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.

A Study of EM Algorithm as an Imputation Method: A Model-Based Simulation Study with Application to a Synthetic Compositional Data

Compositional data, such as relative information, is a crucial aspect of machine learning and other related fields. It is typically recorded as closed data or sums to a constant, like 100%. The statistical linear model is the most used technique for identifying hidden relationships between underlying random variables of interest. However, data quality is a significant challenge in machine learning, especially when missing data is present. The linear regression model is a commonly used statistical modeling technique used in various applications to find relationships between variables of interest. When estimating linear regression parameters which are useful for things like future prediction and partial effects analysis of independent variables, maximum likelihood estimation (MLE) is the method of choice. However, many datasets contain missing observations, which can lead to costly and time-consuming data recovery. To address this issue, the expectation-maximization (EM) algorithm has been suggested as a solution for situations including missing data. The EM algorithm repeatedly finds the best estimates of parameters in statistical models that depend on variables or data that have not been observed. This is called maximum likelihood or maximum a posteriori (MAP). Using the present estimate as input, the expectation (E) step constructs a log-likelihood function. Finding the parameters that maximize the anticipated log-likelihood, as determined in the E step, is the job of the maximization (M) phase. This study looked at how well the EM algorithm worked on a made-up compositional dataset with missing observations. It used both the robust least square version and ordinary least square regression techniques. The efficacy of the EM algorithm was compared with two alternative imputation techniques, k-Nearest Neighbor (k-NN) and mean imputation (), in terms of Aitchison distances and covariance.

Immune Algorithm for Selecting Optimum Services in Web Services Composition

For the problem of dynamic optimization in Web services composition, this paper presents a novel approach for selecting optimum Web services, which is based on the longest path method of weighted multistage graph. We propose and implement an Immune Algorithm for global optimization to construct composed Web services. Results of the experimentation illustrates that the algorithm in this paper has a powerful capability and can greatly improve the efficiency and veracity in service selection.

Dynamic services selection algorithm in Web services composition supporting cross-enterprises collaboration

Based on the deficiency of time convergence and variability of Web services selection for services composition supporting cross-enterprises collaboration,an algorithm QCDSS(QoS constraints of dynamic Web services selection)to resolve dynamic Web services selection with QoS global optimal path,was proposed.The essence of the algorithm was that the problem of dynamic Web services selection with QoS global optimal path was transformed into a multi-objective services composition optimization problem with QoS constraints.The operations of the cross and mutation in genetic algorithm were brought into PSOA(particle swarm optimization algorithm),forming an improved algorithm(IPSOA)to solve the QoS global optimal problem.Theoretical analysis and experimental results indicate that the algorithm can better satisfy the time convergence requirement for Web services composition supporting cross-enterprises collaboration than the traditional algorithms.

Composition of Web Services of Multi-Population Adaptive Genetic Algorithm Based on Cosine Improvement

Web quality of service (QoS) awareness requires not only the selection of specific services to complete specific tasks, but also the comprehensive quality of service of the whole web service composition. How to select the web service composition with the highest comprehensive QoS is a NP hard problem. In this paper, an improved multi population genetic algorithm is proposed. Cosine adaptive operator is added to the algorithm to avoid premature algorithm caused by improper genetic operator and the disadvantage of destroying excellent individuals in later period. Experimental results show that compared with the common genetic algorithm and multi population genetic algorithm, this algorithm has the advantages of shorter time consumption and higher accuracy, and effectively avoids the loss of effective genes in the population.

Service Composition Instantiation Based on Cross-Modified Artificial Bee Colony Algorithm

Internet of things(IoT) imposes new challenges on service composition as it is difficult to manage a quick instantiation of a complex services from a growing number of dynamic candidate services. A cross-modified Artificial Bee Colony Algorithm(CMABC) is proposed to achieve the optimal solution services in an acceptable time and high accuracy. Firstly, web service instantiation model was established. What is more, to overcome the problem of discrete and chaotic solution space, the global optimal solution was used to accelerate convergence rate by imitating the cross operation of Genetic algorithm(GA). The simulation experiment result shows that CMABC exhibited faster convergence speed and better convergence accuracy than some other intelligent optimization algorithms.

CHC-TSCM:A Trustworthy Service Composition Method Based on an Improved CHC Genetic Algorithm

Trustworthy service composition is an extremely important task when service composition becomes infeasible or even fails in an environment which is open,autonomic,uncertain and deceptive.This paper presents a trustworthy service composition method based on an improved Cross generation elitist selection,Heterogeneous recombination,Catacly-smic mutation(CHC) Trustworthy Service Composition Method(CHC-TSCM) genetic algorithm.CHCTSCM firstly obtains the total trust degree of the individual service using a trust degree measurement and evaluation model proposed in previous research.Trust combination and computation then are performed according to the structural relation of the composite service.Finally,the optimal trustworthy service composition is acquired by the improved CHC genetic algorithm.Experimental results show that CHC-TSCM can effectively solve the trustworthy service composition problem.Comparing with GODSS and TOCSS,this new method has several advantages:1) a higher service composition successrate;2) a smaller decline trend of the service composition success-rate,and 3) enhanced stability.

