An Optimisation-Driven Prediction Method for Automated Diagnosis and Prognosis

Santucci, Valentino; Milani, Alfredo; Caraffini, Fabio

doi:10.3390/math7111051

Cited by 20 publications

(13 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…PSO has been applied to ML as well as research for performance improvement, such as a PSO convolutional neural network (PSO-CNN), which uses a PSO to classify images [ 17 , 18 ], linearly decreasing weight PSO (LDW-PSO) for convolutional neural network (CNN) hyperparameter optimization [ 19 ], and PSO and CNNs for lung nodule analysis [ 20 ]. Self-adapted particle swarm estimation of distribution algorithms (sa-PSEDA) apply PSO for optimization-driven prediction (ODP), a new classification method for automatic medical diagnosis and prognosis prediction [ 21 ]. Another paper used PSO enhanced with ANNs to solve complex problems in civil engineering [ 22 ].…”

Section: Background and Related Workmentioning

confidence: 99%

FedPSO: Federated Learning Using Particle Swarm Optimization to Reduce Communication Costs

Park

Suh

Lee

2021

Sensors

View full text Add to dashboard Cite

Federated learning is a learning method that collects only learned models on a server to ensure data privacy. This method does not collect data on the server but instead proceeds with data directly from distributed clients. Because federated learning clients often have limited communication bandwidth, communication between servers and clients should be optimized to improve performance. Federated learning clients often use Wi-Fi and have to communicate in unstable network environments. However, as existing federated learning aggregation algorithms transmit and receive a large amount of weights, accuracy is significantly reduced in unstable network environments. In this study, we propose the algorithm using particle swarm optimization algorithm instead of FedAvg, which updates the global model by collecting weights of learned models that were mainly used in federated learning. The algorithm is named as federated particle swarm optimization (FedPSO), and we increase its robustness in unstable network environments by transmitting score values rather than large weights. Thus, we propose a FedPSO, a global model update algorithm with improved network communication performance, by changing the form of the data that clients transmit to servers. This study showed that applying FedPSO significantly reduced the amount of data used in network communication and improved the accuracy of the global model by an average of 9.47%. Moreover, it showed an improvement in loss of accuracy by approximately 4% in experiments on an unstable network.

show abstract

Section: Background and Related Workmentioning

confidence: 99%

FedPSO: Federated Learning Using Particle Swarm Optimization to Reduce Communication Costs

Park

Suh

Lee

2021

Sensors

View full text Add to dashboard Cite

show abstract

“…Some popular and new methods are particle swarm optimization (PSO) [65], [66], ant colony optimization (ACO) [67], bacterial foraging optimization (BFO) [68]- [70], teaching-learning based optimizer (TLBO) [71], gray wolf optimizer (GWO) [45], [72], moth-flame optimization (MFO) [73]- [75], moth search algorithm (MSA) [76], grasshopper optimization algorithm (GOA) [77]- [79], whale optimization algorithm (WOA) [27], [80]- [82], fruit fly optimization algorithm (FOA) [83]- [85] and Harris hawks optimizer (HHO) [86]. Owing to its strong global optimization capability, these MAs have applied in many scenarios, including medical diagnosis, machine learning, engineering design, energy management, job scheduling, and pharmaceutical industry [87]- [98]. As a new member of MAs, SCA has a simple structure and can be implemented easily.…”

Section: Proposed Coscamentioning

confidence: 99%

Predicting Cervical Hyperextension Injury: A Covariance Guided Sine Cosine Support Vector Machine

et al. 2020

View full text Add to dashboard Cite

This study proposes an effective intelligent predictive model for prediction of cervical hyperextension injury. The prediction model is constructed by combing an improved sine cosine algorithm (SCA) with support vector machines (SVM), which is named COSCA-SVM. The core of the developed model is the COSCA method that combines the opposition-based learning mechanism and covariance mechanism to boost and recover the exploratory competence of SCA. The proposed COSCA approach is utilized to optimize the two critical parameters of the SVM, and it is also employed to catch the optimal feature subset. Based on the optimal parameter combination and feature subset, COSCA-SVM is able to make self-directed prediction of cervical hyperextension injury. The proposed COSCA was compared with other well-known and effective methods using 23 benchmark problems. Simulation results verify that the proposed COSCA is significantly superior to studied methods in dealing with majority of benchmark problems. Meanwhile, the proposed COSCA-SVM is compared with six other machine learning approaches considering a reallife dataset. Results have shown that the proposed COSCA-SVM can achieve better classification routine and higher stability on all four indicators. Therefore, we can expect that COSCA-SVM can be a promising building block for predicting cervical hyperextension injury.

show abstract

“…The estimation of distribution algorithm (EDA) framework has been demonstrated in [13] to have high performance despite little memory requirements, it was combined with PSO in [14] and was used to estimate and preserve the distribution information of particles' historical memories (personal best positions) to help the algorithm break out of local minimum solutions. The particle swarm estimation of distribution algorithms (PSDA) was also implemented in [15] for optimal-driven-projection of automated medical diagnosis and prognosis. Medical diagnosis is a key process in clinical medicine for identifying diseases, reducing cost, and enhancing accuracy.…”

Section: Swarm Intelligencementioning

confidence: 99%

Developing a New Robust Swarm-Based Algorithm for Robot Analysis

et al. 2020

View full text Add to dashboard Cite

Metaheuristics are incapable of analyzing robot problems without being enhanced, modified, or hybridized. Enhanced metaheuristics reported in other works of literature are problem-specific and often not suitable for analyzing other robot configurations. The parameters of standard particle swarm optimization (SPSO) were shown to be incapable of resolving robot optimization problems. A novel algorithm for robot kinematic analysis with enhanced parameters is hereby presented. The algorithm is capable of analyzing all the known robot configurations. This was achieved by studying the convergence behavior of PSO under various robot configurations, with a view of determining new PSO parameters for robot analysis and a suitable adaptive technique for parameter identification. Most of the parameters tested stagnated in the vicinity of strong local minimizers. A few parameters escaped stagnation but were incapable of finding the global minimum solution, this is undesirable because accuracy is an important criterion for robot analysis and control. The algorithm was trained to identify stagnating solutions. The algorithm proposed herein was found to compete favorably with other algorithms reported in the literature. There is a great potential of further expanding the findings herein for dynamic parameter identification.

show abstract

An Optimisation-Driven Prediction Method for Automated Diagnosis and Prognosis

Cited by 20 publications

References 63 publications

FedPSO: Federated Learning Using Particle Swarm Optimization to Reduce Communication Costs

FedPSO: Federated Learning Using Particle Swarm Optimization to Reduce Communication Costs

Predicting Cervical Hyperextension Injury: A Covariance Guided Sine Cosine Support Vector Machine

Developing a New Robust Swarm-Based Algorithm for Robot Analysis

Contact Info

Product

Resources

About