KINDI Center for Computing Research: Recent submissions
Now showing items 81-100 of 297
-
Generalized Model and Deep Reinforcement Learning-Based Evolutionary Method for Multitype Satellite Observation Scheduling
( Institute of Electrical and Electronics Engineers Inc. , 2024 , Article)Multitype satellite observation, including optical observation satellites, synthetic aperture radar (SAR) satellites, and electromagnetic satellites, has become an important direction in integrated satellite applications ... -
Localized Constrained-Domination Principle for Constrained Multiobjective Optimization
( Institute of Electrical and Electronics Engineers Inc. , 2024 , Article)The constrained-domination principle (CDP) is one of the most popular constraint-handling techniques (CHTs), since it is simple, nonparametric, and easily embedded in unconstrained multiobjective evolutionary algorithms ... -
Multimodal and Multiuser Semantic Communications for Channel-Level Information Fusion
( Institute of Electrical and Electronics Engineers Inc. , 2024 , Article)Recently, semantic communication emerged as one of the enabling technologies for intelligent communications and multimodal information fusion plays an important role therein, where various sensors collect environment ... -
An evolutionary multiobjective method based on dominance and decomposition for feature selection in classification
( Science China Press , 2024 , Article)Feature selection in classification can be considered a multiobjective problem with the objectives of increasing classification accuracy and decreasing the size of the selected feature subset. Dominance-based and ... -
UNIFIED DISCRETE DIFFUSION FOR SIMULTANEOUS VISION-LANGUAGE GENERATION
( International Conference on Learning Representations, ICLR , 2023 , Conference)The recently developed discrete diffusion models perform extraordinarily well in the text-to-image task, showing significant promise for handling the multi-modality signals. In this work, we harness these traits and present ... -
Support Vector Machine Based Models with Sparse Auto-encoder Based Features for Classification Problem
( Springer Science and Business Media Deutschland GmbH , 2023 , Conference)Auto-encoder is a special type of artificial neural network (ANN) that is used to learn informative features from data. In the literature, the generalization performance of several machine learning models have been improved ... -
Double Regularization-Based RVFL and edRVFL Networks for Sparse-Dataset Classification
( Springer Science and Business Media Deutschland GmbH , 2023 , Conference)In our previous work, the random vector functional link network (RVFL) and the ensemble deep RVFL network (edRVFL) have been proven to be competitive for tabular-dataset classification, and their sparse pre-trained versions ... -
Adaptive Scaling for U-Net in Time Series Classification
( Springer Science and Business Media Deutschland GmbH , 2023 , Conference)Convolutional Neural Networks such as U-Net are recently getting popular among researchers in many applications, such as Biomedical Image Segmentation. U-Net is one of the popular deep Convolutional Neural Networks which ... -
Random vector functional link network: Recent developments, applications, and future directions
( Elsevier , 2023 , Article)Neural networks have been successfully employed in various domains such as classification, regression and clustering, etc. Generally, the back propagation (BP) based iterative approaches are used to train the neural networks, ... -
A cultural evolution with a modified selection function and adaptive α-cognition procedure for numerical optimization
( Elsevier , 2023 , Article)In recent years, several population-based evolutionary and swarm algorithms have been developed and used in the literature. This work introduces an improved Cultural Algorithm with a modified selection function and a dynamic ... -
Ensemble reinforcement learning: A survey
( Elsevier , 2023 , Article Review)Reinforcement Learning (RL) has emerged as a highly effective technique for addressing various scientific and applied problems. Despite its success, certain complex tasks remain challenging to be addressed solely with a ... -
Online dynamic ensemble deep random vector functional link neural network for forecasting
( Elsevier , 2023 , Article)This paper proposes a three-stage online deep learning model for time series based on the ensemble deep random vector functional link (edRVFL). The edRVFL stacks multiple randomized layers to enhance the single-layer RVFL's ... -
A spectral-ensemble deep random vector functional link network for passive brain-computer interface
( Elsevier , 2023 , Article)Randomized neural networks (RNNs) have shown outstanding performance in many different fields. The superiority of having fewer training parameters and closed-form solutions makes them popular in small datasets analysis. ... -
Online learning using deep random vector functional link network
( Elsevier , 2023 , Article)Deep neural networks have shown their promise in recent years with their state-of-the-art results. Yet, backpropagation-based methods may suffer from time-consuming training process and catastrophic forgetting when performing ... -
A problem-specific knowledge based artificial bee colony algorithm for scheduling distributed permutation flowshop problems with peak power consumption
( Elsevier , 2023 , Article)A distributed permutation flowshop scheduling problem (DPFSP) with peak power consumption is addressed in this work. The instantaneous energy consumption of each factory cannot exceed a threshold. First, a mathematical ... -
Problem feature based meta-heuristics with Q-learning for solving urban traffic light scheduling problems
( Elsevier , 2023 , Article)An urban traffic light scheduling problem (UTLSP) is studied by using problem feature based meta-heuristics with Q-learning. The goal is to minimize the network-wise total delay time within a time window by finding a ... -
Probabilistic Wind Power Forecasting Using Optimized Deep Auto-Regressive Recurrent Neural Networks
( IEEE Computer Society , 2023 , Article)Wind power forecasting is very crucial for power system planning and scheduling. Deep neural networks (DNNs) are widely used in forecasting applications due to their exceptional performance. However, the DNNs' architectural ... -
Orthogonal Experimental Design Based Binary Optimization Without Iteration for Fault Section Diagnosis of Power Systems
( IEEE Computer Society , 2024 , Article)Fault section diagnosis (FSD) is considerably indispensable for the continuous and reliable electricity supply. In general, the analytical model of FSD is solved by derivative-free intelligent metaheuristic algorithms. ... -
Performance assessment and exhaustive listing of 500+ nature-inspired metaheuristic algorithms
( Elsevier , 2023 , Article)Metaheuristics are popularly used in various fields, and they have attracted much attention in the scientific and industrial communities. In recent years, the number of new metaheuristic names has been continuously growing. ... -
Knowledge-embedded constrained multiobjective evolutionary algorithm based on structural network control principles for personalized drug targets recognition in cancer
( Elsevier , 2024 , Article)The structural network control principle for identifying personalized drug targets (SNCPDTs) is a kind of constrained multiobjective optimization (CMO) problem with NP-hard features, which makes traditional mathematical ...
