Optimizing Deep Learning for Computer-Aided Diagnosis of Lung Diseases: An Automated Method Combining Evolutionary Algorithm, Transfer Learning, and Model Compression

Recent developments in Computer Vision have presented novel opportunities to tackle complex healthcare issues,particularly in the field of lung disease diagnosis.One promising avenue involves the use of chest X-Rays,which are commonly utilized in radiology.To fully exploit their potential,researchers have suggested utilizing deep learning methods to construct computer-aided diagnostic systems.However,constructing and compressing these systems presents a significant challenge,as it relies heavily on the expertise of data scientists.To tackle this issue,we propose an automated approach that utilizes an evolutionary algorithm(EA)to optimize the design and compression of a convolutional neural network(CNN)for X-Ray image classification.Our approach accurately classifies radiography images and detects potential chest abnormalities and infections,including COVID-19.Furthermore,our approach incorporates transfer learning,where a pre-trainedCNNmodel on a vast dataset of chest X-Ray images is fine-tuned for the specific task of detecting COVID-19.This method can help reduce the amount of labeled data required for the task and enhance the overall performance of the model.We have validated our method via a series of experiments against state-of-the-art architectures.

An Opposition-Based Learning-Based Search Mechanism for Flying Foxes Optimization Algorithm

The flying foxes optimization(FFO)algorithm,as a newly introduced metaheuristic algorithm,is inspired by the survival tactics of flying foxes in heat wave environments.FFO preferentially selects the best-performing individuals.This tendency will cause the newly generated solution to remain closely tied to the candidate optimal in the search area.To address this issue,the paper introduces an opposition-based learning-based search mechanism for FFO algorithm(IFFO).Firstly,this paper introduces niching techniques to improve the survival list method,which not only focuses on the adaptability of individuals but also considers the population’s crowding degree to enhance the global search capability.Secondly,an initialization strategy of opposition-based learning is used to perturb the initial population and elevate its quality.Finally,to verify the superiority of the improved search mechanism,IFFO,FFO and the cutting-edge metaheuristic algorithms are compared and analyzed using a set of test functions.The results prove that compared with other algorithms,IFFO is characterized by its rapid convergence,precise results and robust stability.

Enhancing Cancer Classification through a Hybrid Bio-Inspired Evolutionary Algorithm for Biomarker Gene Selection

In this study,our aim is to address the problem of gene selection by proposing a hybrid bio-inspired evolutionary algorithm that combines Grey Wolf Optimization(GWO)with Harris Hawks Optimization(HHO)for feature selection.Themotivation for utilizingGWOandHHOstems fromtheir bio-inspired nature and their demonstrated success in optimization problems.We aimto leverage the strengths of these algorithms to enhance the effectiveness of feature selection in microarray-based cancer classification.We selected leave-one-out cross-validation(LOOCV)to evaluate the performance of both two widely used classifiers,k-nearest neighbors(KNN)and support vector machine(SVM),on high-dimensional cancer microarray data.The proposed method is extensively tested on six publicly available cancer microarray datasets,and a comprehensive comparison with recently published methods is conducted.Our hybrid algorithm demonstrates its effectiveness in improving classification performance,Surpassing alternative approaches in terms of precision.The outcomes confirm the capability of our method to substantially improve both the precision and efficiency of cancer classification,thereby advancing the development ofmore efficient treatment strategies.The proposed hybridmethod offers a promising solution to the gene selection problem in microarray-based cancer classification.It improves the accuracy and efficiency of cancer diagnosis and treatment,and its superior performance compared to other methods highlights its potential applicability in realworld cancer classification tasks.By harnessing the complementary search mechanisms of GWO and HHO,we leverage their bio-inspired behavior to identify informative genes relevant to cancer diagnosis and treatment.

