Earticle

Machine learning-based sentiment classification is the best-performing method to understand public sentiment. However, the method has some problems, such as noisy features and high-dimensional feature space which affect the sentiment classification performance. To address the problems, this paper proposes a new feature selection using hybrid Query Expansion Ranking and Binary Particle Swarm Optimization with Adaptive Inertia Weights. The proposed method was validated using five tweet datasets on different topics both in Indonesian and English, and compared with state-of-the-art of filter and wrapper-based feature selection methods. Experimental results show the proposed method significantly improves sentiment classification performance and decrease computational time.

Task scheduling is one of the most important issues in heterogeneous environments when high efficiency is required. Because task scheduling is a Nondeterministic Polynomial (NP)-hard problem, many evolutionary algorithms have been adopted to solve this problem. Since the convergence speed of solutions in population-based algorithms is low, they are integrated with local search algorithms. Thus, in this paper, to optimize the task scheduling makespan, a hybrid particle swarm optimization and hill climbing algorithm is proposed. The experimental results on random and scientific Directed Acyclic Graph (DAG) showed that the proposed algorithm performs effectively in terms of the makespan compared to the current well-known heuristic and particle swarm optimization algorithms.

Medical image processing is one of the most challenging and emerging filed. Processing of medical image is one of the important tasks for the diagnosis of brain tumor. Image segmentation is required for detection of brain tumors, which is a quite complicated job if performed automatically. In recent time, scientists from various fields including medical, mathematical and computer science have collaborated to find out a better understanding of the disease and devise more cost-effective treatments. Due to advancements in the field of science and technology, we have innumerous methods for image segmentation which are used for the detection of brain tumor and to clearly recognize it from MRI imagery. Various methods and algorithms have been implemented for segmenting MRI imagery. This work implements particle swarm optimization technique to recognize brain tumor by characterizing MRI images. Machine learning algorithm is used for severity analysis of brain tumor.

최근에 진화연산방법은 건설 분야의 여러 문제에 성공적으로 적용되어 왔으며 대표적인 방법으로는 유전자 알고리즘과 Particle Swarm Optimization이 있다. 유전자 알고리즘은 생물유전학과 자연선택이론에 바탕을 둔 병렬적인 최적화 탐색방법이며 PSO는 새나 물고리 무리의 집단적인 행동에서 영감을 얻은 진화형 통계탐색방법이다. 두 방법은 많은 유사한 점을 공유하고 있지만, 어느 한 방법이 다른 방법도 효율과 효과 면에서 항상 뛰어나다는 것을 증명할 수 없다. 이에 본 연구는 유전자 알고리즘과 PSO방법 중 어떤 방법이 공동주택 사업초기단계에서의 공사비 예측문제에서 더 뛰어난 예측성능을 보여주는 지를 조사하였다. 한국건설감리협회의 감리자 입찰공고를 통해 수집한 219개의 공동주택 사업자료를 가지고 NeuroShell Predictor 소프트웨어에서 두 방법을 이용한 예측모델을 제시하였고 모델의 예측성능을 점검하였다. 소프트웨어에서 제공하는 높은 R-squared 및 상관계수값을 통해서 두 예측모델의 성능은 우수한 것으로 판명되었으나 PSO 기반 예측모델이 유전자 알고리즘 기반 모델보다 평가시험그룹에서의 예측정확도면에서 약간 더 우수한 것으로 나타났다.

In recent years, evolutionary computation methods have been successfully applied to various problems in the construction field. Two of these popular methods are Genetic Algorithm(GA) and Particle Swarm Optimization(PSO). GA is a parallel search method for an optimal solution based on the genetics and natural selection and PSO is a population-based stochastic optimization method inspired by social behavior of bird flocking or fish schooling. While two methods share many similarities, one cannot be proven to always outperform the other in terms of efficiency and effectiveness. From this point, this paper examined whether GA or PSO is superior at a problem to predict construction cost on apartment housing projects at the early stage. With 219 apartment housing project data obtained from bidding announcements for construction supervisors in the Korea Construction Consulting Engineers Association, prediction models using two methods were suggested in the NeuroShell Predictor software and prediction performances of two models were checked. From high R-squared and correlation coefficient values provided by the software, performances of two prediction models were found to be good. However, the findings also showed that the PSO-based model is slightly better than the GA-based one in the comparison of prediction accuracy on the testing dataset.

