Whale optimization algorithm: a systematic review of contemporary applications, modifications and developments

E2SVM: Electricity-Efficient SLA-aware Virtual Machine Consolidation approach in cloud data centers

Cloud data centers present a challenge to environmental sustainability because of their significant energy consumption. Additionally, performance degradation resulting from energy management solutions, such as virtual machine (VM) consolidation, impacts service level agreements (SLAs) between cloud service providers and users. Thus, to achieve a balance between efficient energy consumption and avoiding SLA violations, we propose a novel VM consolidation algorithm. Conventional algorithms result in unnecessary migrations when improperly selecting VMs. Therefore, our proposed E2SVM algorithm addresses this issue by selecting VMs with high load fluctuations and minimal resource usage from overloaded servers. These selected VMs are then placed on normally loaded servers, considering their stability index. Moreover, our approach prevents server underutilization by either applying all or no VM migrations. Simulation results demonstrate a 12.9% decrease in maximum energy consumption compared with the minimum migration time VM selection policy. In addition, a 47% reduction in SLA violations was observed when using the medium absolute deviation as the overload detection policy. Therefore, this approach holds promise for real-world data centers because it minimizes energy waste and maintains low SLA violations.

Solving Engineering Optimization Problems Based on Multi-Strategy Particle Swarm Optimization Hybrid Dandelion Optimization Algorithm

In recent years, swarm intelligence optimization methods have been increasingly applied in many fields such as mechanical design, microgrid scheduling, drone technology, neural network training, and multi-objective optimization. In this paper, a multi-strategy particle swarm optimization hybrid dandelion optimization algorithm (PSODO) is proposed, which is based on the problems of slow optimization speed and being easily susceptible to falling into local extremum in the optimization ability of the dandelion optimization algorithm. This hybrid algorithm makes the whole algorithm more diverse by introducing the strong global search ability of particle swarm optimization and the unique individual update rules of the dandelion algorithm (i.e., rising, falling and landing). The ascending and descending stages of dandelion also help to introduce more changes and explorations into the search space, thus better balancing the global and local search. The experimental results show that compared with other algorithms, the proposed PSODO algorithm greatly improves the global optimal value search ability, convergence speed and optimization speed. The effectiveness and feasibility of the PSODO algorithm are verified by solving 22 benchmark functions and three engineering design problems with different complexities in CEC 2005 and comparing it with other optimization algorithms.

Deep Learning Paradigm and Its Bias for Coronary Artery Wall Segmentation in Intravascular Ultrasound Scans: A Closer Look

BACKGROUND AND MOTIVATION

Coronary artery disease (CAD) has the highest mortality rate; therefore, its diagnosis is vital. Intravascular ultrasound (IVUS) is a high-resolution imaging solution that can image coronary arteries, but the diagnosis software via wall segmentation and quantification has been evolving. In this study, a deep learning (DL) paradigm was explored along with its bias.

METHODS

Using a PRISMA model, 145 best UNet-based and non-UNet-based methods for wall segmentation were selected and analyzed for their characteristics and scientific and clinical validation. This study computed the coronary wall thickness by estimating the inner and outer borders of the coronary artery IVUS cross-sectional scans. Further, the review explored the bias in the DL system for the first time when it comes to wall segmentation in IVUS scans. Three bias methods, namely (i) ranking, (ii) radial, and (iii) regional area, were applied and compared using a Venn diagram. Finally, the study presented explainable AI (XAI) paradigms in the DL framework.

FINDINGS AND CONCLUSIONS

UNet provides a powerful paradigm for the segmentation of coronary walls in IVUS scans due to its ability to extract automated features at different scales in encoders, reconstruct the segmented image using decoders, and embed the variants in skip connections. Most of the research was hampered by a lack of motivation for XAI and pruned AI (PAI) models. None of the UNet models met the criteria for bias-free design. For clinical assessment and settings, it is necessary to move from a paper-to-practice approach.