Enhancing Evolutionary Algorithms With Pattern Mining for Sparse Large-Scale Multi-Objective Optimization Problems

Sparse large-scale multi-objective optimization problems(SLMOPs)are common in science and engineering.However,the large-scale problem represents the high dimensionality of the decision space,requiring algorithms to traverse vast expanse with limited computational resources.Furthermore,in the context of sparse,most variables in Pareto optimal solutions are zero,making it difficult for algorithms to identify non-zero variables efficiently.This paper is dedicated to addressing the challenges posed by SLMOPs.To start,we introduce innovative objective functions customized to mine maximum and minimum candidate sets.This substantial enhancement dramatically improves the efficacy of frequent pattern mining.In this way,selecting candidate sets is no longer based on the quantity of nonzero variables they contain but on a higher proportion of nonzero variables within specific dimensions.Additionally,we unveil a novel approach to association rule mining,which delves into the intricate relationships between non-zero variables.This novel methodology aids in identifying sparse distributions that can potentially expedite reductions in the objective function value.We extensively tested our algorithm across eight benchmark problems and four real-world SLMOPs.The results demonstrate that our approach achieves competitive solutions across various challenges.

Hybrid Hierarchical Particle Swarm Optimization with Evolutionary Artificial Bee Colony Algorithm for Task Scheduling in Cloud Computing

Task scheduling plays a key role in effectively managing and allocating computing resources to meet various computing tasks in a cloud computing environment.Short execution time and low load imbalance may be the challenges for some algorithms in resource scheduling scenarios.In this work,the Hierarchical Particle Swarm Optimization-Evolutionary Artificial Bee Colony Algorithm(HPSO-EABC)has been proposed,which hybrids our presented Evolutionary Artificial Bee Colony(EABC),and Hierarchical Particle Swarm Optimization(HPSO)algorithm.The HPSO-EABC algorithm incorporates both the advantages of the HPSO and the EABC algorithm.Comprehensive testing including evaluations of algorithm convergence speed,resource execution time,load balancing,and operational costs has been done.The results indicate that the EABC algorithm exhibits greater parallelism compared to the Artificial Bee Colony algorithm.Compared with the Particle Swarm Optimization algorithm,the HPSO algorithmnot only improves the global search capability but also effectively mitigates getting stuck in local optima.As a result,the hybrid HPSO-EABC algorithm demonstrates significant improvements in terms of stability and convergence speed.Moreover,it exhibits enhanced resource scheduling performance in both homogeneous and heterogeneous environments,effectively reducing execution time and cost,which also is verified by the ablation experimental.

Simultaneous Identification of Thermophysical Properties of Semitransparent Media Using a Hybrid Model Based on Artificial Neural Network and Evolutionary Algorithm

A hybrid identification model based on multilayer artificial neural networks(ANNs) and particle swarm optimization(PSO) algorithm is developed to improve the simultaneous identification efficiency of thermal conductivity and effective absorption coefficient of semitransparent materials.For the direct model,the spherical harmonic method and the finite volume method are used to solve the coupled conduction-radiation heat transfer problem in an absorbing,emitting,and non-scattering 2D axisymmetric gray medium in the background of laser flash method.For the identification part,firstly,the temperature field and the incident radiation field in different positions are chosen as observables.Then,a traditional identification model based on PSO algorithm is established.Finally,multilayer ANNs are built to fit and replace the direct model in the traditional identification model to speed up the identification process.The results show that compared with the traditional identification model,the time cost of the hybrid identification model is reduced by about 1 000 times.Besides,the hybrid identification model remains a high level of accuracy even with measurement errors.

MaOEA/I:Many-objective Evolutionary Algorithm Based on Indicator I_(ε+)

Balancing the diversity and convergence of the population is challenging in multi-objective optimization. The work proposed a many-objective evolutionary algorithm based on indicator I_(ε+)(MaOEA/I) to solve the above problems. Indicator I_(ε+)(x,y) is used for environmental selection to ensure diversity and convergence of the population. I_(ε+)(x,y) can evaluate the quality of individual x compared with individual y instead of the whole population. If I_(ε+)(x,y) is less than 0, individual x dominates y. If I_(ε+)(x,y) is 0, individuals x and y are the same. If I_(ε+)(x,y) is greater than 0, no dominant relationship exists between individuals x and y. The smaller I_(ε+)(x,y), the closer the two individuals. The dominated individuals should be deleted in environmental selection because they do not contribute to convergence. If there is no dominant individual, the same individuals and similar individuals should be deleted because they do not contribute to diversity. Therefore, the environmental selection of MaOEA/I should consider the two individuals with the smallest I_(ε+)(x,y). If I_(ε+)(x,y) is not greater than 0, delete individual y;if I_(ε+)(x,y) is greater than 0, check the distance between individuals x, y, and the target point and delete the individual with a longer distance. MaOEA/I is compared with 6 algorithms until the population does not exceed the population size. Experimental results demonstrate that MaOEA/I can gain highly competitive performance when solving many-objective optimization problems.

