruary 2024
Towards white box modeling of compressive strength of sustainable ternary cement concrete using explainable artificial intelligence (XAI)
Applied Soft Computing (APSC), Volume 149, Issue PBDec 2023https://doi.org/10.1016/j.asoc.2023.110997AbstractSince the production of sustainable ternary cement concrete (TCC) involves a large range of constituents which can affect the compressive strength (CS) of TCC in different ways, the evaluation of CS in a unified manner is necessary. Unlike the ...
Highlights- XAI using SHAP based machine learning model predictions for ternary cement concrete compressive strength.
- Comparative analysis of conventional machine learning (ML) and ensemble ML models.
- Higher accuracy with ensemble ML models ...
- research-articleFebruary 2024
Uncertainty aware neural network from similarity and sensitivity▪
- H.M. Dipu Kabir,
- Subrota Kumar Mondal,
- Sadia Khanam,
- Abbas Khosravi,
- Shafin Rahman,
- Mohammad Reza Chalak Qazani,
- Roohallah Alizadehsani,
- Houshyar Asadi,
- Shady Mohamed,
- Saeid Nahavandi,
- U. Rajendra Acharya
Applied Soft Computing (APSC), Volume 149, Issue PADec 2023https://doi.org/10.1016/j.asoc.2023.111027AbstractRecent uncertainty quantification approaches lack transparency. Algorithms often perform poorly in an input domain and the reason for poor performance remains unknown. Therefore, we present a neural network training method that considers similar ...
Highlights- Proposing a high performing NN based uncertainty quantification from similarity-based data preparation.
- Demonstrating scripts of Bayesian, Direct NN and Similarity based uncertainty quantification methods.
- Visualizing the effect of ...
- research-articleFebruary 2024
Auction-based deep learning-driven smart agricultural supply chain mechanism
Applied Soft Computing (APSC), Volume 149, Issue PADec 2023https://doi.org/10.1016/j.asoc.2023.111009AbstractAgricultural product prices are subject to significant fluctuations due to variations in sales cycles, impacting people's quality of life and farmers' income while potentially giving rise to social problems. To address this issue in the smart ...
Highlights- This study combines CEEMD with LSTM to construct an end-to-end agricultural product price prediction model.
- Based on the prediction results, corresponding auction mechanisms will be developed to achieve the optimal allocation of ...
- research-articleFebruary 2024
Multi-objective decomposition evolutionary algorithm with objective modification-based dominance and external archive
Applied Soft Computing (APSC), Volume 149, Issue PADec 2023https://doi.org/10.1016/j.asoc.2023.111006AbstractIn practice, the multi-objective optimization problem (MOP) is typically challenging in two aspects. On the one hand, its Pareto front has imbalanced search difficulties; on the other hand, its search space contains many dominance resistant ...
Highlights- Decomposing an MOP into multi-objective subproblems to diversity preservation.
- A dominance criterion is proposed to deal with dominance resistant solutions.
- An external archive is used to remove extreme solutions.
- research-articleFebruary 2024
Digital twin model construction of robot and multi-object under stacking environment for grasping planning
- Juntong Yun,
- Gongfa Li,
- Du Jiang,
- Manman Xu,
- Feng Xiang,
- Li Huang,
- Guozhang Jiang,
- Xin Liu,
- Yuanmin Xie,
- Bo Tao,
- Zifan Fang
Applied Soft Computing (APSC), Volume 149, Issue PADec 2023https://doi.org/10.1016/j.asoc.2023.111005AbstractObject grasping is the basic function for robots to complete various tasks. However, it is still a hot and difficult problem to grasp object in multi-object stacking environment. A digital twin model construction method for robot grasping under ...
Highlights- Robot digital twin model is constructed based on twin model construction guidelines to realize the collection of information, virtual model driving of robot physical entities and Robot visualization.
- A stacked object interaction ...