Node deployment optimization of underwater wireless sensor networks using intelligent optimization algorithm and robot collaboration

This study aims to optimize the node deployment of underwater wireless sensor networks (UWSNs) using intelligent optimization algorithms and robot collaboration technology to enhance network performance and coverage. The study employs the chemical reaction optimization (CRO) algorithm, which combines the advantages of genetic algorithms, simulated annealing algorithms, and ant colony algorithms. The CRO algorithm is enhanced through a structure correction function to determine the optimal node deployment scheme to achieve effective and optimal coverage control of the UWSN. Additionally, the flexibility and autonomy of robots are leveraged to improve the efficiency of node deployment and address the unique challenges posed by the underwater environment. Furthermore, the study conducts a comparative analysis of different intelligent optimization algorithms and demonstrates the effectiveness and advantages of the enhanced CRO algorithm in optimizing node deployment for UWSNs. The study findings reveal that the improved algorithm achieves an average coverage rate of 95.66%, significantly outperforming traditional intelligent optimization algorithms. The coverage of UWSNs can be significantly improved by utilizing the enhanced CRO algorithm and robot collaboration technology for node deployment optimization, which offers an effective approach for achieving optimal node deployment. Moreover, the rational deployment of nodes enhances the monitoring capability, resource utilization efficiency, and accuracy of environmental monitoring in underwater networks. The results of this study hold great practical significance for underwater environment monitoring, marine resource exploration, and marine scientific research.

Topic sentiment analysis based on deep neural network using document embedding technique

Sentiment Analysis (SA) is a domain- or topic-dependent task since polarity terms convey different sentiments in various domains. Hence, machine learning models trained on a specific domain cannot be employed in other domains, and existing domain-independent lexicons cannot correctly recognize the polarity of domain-specific polarity terms. Conventional approaches of Topic Sentiment Analysis perform Topic Modeling (TM) and SA sequentially, utilizing the previously trained models on irrelevant datasets for classifying sentiments that cannot provide acceptable accuracy. However, some researchers perform TM and SA simultaneously using topic-sentiment joint models, which require a list of seeds and their sentiments from widely used domain-independent lexicons. As a result, these methods cannot find the polarity of domain-specific terms correctly. This paper proposes a novel supervised hybrid TSA approach, called Embedding Topic Sentiment Analysis using Deep Neural Networks (ETSANet), that extracts the semantic relationships between the hidden topics and the training dataset using Semantically Topic-Related Documents Finder (STRDF). STRDF discovers those training documents in the same context as the topic based on the semantic relationships between the Semantic Topic Vector, a newly introduced concept that encompasses the semantic aspects of a topic, and the training dataset. Then, a hybrid CNN-GRU model is trained by these semantically topic-related documents. Moreover, a hybrid metaheuristic method utilizing Grey Wolf Optimization and Whale Optimization Algorithm is employed to fine-tune the hyperparameters of the CNN-GRU network. The evaluation results demonstrate that ETSANet increases the accuracy of the state-of-the-art methods by 1.92%.

A Systematic Review of the Whale Optimization Algorithm: Theoretical Foundation, Improvements, and Hybridizations

Despite the simplicity of the whale optimization algorithm (WOA) and its success in solving some optimization problems, it faces many issues. Thus, WOA has attracted scholars' attention, and researchers frequently prefer to employ and improve it to address real-world application optimization problems. As a result, many WOA variations have been developed, usually using two main approaches improvement and hybridization. However, no comprehensive study critically reviews and analyzes WOA and its variants to find effective techniques and algorithms and develop more successful variants. Therefore, in this paper, first, the WOA is critically analyzed, then the last 5 years' developments of WOA are systematically reviewed. To do this, a new adapted PRISMA methodology is introduced to select eligible papers, including three main stages: identification, evaluation, and reporting. The evaluation stage was improved using three screening steps and strict inclusion criteria to select a reasonable number of eligible papers. Ultimately, 59 improved WOA and 57 hybrid WOA variants published by reputable publishers, including Springer, Elsevier, and IEEE, were selected as eligible papers. Effective techniques for improving and successful algorithms for hybridizing eligible WOA variants are described. The eligible WOA are reviewed in continuous, binary, single-objective, and multi/many-objective categories. The distribution of eligible WOA variants regarding their publisher, journal, application, and authors' country was visualized. It is also concluded that most papers in this area lack a comprehensive comparison with previous WOA variants and are usually compared only with other algorithms. Finally, some future directions are suggested.