Optimization of the Active Composition of the Wind Farm Using Genetic Algorithms

The article presents the results of research on the possibilities of using genetic algorithms for solving the multicriteria optimization problem of determining the active components of a wind farm.Optimization is carried out on two parameters:efficiency factor of wind farm use(integrated parameter calculated on the basis of 6 parameters of each of the wind farm),average power deviation level(average difference between the load power and energy generation capabilities of the active wind farm).That was done an analysis of publications on the use of genetic algorithms to solve multicriteria optimization problems.Computer simulations were performed,which allowed us to analyze the obtained statistical data and determine the main optimization indicators.That was carried out a comparative analysis of the obtained results with other methods,such as the dynamic programming method;the dynamic programming method with the general increase of the set loading;the modified dynamic programming method,neural networks.It is established that the average power deviation for the genetic algorithm and for the modified dynamic programming method is located at the same level,33.7 and 28.8 kW,respectively.The average value of the efficiency coefficient of wind turbine used for the genetic algorithm is 2.4%less than for the modified dynamic programming method.However,the time of finding the solution by the genetic algorithm is 3.6 times less than for the modified dynamic programming method.The obtained results provide an opportunity to implement an effective decision support system in energy flow management.

Neighborhood Search Based Improved Bat Algorithm for Web Service Composition

Web services are provided as reusable software components in the services-oriented architecture.More complicated composite services can be combined from these components to satisfy the user requirements represented as a workflow with specified Quality of Service(QoS)limitations.The workflow consists of tasks where many services can be considered for each task.Searching for optimal services combination and optimizing the overall QoS limitations is a Non-deterministic Polynomial(NP)-hard problem.This work focuses on the Web Service Composition(WSC)problem and proposes a new service composition algorithm based on the micro-bats behavior while hunting the prey.The proposed algorithm determines the optimal combination of the web services to satisfy the complex user needs.It also addresses the Bat Algorithm(BA)shortcomings,such as the tradeoff among exploration and exploitation searching mechanisms,local optima,and convergence rate.The proposed enhancement includes a developed cooperative and adaptive population initialization mechanism.An elitist mechanism is utilized to address the BA convergence rate.The tradeoff between exploration and exploitation is handled through a neighborhood search mechanism.Several benchmark datasets are selected to evaluate the proposed bat algorithm’s performance.The simulation results are estimated using the average fitness value,the standard deviation of the fitness value,and an average of the execution time and compared with four bat-inspired algorithms.It is observed from the simulation results that introduced enhancement obtains significant results.

Hybrid Chameleon and Honey Badger Optimization Algorithm for QoS-Based Cloud Service Composition Problem

Cloud computing facilitates the great potentiality of storing and managing remote access to services in terms of software as a service(SaaS).Several organizations have moved towards outsourcing over the cloud to reduce the burden on local resources.In this context,the metaheuristic optimization method is determined to be highly suitable for selecting appropriate services that comply with the requirements of the client’s requests,as the services stored over the cloud are too complex and scalable.To achieve better service composition,the parameters of Quality of Service(QoS)related to each service considered to be the best resource need to be selected and optimized for attaining potential services over the cloud.Thus,the cloud service composition needs to concentrate on the selection and integration of services over the cloud to satisfy the client’s requests.In this paper,a Hybrid Chameleon and Honey Badger Optimization Algorithm(HCHBOA)-based cloud service composition scheme is presented for achieving efficient services with satisfying the requirements ofQoS over the cloud.This proposed HCHBOA integrated the merits of the Chameleon Search Algorithm(CSA)and Honey Badger Optimization Algorithm(HBOA)for balancing the tradeoff between the rate of exploration and exploitation.It specifically used HBOA for tuning the parameters of CSA automatically so that CSA could adapt its performance depending on its incorporated tuning factors.The experimental results of the proposed HCHBOA with experimental datasets exhibited its predominance by improving the response time by 21.38%,availability by 20.93%and reliability by 19.31%with a minimized execution time of 23.18%,compared to the baseline cloud service composition schemes used for investigation.