This work proposes the application of a hybrid Particle Swarm Optimization (PSO) with Levenberg Marquardt Back-Propagation (LMBP) algorithm to train Artificial Neural Networks (ANNs) for classification of medium resolution multispectral satellite imageries. ANNs have been widely used in satellite image classification and have been shown to outperform traditional classifiers in many situations. However the Back Propagation (BP) algorithm traditionally used in training ANN suffer the problem of local minima entrapment, thus affecting the accuracy and performance of the ANN classifier. A hybrid combination of PSO and LMBP algorithm is applied to resolve the aforementioned problem and enhance the accuracy and performance of the ANN classifier. To investigate the performance of the proposed method, medium resolution multispectral satellite imagery was classified using the proposed classifier and its performance compared with that of conventional LMBP and Scaled Conjugate Back-Propagation (SCBP) trained ANN classifier. Results obtained shows that the hybrid PSO and LMBP trained ANN classifier out performs the conventional LMBP and SCBP trained ANN classifier and achieves ≈95% accuracy on the test medium resolution satellite imagery.

Churn prediction is an important task for Customer Relationship Management (CRM) in telecommunication companies. Accurate churn prediction helps CRM in planning effective strategies to retain their valuable customers. However, churn prediction is a complex and challenging task. In this paper, a hybrid churn prediction model is proposed based on combining two approaches; Neighborhood Cleaning Rules (NCL) and Particle Swarm Optimization (PSO). NCL is applied in the preprocessing stage for handling the imbalanced churn data; and eliminating outliers and unrepresentative data. In the next stage, a Constricted PSO is applied for developing the final prediction model. The developed model is evaluated and compared with a baseline PSO model. The proposed hybrid model is compared also with Artificial Neural Networks (ANN) and Decision trees (DT) models which are traditional and common approaches used in the literature for churn prediction. The experimental results show that the proposed hybrid model outperforms the baseline PSO model, ANN and DT in terms of accuracy and actual churn rate.

Affinity propagation algorithm is a new powerful and effective clustering method. One of the major problems in clustering is the determination of the optimal number of clusters. In this paper, the particle swarm optimization algorithm is utilized to cope with this problem by using the parameter p as each particle and Silhouette index as the fitness, which can search for the optimal value of p and determine the optimal number of clusters automatically. Moreover, the problem of information overlap is the main drawback of affinity propagation algorithm in dealing with complex structure or high dimensional data for clustering. Hence the enhanced Locality preserving projections method is proposed to integrate with affinity propagation algorithm to reduce the dimension of the data as a processing step. As the result of experiment shows, the proposed method can simultaneously obtain the optimal number of clusters accurately and improve the clustering accuracy by eliminating the redundant information of the data without losing the internal nonlinear structure.

Bargaining game analysis using metaheuristics has been drawing attention in recent years. This paper presents the interaction and co-evolutionary process between two kinds of metaheuristics-based agents, genetic algorithms (GA-based agent) and particle swarm optimization (PSO-based agent), in a bargaining game. Game performance with regard to payoff and deal rate through the interaction and co-evolution of agents is studied. The experimental results show that the PSO-based agent outperforms the GA-based agent in the bargaining game.

In this paper, we propose a fragile watermarking hybrid approach using rough set kmeans and exponential particle swarm optimization (EPSO) systems. It is based on a block-wise dependency mechanism which can detect any alterations made to the protected image. Initially, the input image is divided into blocks with equal size in order to improve image tamper localization precision. Then feature sequence is generated by applying rough k-means and EPSO clustering to create the relationship between all image blocks and cluster all of them since EPSO is used to optimize the parameters of rough k-means. Both feature sequence and generated secret key are used to construct the authentication data. Each resultant 8-bit authentication data is embedded into the eight least significant bits (LSBs) of the corresponding image block. We gives experimental results which show the feasibility of using these optimization algorithms for the fragile watermarking and demonstrate the accuracy of the proposed approach. The performance comparison of the approach was also realized. The performance of a fragile watermarking approach has been improved in this paper by using exponential particle swarm optimization (EPSO) to optimize the rough kmean parameters. The proposed approach can embed watermark without causing noticeable visual artifacts, and does not only achieve superior tamper detection in images accurately, it also recovers tampered regions effectively. In addition, the results show that the proposed approach can effectively thwart different attacks, such as the cut-and paste attack and collage attack, while sustaining superior tamper detection and localization accuracy.

Context fusion is a very important aspect in a system that has to adequately simplify a required task in achieving context awareness in the Internet of things (IoT). IoT generates a large amount of data, which are massive, multi-source, heterogeneous, dynamic and sparse. Context information fusion is an important tool in the manipulation and management of these data in order to improve processing efficiency, provide advanced intelligence and increase reliability. Context information fusion can reduce the amount of data traffic, filter noisy measurements, and make predictions and inferences in any stages of data processing in IoT. As such when context is acquired from this domain, it has low confidence level due to reliability factors. In this paper Context information’s reliability has been addressed through the use quality of context (QoC) by determining the combined confidence for acquired context from multiple sources. Particle Swarm Optimization selects the context information with the highest level of confidence and Dempster Shafer rule of combination fuses this context into more reliable information that can be used by the system to effectively adapt to changing context. From the obtained results the proposed solution indicates an improved fusion process with increased confidence.