Whale optimization with random contraction and Rosenbrock method for COVID-19 disease prediction

Coronavirus Disease 2019 (COVID-19), instigated by severe acute respiratory syndrome coronavirus 2 (SARS-CoV-2), has hugely impacted global public health. To identify and intervene in critically ill patients early, this paper proposes an efficient, intelligent prediction model based on the machine learning approach, which combines the improved whale optimization algorithm (RRWOA) with the k-nearest neighbor (KNN) classifier. In order to improve the problem that WOA is prone to fall into local optimum, an improved version named RRWOA is proposed based on the random contraction strategy (RCS) and the Rosenbrock method. To verify the capability of the proposed algorithm, RRWOA is tested against nine classical metaheuristics, nine advanced metaheuristics, and seven well-known WOA variants based on 30 IEEE CEC2014 competition functions, respectively. The experimental results in mean, standard deviation, the Friedman test, and the Wilcoxon signed-rank test are considered, proving that RRWOA won first place on 18, 24, and 25 test functions, respectively. In addition, a binary version of the algorithm, called BRRWOA, is developed for feature selection problems. An efficient prediction model based on BRRWOA and KNN classifier is proposed and compared with seven existing binary metaheuristics based on 15 datasets of UCI repositories. The experimental results show that the proposed algorithm obtains the smallest fitness value in eleven datasets and can solve combinatorial optimization problems, indicating that it still performs well in discrete cases. More importantly, the model was compared with five other algorithms on the COVID-19 dataset. The experiment outcomes demonstrate that the model offers a scientific framework to support clinical diagnostic decision-making. Therefore, RRWOA is an effectively improved optimizer with efficient value.

An Optimization-Linked Intelligent Security Algorithm for Smart Healthcare Organizations

IoT-enabled healthcare apps are providing significant value to society by offering cost-effective patient monitoring solutions in IoT-enabled buildings. However, with a large number of users and sensitive personal information readily available in today's fast-paced, internet, and cloud-based environment, the security of these healthcare systems must be a top priority. The idea of safely storing a patient's health data in an electronic format raises issues regarding patient data privacy and security. Furthermore, with traditional classifiers, processing large amounts of data is a difficult challenge. Several computational intelligence approaches are useful for effectively categorizing massive quantities of data for this goal. For many of these reasons, a novel healthcare monitoring system that tracks disease processes and forecasts diseases based on the available data obtained from patients in distant communities is proposed in this study. The proposed framework consists of three major stages, namely data collection, secured storage, and disease detection. The data are collected using IoT sensor devices. After that, the homomorphic encryption (HE) model is used for secured data storage. Finally, the disease detection framework is designed with the help of Centered Convolutional Restricted Boltzmann Machines-based whale optimization (CCRBM-WO) algorithm. The experiment is conducted on a Python-based cloud tool. The proposed system outperforms current e-healthcare solutions, according to the findings of the experiments. The accuracy, precision, F1-measure, and recall of our suggested technique are 96.87%, 97.45%, 97.78%, and 98.57%, respectively, according to the proposed method.

Swarm Intelligence in Internet of Medical Things: A Review

Continuous advancements of technologies such as machine-to-machine interactions and big data analysis have led to the internet of things (IoT) making information sharing and smart decision-making possible using everyday devices. On the other hand, swarm intelligence (SI) algorithms seek to establish constructive interaction among agents regardless of their intelligence level. In SI algorithms, multiple individuals run simultaneously and possibly in a cooperative manner to address complex nonlinear problems. In this paper, the application of SI algorithms in IoT is investigated with a special focus on the internet of medical things (IoMT). The role of wearable devices in IoMT is briefly reviewed. Existing works on applications of SI in addressing IoMT problems are discussed. Possible problems include disease prediction, data encryption, missing values prediction, resource allocation, network routing, and hardware failure management. Finally, research perspectives and future trends are outlined.