Hybridizing Artificial Bee Colony with Bat Algorithm for Web Service Composition

In the Internet of Things(IoT),the users have complex needs,and the Web Service Composition(WSC)was introduced to address these needs.The WSC’s main objective is to search for the optimal combination of web services in response to the user needs and the level of Quality of Services(QoS)constraints.The challenge of this problem is the huge number of web services that achieve similar functionality with different levels of QoS constraints.In this paper,we introduce an extension of our previous works on the Artificial Bee Colony(ABC)and Bat Algorithm(BA).A new hybrid algorithm was proposed between the ABC and BA to achieve a better tradeoff between local exploitation and global search.The bat agent is used to improve the solution of exhausted bees after a threshold(limits),and also an Elitist Strategy(ES)is added to BA to increase the convergence rate.The performance and convergence behavior of the proposed hybrid algorithm was tested using extensive comparative experiments with current state-ofthe-art nature-inspired algorithms on 12 benchmark datasets using three evaluation criteria(average fitness values,best fitness values,and execution time)that were measured for 30 different runs.These datasets are created from real-world datasets and artificially to form different scale sizes of WSC datasets.The results show that the proposed algorithm enhances the search performance and convergence rate on finding the near-optimal web services combination compared to competitors.TheWilcoxon signed-rank significant test is usedwhere the proposed algorithm results significantly differ fromother algorithms on 100%of datasets.

Composite Structural Optimization by Genetic Algorithm and Neural Network Response Surface Modeling

Neural-Network Response Surfaces （NNRS） is applied to replace the actual expensive finite element analysis during the composite structural optimization process. The Orthotropic Experiment Method （OEM） is used to select the most appropriate design samples for network training. The trained response surfaces can either be objective function or constraint conditions. Together with other conven- tional constraints, an optimization model is then set up and can be solved by Genetic Algorithm （GA）. This allows the separation between design analysis modeling and optimization searching. Through an example of a hat-stiffened composite plate design, the weight response surface is constructed to be objective function, and strength and buckling response surfaces as constraints; and all of them are trained through NASTRAN finite element analysis. The results of optimization study illustrate that the cycles of structural analysis ean be remarkably reduced or even eliminated during the optimization, thus greatly raising the efficiency of optimization process. It also observed that NNRS approximation can achieve equal or even better accuracy than conventional functional response surfaces.

Optimization model coupling both chemical compositions and high-temperature characteristics of sintering materials for sintering burden

We developed a mathematical optimization model coupling chemical compositions and high-temperature characteristics of sintering materials, targeting the best quality and lowest cost. The simplex algorithm was adopted to solve this model. Four kinds of imported iron ores, two kinds of Chinese iron ore concentrates, and two kinds of fluxes were selected to verify both the model and the algorithm. The results confirmed the possibility of considering both chemical compositions and high-temperature characteristics of iron ores in the optimization model. This model provides a technical roadmap to obtain a precise mathematical correlation between the lowest cost and the grade of iron in sinters based on the condition of given raw materials, which can provide a reference to adjust the grade of iron in the sintering process for enterprise.

Computer Aided Composition Design of Prehardened-Mould Steel for Plastic

The improvement of machining behavior of prehardened-mould steel for plastic is realized by using computer-aided composition design in this work. The results showed that the matrix composition of large sectional prehardened mould steel for plastic markedly influences the precipitation of non-metallic inclusion and the control of composition aided by Thermo-Calc software package minimizes the amount of detrimental oxide inclusion. In addition the modification of calcium is optimized in the light of composition design.

Computer-Aided Design of Some Advanced Steels and Cemented Carbides

Thermodynamic and kinetic study on TRIP （transformation induced plasticity） steels, cemented carbides and mold steel for plastics were carried out in order to design modern advanced materials. With the sublattice model, equilibrium compositions of ferrite and austenite phases in TRIP steels, as well as volume fraction of austenite at inter-critical temperatures for different time were calculated. Concentration profiles of carbon, manganese, aluminum and silicon in the steels were also estimated in the lattice fixed frame of reference. The effect of Si and Mn on TRIP was discussed according to thermodynamic and kinetic analyses. In order to understand and produce the graded nanophase structure of cemented carbides, miscellaneous phases in the M-Co-C （M= Ti, Ta, Nh） systems and Co-V-C system were modeled. Solution parameters and thermodynamic： properties were listed in detail. The improvement of machining behavior of prehardened mould steel for plastics was obtained by computer-aided composition design. The results showed that the matrix composition of large-section prehardened mould steel for plastic markedly influences the precipitation of non-metallic inclusion and the composition control by the aid of Thermo-Calc software package minimizes the amount of detrimental oxide inclusion. In addition, the modification of calcium was optimized in composition design.