- research-articleFebruary 2024
Volleyball premier league algorithm with ACO and ALNS for simultaneous pickup–delivery location routing problem
Applied Soft Computing (APSC), Volume 149, Issue PADec 2023https://doi.org/10.1016/j.asoc.2023.111004AbstractThe reverse logistics problem, which involves customer returns and incurs high additional logistics costs, has become a topic of increasing interest. This problem is modeled as the location routing problem with simultaneous pickup and delivery ...
Highlights- Redesigned strategies for solving combinatorial optimization problems, extending the VPL algorithm.
- Improved Bellman’s algorithm for determining depot locations and constructing vehicle routes.
- Integrated ALNS and ACO sub-...
- research-articleFebruary 2024
A heterogeneous fuzzy collaborative intelligence approach: Air quality monitor selection study
Applied Soft Computing (APSC), Volume 149, Issue PADec 2023https://doi.org/10.1016/j.asoc.2023.111000AbstractSmart backpacks with novel functions have an enormous potential market. Therefore, the ability to embed smart functions (e.g., air quality detection) into a backpack design is critical. This study aimed to select an air quality monitor suitable ...
Highlights- The suitability of an air quality monitor for smart backpacks is evaluated.
- A heterogeneous fuzzy collaborative intelligence approach is proposed.
- Experts can apply different types of decision-making methods to make a joint ...
- research-articleFebruary 2024
Multi-agent target search strategy optimization: Hierarchical reinforcement learning with multi-criteria negative feedback
Applied Soft Computing (APSC), Volume 149, Issue PADec 2023https://doi.org/10.1016/j.asoc.2023.110999AbstractRecently, using unmanned platforms to perform target search tasks has received extensive attention and research. The complexity of the search scenario and the unpredictability of the target movement pose significant challenges for unmanned ...
Highlights- We propose a new reinforcement learning method for the multi-agent target search strategy optimization problem.
- We design a novel two-stage reward function based on convex polygon theory to handle reward sparsity.
- Our method ...
- research-articleFebruary 2024
Optimization of time based fuzzy multi-objective reliability redundancy allocation problem for x j − o u t − o f − m system using tuning and neighborhood based fuzzy MOPSO algorithm
Applied Soft Computing (APSC), Volume 149, Issue PADec 2023https://doi.org/10.1016/j.asoc.2023.110998AbstractIn this paper, a time based fuzzy multi objective reliability redundancy allocation problem (FMORRAP) is proposed for the x j − o u t − o f − m series–parallel system. The main objective is to maximize the system reliability with minimization of ...
Highlights- A time based fuzzy multi-objective reliability redundancy allocation problem is introduced.
- Triangular fuzzy number is used to make the model more flexible and reliable.
- Tuning and neighborhood based fuzzy MOPSO (TNF-MOPSO) ...
- research-articleFebruary 2024
Stealthy dynamic backdoor attack against neural networks for image classification
Applied Soft Computing (APSC), Volume 149, Issue PADec 2023https://doi.org/10.1016/j.asoc.2023.110993AbstractDeep Neural Networks (DNNs) are vulnerable to backdoor attacks, which are external entity model providers that can inject backdoors into the network for illegal purposes. Current attack methods rely on manipulated images with embedded triggers to ...
Highlights- We employ a novel dynamic backdoor attack against neural networks (NNSDB).
- NNSDB produces adversarial perturbations as trigger patterns using Generative Adversarial Networks.
- NNSDB achieves satisfactory attack performance and can ...
- research-articleFebruary 2024
Constructing convolutional neural network by utilizing nematode connectome: A brain-inspired method
Applied Soft Computing (APSC), Volume 149, Issue PADec 2023https://doi.org/10.1016/j.asoc.2023.110992AbstractConvolutional neural networks have achieved impressive results in areas such as computer vision tasks. Recently, more complex architectures have been designed that add additional operations and connections to the standard architecture to enable ...
Highlights- A brain-inspired connection pattern is proposed to construct the convolutional neural network called the nematode connectome neural network (NCNN).
- The NCNN is constructed by transforming biological connectomes into connection graphs ...