Velocity pausing particle swarm optimization: a novel variant for global optimization

Particle swarm optimization (PSO) is one of the most well-regard metaheuristics with remarkable performance when solving diverse optimization problems. However, PSO faces two main problems that degrade its performance: slow convergence and local optima entrapment. In addition, the performance of this algorithm substantially degrades on high-dimensional problems. In the classical PSO, particles can move in each iteration with either slower or faster speed. This work proposes a novel idea called velocity pausing where particles in the proposed velocity pausing PSO (VPPSO) variant are supported by a third movement option that allows them to move with the same velocity as they did in the previous iteration. As a result, VPPSO has a higher potential to balance exploration and exploitation. To avoid the PSO premature convergence, VPPSO modifies the first term of the PSO velocity equation. In addition, the population of VPPSO is divided into two swarms to maintain diversity. The performance of VPPSO is validated on forty three benchmark functions and four real-world engineering problems. According to the Wilcoxon rank-sum and Friedman tests, VPPSO can significantly outperform seven prominent algorithms on most of the tested functions on both low- and high-dimensional cases. Due to its superior performance in solving complex high-dimensional problems, VPPSO can be applied to solve diverse real-world optimization problems. Moreover, the velocity pausing concept can be easily integrated with new or existing metaheuristic algorithms to enhance their performances. The Matlab code of VPPSO is available at: https://uk.mathworks.com/matlabcentral/fileexchange/119633-vppso.

A Systematic Review on Metaheuristic Optimization Techniques for Feature Selections in Disease Diagnosis: Open Issues and Challenges

There is a need for some techniques to solve various problems in today's computing world. Metaheuristic algorithms are one of the techniques which are capable of providing practical solutions to such issues. Due to their efficiency, metaheuristic algorithms are now used in healthcare data to diagnose diseases practically and with better results than traditional methods. In this study, an efficient search has been performed where 173 papers from different research databases such as Scopus, Web of Science, PubMed, PsycINFO, and others have been considered impactful in diagnosing the diseases using metaheuristic techniques. Ten metaheuristic techniques have been studied, which include spider monkey, shuffled frog leaping algorithm, cuckoo search algorithm, ant lion technique of optimization, lion optimization technique, moth flame technique, bat-inspired algorithm, grey wolf algorithm, whale optimization, and dragonfly technique of optimization for selecting and optimizing the features to predict heart disease, Alzheimer's disease, brain disorder, diabetes, chronic disease features, liver disease, covid-19, etc. Besides, the framework has also been shown to provide information on various phases behind the execution of metaheuristic techniques to predict diseases. The study's primary goal is to present the contribution of the researchers by demonstrating their methodology to predict diseases using the metaheuristic techniques mentioned above. Later, their work has also been compared and evaluated using accuracy, precision, F1 score, error rate, sensitivity, specificity, an area under a curve, etc., to help the researchers to choose the right field and methods for predicting the diseases in the future.

Optimization and Its Implementation Impact of Two-Modes Controller Fractional Approximation for Buck Converters

Additional degrees of freedom in a fractional-order control strategy for power electronic converters are well received despite the lack of reliable tuning methods. Despite artificial/swarm intelligence techniques have been used to adjust controller parameters to improve more than one characteristic/property at the same time, smart tuning not always leads to realizable structures or reachable parameter values. Thus, adjustment boundaries to ensure controller viability are needed. In this manuscript the fractional-order approach is described in terms of El-Khazali biquadratic module, which produces the lowest order approximation, instead of using a definition. A two-modes controller structure is synthesize depending on uncontrolled plant needs and parameters are adjusted through particle swarm and genetic optimization algorithms for comparison. Two error-based minimization criteria are used to consider output performance into the process. Two restrictions complement the optimization scheme, one seeks to ensure desired robustness while the other prevents from synthesizing a high-gain controller. Optimization results showed similarity between minima obtained and significant difference between parameters of those controller optimized without the proposed constraints was determined. Numerical and experimental results are provide to validate proposed approach effectiveness. Effective regulation, good tracking characteristic and robustness in the presence of load variations are the main results.