Biometric Finger Vein Recognition Using Evolutionary Algorithm with Deep Learning

In recent years,the demand for biometric-based human recog-nition methods has drastically increased to meet the privacy and security requirements.Palm prints,palm veins,finger veins,fingerprints,hand veins and other anatomic and behavioral features are utilized in the development of different biometric recognition techniques.Amongst the available biometric recognition techniques,Finger Vein Recognition(FVR)is a general technique that analyzes the patterns of finger veins to authenticate the individuals.Deep Learning(DL)-based techniques have gained immense attention in the recent years,since it accomplishes excellent outcomes in various challenging domains such as computer vision,speech detection and Natural Language Processing(NLP).This technique is a natural fit to overcome the ever-increasing biomet-ric detection problems and cell phone authentication issues in airport security techniques.The current study presents an Automated Biometric Finger Vein Recognition using Evolutionary Algorithm with Deep Learning(ABFVR-EADL)model.The presented ABFVR-EADL model aims to accomplish bio-metric recognition using the patterns of the finger veins.Initially,the presented ABFVR-EADL model employs the histogram equalization technique to pre-process the input images.For feature extraction,the Salp Swarm Algorithm(SSA)with Densely-connected Networks(DenseNet-201)model is exploited,showing the proposed method’s novelty.Finally,the Deep-Stacked Denoising Autoencoder(DSAE)is utilized for biometric recognition.The proposed ABFVR-EADL method was experimentally validated using the benchmark databases,and the outcomes confirmed the productive performance of the proposed ABFVR-EADL model over other DL models.

Optimal Design of Tapered Roller Bearings Based on Multi⁃Physics Objectives Using Evolutionary Algorithms

Rolling element bearing is the most common machine element in rotating machinery.An extended life is among the foremost imperative standards in the optimal design of rolling element bearings,which confide on the fatigue failure,wear,and thermal conditions of bearings.To fill the gap,in the current work,all three objectives of a tapered roller bearing have been innovatively considered respectively,which are the dynamic capacity,elasto-hydrodynamic lubrication(EHL)minimum film⁃thickness,and maximum bearing temperature.These objective function formulations are presented,associated design variables are identified,and constraints are discussed.To solve complex non⁃linear constrained optimization formulations,a best⁃practice design procedure was investigated using the Artificial Bee Colony(ABC)algorithms.A sensitivity analysis of several geometric design variables was conducted to observe the difference in all three objectives.An excellent enhancement was found in the bearing designs that have been optimized as compared with bearing standards and previously published works.The present study will definitely add to the present experience based design followed in bearing industries to save time and obtain assessment of bearing performance before manufacturing.To verify the improvement,an experimental investigation is worthwhile conducting.

基于CatBoost-MOEAD的大直径泥水盾构施工多目标预测优化

为有效优化盾构施工参数,实现在大直径泥水盾构掘进过程中安全、高效和节能的目标,提出分类助推(CatBoost)和基于分解的多目标进化算法(MOEAD)相结合的混合智能算法;综合考虑盾构施工参数与地质条件,以主要的盾构施工参数为研究对象,选择地表沉降、贯入度和掘进比能为预测和控制目标;优化调控选择的盾构施工参数,并以武汉市轨道交通某号线为例,验证该混合算法的有效性。结果表明:采用CatBoost算法建立的预测模型在大直径泥水盾构上表现出来的预测性能良好,对3个控制目标的拟合精度(R 2)均达到0.9以上;预测模型的重要性排序表明:大直径泥水盾构的总推进力和推进速度对地表沉降、贯入度和掘进比能有显著影响;所提出的CatBoost-MOEAD混合智能算法对3个控制目标的优化效果明显,地表沉降、贯入度和掘进比能分别达到12.35%、7.47%和10.70%的优化幅度,并给出相应盾构施工参数的控制范围。