Communication Mechanism and Algorithm of Composite Location Analysis of Emergency Communication based on Rail

The emergency communication system based on rail is an unconventional emergency communication mode,it is a complement equipment for that conventional communication system can’t work while tunnel mine accident occurs.Medium of transmission channel is the widely existing rail in the tunnel.In this paper we analyzed the characteristics of the rail transmission channel,verified the feasibility that information is transmitted by vibration signal in rail,we proposed the realization plan of the system.Communication protocol and processing mechanism suitable for rail transmission are designed according to the characteristics of channel bandwidth and low data transmission.Information communication with low bit rate and low bit error is realized in the communication simulation model.In the simplified model,we realized to transmit recognition speech information,and the error rate of the key text information is low to accept.The most concerned problem of personnel location in the mine disaster rescue is proposed,the composite algorithm is based on the model of signal amplitude attenuation,key node information and data frame transmission delay.Location information of hitting point can be achieved within the simplified model of the experiment.Furthermore,we discuss the characteristics of vibration signals passing through different channels.

A Service Composition Approach Based on Sequence Mining for Migrating E-learning Legacy System to SOA

With the fast development of business logic and information technology, today＇s best solutions are tomorrow＇s legacy systems. In China, the situation in the education domain follows the same path. Currently, there exists a number of e-learning legacy assets with accumulated practical business experience, such as program resource, usage behaviour data resource, and so on. In order to use these legacy assets adequately and efficiently, we should not only utilize the explicit assets but also discover the hidden assets. The usage behaviour data resource is the set of practical operation sequences requested by all users. The hidden patterns in this data resource will provide users＇ practical experiences, which can benefit the service composition in service-oriented architecture （SOA） migration. Namely, these discovered patterns will be the candidate composite services （coarse-grained） in SOA systems. Although data mining techniques have been used for software engineering tasks, little is known about how they can be used for service composition of migrating an e-learning legacy system （MELS） to SOA. In this paper, we propose a service composition approach based on sequence mining techniques for MELS. Composite services found by this approach will be the complementation of business logic analysis results of MELS. The core of this approach is to develop an appropriate sequence mining algorithm for mining related data collected from an e-learning legacy system. According to the features of execution trace data on usage behaviour from this e-learning legacy system and needs of further pattern analysis, we propose a sequential mining algorithm to mine this kind of data of tile legacy system. For validation, this approach has been applied to the corresponding real data, which was collected from the e-learning legacy system; meanwhile, some investigation questionnaires were set up to collect satisfaction data. The investigation result is 90% the same with the result obtained through our approach.

Composition control and temperature inferential control of dividing wall column based on model predictive control and PI strategies

The dividing wall column （DWC） is considered as a major breakthrough in distillation technology and has good prospect of industrialization. Model predictive control （MPC） is an advanced control strategy that has acquired extensive applications in various industries. In this study, MPC is applied to the process for separating ethanol, n-propanol, and n-butanol ternary mixture in a fully thermally coupled DWC. Both composition control and tem- perature inferent/al control are considered. The multiobjective genetic algor/thm function ＂gamult/obj＂ in Matlab is used for the weight tuning of MPC. Comparisons are made between the control performances of MPC and PI strategies. Simulation results show that although both MPC and PI schemes can stabilize the DWC in case of feed disturbances, MPC generally behaves better than the PI strategy for both composition control and tempera- ture inferential control, resulting in a more stable and superior performance with lower values of integral of squared error （ISE）.

Optimization of machining parameters in turning of Al-SiC-Gr hybrid metal matrix composites using grey-fuzzy algorithm

Metal matrix composites reinforced with graphite particles provide better machinability and tribological properties. The present study attempts to find the optimal level of machining parameters for multi-performance characteristics in turning of Al-SiC-Gr hybrid composites using grey-fuzzy algorithm. The hybrid composites with 5%, 7.5% and 10% combined equal mass fraction of SiC-Gr particles were used for the study and their corresponding tensile strength values are 170, 210, 204 MPa respectively. Al-10%（SiC-Gr） hybrid composite provides better machinability when compared with composites with 5% and 7.5% of SiC-Gr. Grey-fuzzy logic approach offers improved grey-fuzzy reasoning grade and has less uncertainties in the output when compared with grey relational technique. The confirmatory test reveals an increase in grey-fuzzy reasoning grade from 0.619 to 0.891, which substantiates the improvement in multi-performance characteristics at the optimal level of process parameters setting.

Auto Composition System for Two Voice Part Inventions Based on Soft Computational Methods

Algorithmic composition is a very popular research field today. Bach's "two voice part invention" is the research object in this paper. The grammar and compositional rules of "invention" are introduced first. Then two soft computational methods,genetic algorithms and back propagation (BP) neural network technology,are combined to the experiment on assisting in composing "two voice part inventions". The system presented in this paper is quite effective and satisfactory.