Monophenolase assay using excitation-emission matrix fluorescence and ELMAN neural network assisted by whale optimization algorithm

Tyrosinase plays a vital role for melanogenesis and inherently involves both monophenolase activity and diphenolase activity. Monophenolase catalyzes hydroxylation of tyrosine to l-DOPA (L-3,4-dihydroxyphenylalanine). Real-time monophenolase assay method is of outstanding interest for both scientific research and industrial application. A combined strategy of three-dimensional excitation-emission matrix (EEM) fluorescence spectra and artificial neural network was developed to determine monophenolase activity. A quantitation system for tyrosine in presence of l-DOPA was designed based on ELMAN neural network. Principal component analysis (PCA) was conducted to reduce the dimensionality of fluorescence spectra. Four principal components was used as input variables. Whale optimization algorithm (WOA) was implemented to optimize the initial weights and threshold network. Real-time concentration of tyrosine in monophenolase reaction was monitored to calculate the initial velocity for tyrosine consumption. The exclusive monophenolase activity without interference from diphenolase reaction was determined. Limit of detection (LOD) for monophenolase assay is 0.0113 U mL^-1. Using the proposed method, enzyme kinetics for monophenolase was investigate. K_m was calculated as 14.16 μM. Inhibitor for monophenolase was screened by using model molecule kojic acid with IC₅₀ of 3.49 μM. The assay method exhibited a promising prospect to characterize the kinetics and inhibitor of monophenolase.

An enhanced whale optimization algorithm with improved dynamic opposite learning and adaptive inertia weight strategy

Whale Optimization Algorithm (WOA), as a newly proposed swarm-based algorithm, has gradually become a popular approach for optimization problems in various engineering fields. However, WOA suffers from the poor balance of exploration and exploitation, and premature convergence. In this paper, a new enhanced WOA (EWOA), which adopts an improved dynamic opposite learning (IDOL) and an adaptive encircling prey stage, is proposed to overcome the problems. IDOL plays an important role in the initialization part and the algorithm iterative process of EWOA. By evaluating the optimal solution in the current population, IDOL can adaptively switch exploitation/exploration modes constructed by the DOL strategy and a modified search strategy, respectively. On the other hand, for the encircling prey stage of EWOA in the latter part of the iteration, an adaptive inertia weight strategy is introduced into this stage to adaptively adjust the prey’s position to avoid falling into local optima. Numerical experiments, with unimodal, multimodal, hybrid and composition benchmarks, and three typical engineering problems are utilized to evaluate the performance of EWOA. The proposed EWOA also evaluates against canonical WOA, three sub-variants of EWOA, three other common algorithms, three advanced algorithms and four advanced variants of WOA. Results indicate that according to Wilcoxon rank sum test and Friedman test, EWOA has balanced exploration and exploitation ability in coping with global optimization, and it has obvious advantages when compared with other state-of-the-art algorithms.

Eight pruning deep learning models for low storage and high-speed COVID-19 computed tomography lung segmentation and heatmap-based lesion localization: A multicenter study using COVLIAS 2.0

BACKGROUND

COVLIAS 1.0: an automated lung segmentation was designed for COVID-19 diagnosis. It has issues related to storage space and speed. This study shows that COVLIAS 2.0 uses pruned AI (PAI) networks for improving both storage and speed, wiliest high performance on lung segmentation and lesion localization.

METHOD

ology: The proposed study uses multicenter ∼9,000 CT slices from two different nations, namely, CroMed from Croatia (80 patients, experimental data), and NovMed from Italy (72 patients, validation data). We hypothesize that by using pruning and evolutionary optimization algorithms, the size of the AI models can be reduced significantly, ensuring optimal performance. Eight different pruning techniques (i) differential evolution (DE), (ii) genetic algorithm (GA), (iii) particle swarm optimization algorithm (PSO), and (iv) whale optimization algorithm (WO) in two deep learning frameworks (i) Fully connected network (FCN) and (ii) SegNet were designed. COVLIAS 2.0 was validated using "Unseen NovMed" and benchmarked against MedSeg. Statistical tests for stability and reliability were also conducted.