Dose reconstruction with Compton camera during proton therapy via subset-driven origin ensemble and double evolutionary algorithm

Compton camera-based prompt gamma(PG) imaging has been proposed for range verification during proton therapy. However, a deviation between the PG and dose distributions, as well as the difference between the reconstructed PG and exact values, limit the effectiveness of the approach in accurate range monitoring during clinical applications. The aim of the study was to realize a PG-based dose reconstruction with a Compton camera, thereby further improving the prediction accuracy of in vivo range verification and providing a novel method for beam monitoring during proton therapy. In this paper, we present an approach based on a subset-driven origin ensemble with resolution recovery and a double evolutionary algorithm to reconstruct the dose depth profile(DDP) from the gamma events obtained by a cadmium-zinc-telluride Compton camera with limited position and energy resolution. Simulations of proton pencil beams with clinical particle rate irradiating phantoms made of different materials and the CT-based thoracic phantom were used to evaluate the feasibility of the proposed method. The results show that for the monoenergetic proton pencil beam irradiating homogeneous-material box phantom,the accuracy of the reconstructed DDP was within 0.3 mm for range prediction and within 5.2% for dose prediction. In particular, for 1.6-Gy irradiation in the therapy simulation of thoracic tumors, the range deviation of the reconstructed spreadout Bragg peak was within 0.8 mm, and the relative dose deviation in the peak area was less than 7% compared to the exact values. The results demonstrate the potential and feasibility of the proposed method in future Compton-based accurate dose reconstruction and range verification during proton therapy.

Design and optimization of diffraction-limited storage ring lattices based on many-objective evolutionary algorithms

Multi-objective evolutionary algorithms(MOEAs) are typically used to optimize two or three objectives in the accelerator field and perform well. However, the performance of these algorithms may severely deteriorate when the optimization objectives for an accelerator are equal to or greater than four. Recently, many-objective evolutionary algorithms(MaOEAs)that can solve problems with four or more optimization objectives have received extensive attention. In this study, two diffraction-limited storage ring(DLSR) lattices of the Extremely Brilliant Source(ESRF-EBS) type with different energies were designed and optimized using three MaOEAs and a widely used MOEA. The initial population was found to have a significant impact on the performance of the algorithms and was carefully studied. The performances of the four algorithms were compared, and the results demonstrated that the grid-based evolutionary algorithm(GrEA) had the best performance.Ma OEAs were applied in many-objective optimization of DLSR lattices for the first time, and lattices with natural emittances of 116 and 23 pm·rad were obtained at energies of 2 and 6 GeV, respectively, both with reasonable dynamic aperture and local momentum aperture(LMA). This work provides a valuable reference for future many-objective optimization of DLSRs.

Tourism Route Recommendation Based on A Multi-Objective Evolutionary Algorithm Using Two-Stage Decomposition and Pareto Layering

Tourism route planning is widely applied in the smart tourism field.The Pareto-optimal front obtained by the traditional multi-objective evolutionary algorithm exhibits long tails,sharp peaks and disconnected regions problems,which leads to uneven distribution and weak diversity of optimization solutions of tourism routes.Inspired by these limitations,we propose a multi-objective evolutionary algorithm for tourism route recommendation(MOTRR)with two-stage and Pareto layering based on decomposition.The method decomposes the multiobjective problem into several subproblems,and improves the distribution of solutions through a two-stage method.The crowding degree mechanism between extreme and intermediate populations is used in the two-stage method.The neighborhood is determined according to the weight of the subproblem for crossover mutation.Finally,Pareto layering is used to improve the updating efficiency and population diversity of the solution.The two-stage method is combined with the Pareto layering structure,which not only maintains the distribution and diversity of the algorithm,but also avoids the same solutions.Compared with several classical benchmark algorithms,the experimental results demonstrate competitive advantages on five test functions,hypervolume(HV)and inverted generational distance(IGD)metrics.Using the experimental results of real scenic spot datasets from two famous tourism social networking sites with vast amounts of users and large-scale online comments in Beijing,our proposed algorithm shows better distribution.It proves that the tourism routes recommended by our proposed algorithm have better distribution and diversity,so that the recommended routes can better meet the personalized needs of tourists.