RESULTS

Pruning algorithms (i) FCN-DE, (ii) FCN-GA, (iii) FCN-PSO, and (iv) FCN-WO showed improvement in storage by 92.4%, 95.3%, 98.7%, and 99.8% respectively when compared against solo FCN, and (v) SegNet-DE, (vi) SegNet-GA, (vii) SegNet-PSO, and (viii) SegNet-WO showed improvement by 97.1%, 97.9%, 98.8%, and 99.2% respectively when compared against solo SegNet. AUC > 0.94 (p < 0.0001) on CroMed and > 0.86 (p < 0.0001) on NovMed data set for all eight EA model. PAI <0.25 s per image. DenseNet-121-based Grad-CAM heatmaps showed validation on glass ground opacity lesions.

CONCLUSIONS

Eight PAI networks that were successfully validated are five times faster, storage efficient, and could be used in clinical settings.

COVLIAS 2.0-cXAI: Cloud-Based Explainable Deep Learning System for COVID-19 Lesion Localization in Computed Tomography Scans

Background: The previous COVID-19 lung diagnosis system lacks both scientific validation and the role of explainable artificial intelligence (AI) for understanding lesion localization. This study presents a cloud-based explainable AI, the “COVLIAS 2.0-cXAI” system using four kinds of class activation maps (CAM) models. Methodology: Our cohort consisted of ~6000 CT slices from two sources (Croatia, 80 COVID-19 patients and Italy, 15 control patients). COVLIAS 2.0-cXAI design consisted of three stages: (i) automated lung segmentation using hybrid deep learning ResNet-UNet model by automatic adjustment of Hounsfield units, hyperparameter optimization, and parallel and distributed training, (ii) classification using three kinds of DenseNet (DN) models (DN-121, DN-169, DN-201), and (iii) validation using four kinds of CAM visualization techniques: gradient-weighted class activation mapping (Grad-CAM), Grad-CAM++, score-weighted CAM (Score-CAM), and FasterScore-CAM. The COVLIAS 2.0-cXAI was validated by three trained senior radiologists for its stability and reliability. The Friedman test was also performed on the scores of the three radiologists. Results: The ResNet-UNet segmentation model resulted in dice similarity of 0.96, Jaccard index of 0.93, a correlation coefficient of 0.99, with a figure-of-merit of 95.99%, while the classifier accuracies for the three DN nets (DN-121, DN-169, and DN-201) were 98%, 98%, and 99% with a loss of ~0.003, ~0.0025, and ~0.002 using 50 epochs, respectively. The mean AUC for all three DN models was 0.99 (p < 0.0001). The COVLIAS 2.0-cXAI showed 80% scans for mean alignment index (MAI) between heatmaps and gold standard, a score of four out of five, establishing the system for clinical settings. Conclusions: The COVLIAS 2.0-cXAI successfully showed a cloud-based explainable AI system for lesion localization in lung CT scans.

Optimization of the Curved Metal Damper to Improve Structural Energy Dissipation Capacity

Structural curved metal dampers are implemented in various applications to mitigate the damages at a specific area efficiently. A stable and saturated hysteretic behavior for the in-plane direction is dependent on the shape of a curved-shaped damper. However, it has been experimentally shown that the hysteretic behavior in the conventional curved-shaped damper is unstable, mainly as a result of bi-directional deformations. Therefore, it is necessary to conduct shape optimization for curved dampers to enhance their hysteretic behavior and energy dissipation capability. In this study, the finite element (FE) model built in ABAQUS, is utilized to obtain optimal shape for the curved-shaped damper. The effectiveness of the model is checked by comparisons of the FE model and experimental results. The parameters for the optimization include the curved length and shape of the damper, and the improved approach is conducted by investigating the curved sections. In addition, the design parameters are represented by B-spline curves (to ensure enhanced system performance), regression analysis is implemented to derive optimization formulations considering energy dissipation, constitutive material model, and cumulative plastic strain. Results determine that the energy dissipation capacity of the curved steel damper could be improved by 32% using shape optimization techniques compared to the conventional dampers. Ultimately, the study proposes simple optimal shapes for further implementations in practical designs.

Automated Intracranial Hematoma Classification in Traumatic Brain Injury (TBI) Patients Using Meta-Heuristic Optimization Techniques

Traumatic Brain Injury (TBI) is a devastating and life-threatening medical condition that can result in long-term physical and mental disabilities and even death. Early and accurate detection of Intracranial Hemorrhage (ICH) in TBI is crucial for analysis and treatment, as the condition can deteriorate significantly with time. Hence, a rapid, reliable, and cost-effective computer-aided approach that can initially capture the hematoma features is highly relevant for real-time clinical diagnostics. In this study, the Gray Level Occurrence Matrix (GLCM), the Gray Level Run Length Matrix (GLRLM), and Hu moments are used to generate the texture features. The best set of discriminating features are obtained using various meta-heuristic algorithms, and these optimal features are subjected to different classifiers. The synthetic samples are generated using ADASYN to compensate for the data imbalance. The proposed CAD system attained 95.74% accuracy, 96.93% sensitivity, and 94.67% specificity using statistical and GLRLM features along with KNN classifier. Thus, the developed automated system can enhance the accuracy of hematoma detection, aid clinicians in the fast interpretation of CT images, and streamline triage workflow.

The Whale Optimization Algorithm Approach for Deep Neural Networks

One of the biggest challenge in the field of deep learning is the parameter selection and optimization process. In recent years different algorithms have been proposed including bio-inspired solutions to solve this problem, however, there are many challenges including local minima, saddle points, and vanishing gradients. In this paper, we introduce the Whale Optimisation Algorithm (WOA) based on the swarm foraging behavior of humpback whales to optimise neural network hyperparameters. We wish to stress that to the best of our knowledge this is the first attempt that uses Whale Optimisation Algorithm for the optimisation task of hyperparameters. After a detailed description of the WOA algorithm we formulate and explain the application in deep learning, present the implementation, and compare the proposed algorithm with other well-known algorithms including widely used Grid and Random Search methods. Additionally, we have implemented a third dimension feature analysis to the original WOA algorithm to utilize 3D search space (3D-WOA). Simulations show that the proposed algorithm can be successfully used for hyperparameters optimization, achieving accuracy of 89.85% and 80.60% for Fashion MNIST and Reuters datasets, respectively.

A new variant of deep belief network assisted with optimal feature selection for heart disease diagnosis using IoT wearable medical devices

In this paper, the information related to heart disease using IoT wearable devices is collected from any benchmark site, which is publicly available. With the collected data, feature extraction process is performed initially, in which heart rate, zero crossing rate, and higher order statistical features like standard deviation, median, skewness, kurtosis, variance, mean, peak amplitude, and entropy are extracted. For acquiring most significant features, the optimal feature selection process is implemented. As a novel contribution, the feature selection process is done by the hybrid optimization algorithm called PS-GWO by integrating GWO and PSO. Next, the extracted features are subjected to a famous deep learning algorithm named modified DBN, in which the activation function and number of hidden neurons is optimized using the same developed hybrid algorithm to improve the heart diagnosis accuracy. From the analysis, for the test case 1, the accuracy of the developed PS-GWO-DBN is 60%, 52.5%, 35% and 35% increased than NN, KNN, SVM, and DBN. For test case 2, the accuracy of the proposed PS-GWO-DBN is 26%, 24%, 21.6% and 17% increased than NN, KNN, SVM, and DBN, respectively. The accuracy of the designed PS-GWO-DBN is 26% advanced than NN, 24% advanced than KNN, 21.6% advanced than SVM and 17% advanced than DBN for test case 3. Thus, the proposed heart disease prediction model using PS-GWO-DBN performs better than other classifiers.