Evolutionary-assisted reinforcement learning for reservoir real-time production optimization under uncertainty

Production optimization has gained increasing attention from the smart oilfield community because it can increase economic benefits and oil recovery substantially.While existing methods could produce high-optimality results,they cannot be applied to real-time optimization for large-scale reservoirs due to high computational demands.In addition,most methods generally assume that the reservoir model is deterministic and ignore the uncertainty of the subsurface environment,making the obtained scheme unreliable for practical deployment.In this work,an efficient and robust method,namely evolutionaryassisted reinforcement learning(EARL),is proposed to achieve real-time production optimization under uncertainty.Specifically,the production optimization problem is modeled as a Markov decision process in which a reinforcement learning agent interacts with the reservoir simulator to train a control policy that maximizes the specified goals.To deal with the problems of brittle convergence properties and lack of efficient exploration strategies of reinforcement learning approaches,a population-based evolutionary algorithm is introduced to assist the training of agents,which provides diverse exploration experiences and promotes stability and robustness due to its inherent redundancy.Compared with prior methods that only optimize a solution for a particular scenario,the proposed approach trains a policy that can adapt to uncertain environments and make real-time decisions to cope with unknown changes.The trained policy,represented by a deep convolutional neural network,can adaptively adjust the well controls based on different reservoir states.Simulation results on two reservoir models show that the proposed approach not only outperforms the RL and EA methods in terms of optimization efficiency but also has strong robustness and real-time decision capacity.

Evolutionary Multitask Optimization in Real-World Applications: A Survey

Because of its strong ability to solve problems,evolutionary multitask optimization(EMTO)algorithms have been widely studied recently.Evolutionary algorithms have the advantage of fast searching for the optimal solution,but it is easy to fall into local optimum and difficult to generalize.Combining evolutionary multitask algorithms with evolutionary optimization algorithms can be an effective method for solving these problems.Through the implicit parallelism of tasks themselves and the knowledge transfer between tasks,more promising individual algorithms can be generated in the evolution process,which can jump out of the local optimum.How to better combine the two has also been studied more and more.This paper explores the existing evolutionary multitasking theory and improvement scheme in detail.Then,it summarizes the application of EMTO in different scenarios.Finally,according to the existing research,the future research trends and potential exploration directions are revealed.

Multiobjective evolutionary algorithm for dynamic nonlinear constrained optimization problems

A new method to solve dynamic nonlinear constrained optimization problems （DNCOP） is proposed. First, the time （environment） variable period of DNCOP is divided into several equal subperiods. In each subperiod, the DNCOP is approximated by a static nonlinear constrained optimization problem （SNCOP）. Second, for each SNCOP, inspired by the idea of multiobjective optimization, it is transformed into a static bi-objective optimization problem. As a result, the original DNCOP is approximately transformed into several static bi-objective optimization problems. Third, a new multiobjective evolutionary algorithm is proposed based on a new selection operator and an improved nonuniformity mutation operator. The simulation results indicate that the proposed algorithm is effective for DNCOP.

Improvements in seismic event locations in a deep western U.S. coal mine using tomographic velocity models and an evolutionary search algorithm

Methods of improving seismic event locations were investigated as part of a research study aimed at reducing ground control safety hazards. Seismic event waveforms collected with a 23-station three-dimensional sensor array during longwall coal mining provide the data set used in the analyses. A spatially variable seismic velocity model is constructed using seismic event sources in a passive tomographic method. The resulting three-dimensional velocity model is used to relocate seismic event positions. An evolutionary optimization algorithm is implemented and used in both the velocity model development and in seeking improved event location solutions. Results obtained using the different velocity models are compared. The combination of the tomographic velocity model development and evolutionary search algorithm provides improvement to the event locations.

Evolution Performance of Symbolic Radial Basis Function Neural Network by Using Evolutionary Algorithms

Radial Basis Function Neural Network(RBFNN)ensembles have long suffered from non-efficient training,where incorrect parameter settings can be computationally disastrous.This paper examines different evolutionary algorithms for training the Symbolic Radial Basis Function Neural Network(SRBFNN)through the behavior’s integration of satisfiability programming.Inspired by evolutionary algorithms,which can iteratively find the nearoptimal solution,different Evolutionary Algorithms(EAs)were designed to optimize the producer output weight of the SRBFNN that corresponds to the embedded logic programming 2Satisfiability representation(SRBFNN-2SAT).The SRBFNN’s objective function that corresponds to Satisfiability logic programming can be minimized by different algorithms,including Genetic Algorithm(GA),Evolution Strategy Algorithm(ES),Differential Evolution Algorithm(DE),and Evolutionary Programming Algorithm(EP).Each of these methods is presented in the steps in the flowchart form which can be used for its straightforward implementation in any programming language.With the use of SRBFNN-2SAT,a training method based on these algorithms has been presented,then training has been compared among algorithms,which were applied in Microsoft Visual C++software using multiple metrics of performance,including Mean Absolute Relative Error(MARE),Root Mean Square Error(RMSE),Mean Absolute Percentage Error(MAPE),Mean Bias Error(MBE),Systematic Error(SD),Schwarz Bayesian Criterion(SBC),and Central Process Unit time(CPU time).Based on the results,the EP algorithm achieved a higher training rate and simple structure compared with the rest of the algorithms.It has been confirmed that the EP algorithm is quite effective in training and obtaining the best output weight,accompanied by the slightest iteration error,which minimizes the objective function of SRBFNN-2SAT.

Design of Evolutionary Algorithm Based Energy Efficient Clustering Approach for Vehicular Adhoc Networks

In a vehicular ad hoc network(VANET),a massive quantity of data needs to be transmitted on a large scale in shorter time durations.At the same time,vehicles exhibit high velocity,leading to more vehicle disconnections.Both of these characteristics result in unreliable data communication in VANET.A vehicle clustering algorithm clusters the vehicles in groups employed in VANET to enhance network scalability and connection reliability.Clustering is considered one of the possible solutions for attaining effectual interaction in VANETs.But one such difficulty was reducing the cluster number under increasing transmitting nodes.This article introduces an Evolutionary Hide Objects Game Optimization based Distance Aware Clustering(EHOGO-DAC)Scheme for VANET.The major intention of the EHOGO-DAC technique is to portion the VANET into distinct sets of clusters by grouping vehicles.In addition,the DHOGO-EAC technique is mainly based on the HOGO algorithm,which is stimulated by old games,and the searching agent tries to identify hidden objects in a given space.The DHOGO-EAC technique derives a fitness function for the clustering process,including the total number of clusters and Euclidean distance.The experimental assessment of the DHOGO-EAC technique was carried out under distinct aspects.The comparison outcome stated the enhanced outcomes of the DHOGO-EAC technique compared to recent approaches.

AN ANALYSIS ABOUT BEHAVIOR OF EVOLUTIONARY ALGORITHMS:A KIND OF THEORETICAL DESCRIPTION BASED ON GLOBAL RANDOM SEARCH METHODS

Evolutionary computation is a kind of adaptive non--numerical computation method which is designed tosimulate evolution of nature. In this paper, evolutionary algorithm behavior is described in terms of theconstruction and evolution of the sampling distributions over the space of candidate solutions. Iterativeconstruction of the sampling distributions is based on the idea of the global random search of generationalmethods. Under this frame, propontional selection is characterized as a gobal search operator, and recombination is characerized as the search process that exploits similarities. It is shown-that by properly constraining the search breadth of recombination operators, weak convergence of evolutionary algorithms to aglobal optimum can be ensured.