Bayesian network is a directed acyclic graph. Existing Bayesian network learning approaches based on search & scoring usually work with a heuristic search for finding the highest scoring structure. This paper describes a new data mining algorithm to learn Bayesian networks structures based on an immune binary particle swarm optimization (IB-PSO) method and the Minimum Description Length (MDL) principle. IBPSO is proposed by combining the immune theory in biology with particle swarm optimization (PSO). It constructs an immune operator accomplished by two steps, vaccination and immune selection. The purpose of adding immune operator is to prevent and overcome premature convergence. Experiments show that IBPSO not only improves the quality of the solutions, but also reduces the time cost.

This paper analysis the electric power communication network structure and performance requirements. To investigate the power communication backbone network and network power substation general way, and in electric power communication network delay, error rate, network bandwidth demand were analyzed. The for prevalent in electric power communication network is not a fully meshed network, explore artificially cobweb logic change principle and system method, artificial transform sheet mesh to the standard web, and making use of the cobweb, based on the characteristics of network fast routing. In order to better in the smart grid communication network using artificially cobweb routing algorithm, for the smart grid in the presence of irregular mesh network, this paper presents a kind of the mesh network into logical artificially cobweb network general standardization method. The principle of combination of label switching, this paper presents artificially cobweb source routing algorithm, expounds the artificially cobweb routing algorithm of label switching and label update mechanism, and artificially cobweb routing algorithm balancing routing method and routing method is described in detail.

The quantum particle swarm optimization (QPSO) algorithm exists some defects, such as premature convergence, poor search ability and easy falling into local optimal solutions. The adaptive adjustment strategy of inertia weight, chaotic search method and neighborhood mutation strategy are introduced into the QPSO algorithm in order to propose an improved quantum particle swarm optimization (AMCQPSO) algorithm in this paper. In the AMCQPSO algorithm, the chaotic search method is employed to promote the quality of initial population. The adaptive adjustment strategy of inertia weight is used to adjust the global search ability and local search ability of particles in the running process of QPSO algorithm. The neighborhood mutation strategy is used to increase the diversity of population and avoid premature convergence. Finally, in order to evaluate the performance of the AMCQPSO algorithm, several well-known benchmark functions are selected in this paper. The experiment simulations show that the proposed AMCQPSO algorithm can effectively improve the quality of solutions, and takes on powerful optimizing ability and more quickly convergence speed.

To reveal how the ancient kiln has evolved along DongHe River Basin in Jingdezhen –Jiangxi Province of China, and further reflect the interaction of the political situation, the institutions and the natural environment, we create ancient virtual maps of study area and propose such constructs to unambiguously denote a integration system by combining the advantages of multi-agents, PSO and CA in time and space. We apply the system to model a dynamic interaction environment and conduct a series of spatial analyses of the land-use pattern from 1271 to 1554. Compared with model PSO-CA, the simulation result of this new model is of richer changing hierarchy and can better reflect the whole process from the first to the last firing. Meantime, the index Moran's I of simulation using the hybrid method is much closer to the actual Moran's I, which can better reflect the interaction between political environment and natural environment of different dynasties with the lack of ancient GIS spatial data.

Due to the less accessibility to the data, relatively little literature has been found on how the ancient kiln site evolves. To understand how land has transformed kiln in ancient Jingdezhen DongHe River Basin from the Yuan Dynasty to the Ming Dynasty, we create virtual maps of ancient study area and present such concepts that unambiguously realize a combination model. In this model, Model parameters and neighborhood rules are obtained with the cellular automata model melt modified Particle Swarm Optimization algorithm. Meanwhile, model performance is evaluated using Moran’s I index estimation for selected landscape pattern indices and make a comparative analysis of different evolution with different number of candidate site and different conversion threshold. In overall, the model that we propose is effective and feasible in simulating kiln landscape evolution in ancient when Geographic Information and System information are lacking.

This paper proposes a novel tuning approach for robust proportional-integral-derivative (PID) controller based on H∞ loop shaping synthesis in combination with gap metric and Particle Swarm Optimization (PSO) algorithm. Different from the traditional research, the controller is designed through the search region constrained by H∞ loop shaping synthesis and gap metric theorem. PSO algorithm is used for tuning the robust PID controller parameters based on the underlying constrained optimization problems without resolving complex arithmetical calculations. The control technique is applied for the robust controller design so as to get a low order structured controller and achieve robust performance and the ability of restraining disturbance. The simulation shows that the proposed method can character the set of all values of the controller parameters that guarantees the robust stability with any supposed accuracy and achieves favorable control performance for uncertain systems.

The Hough Transform algorithm based on RPSO (Reduced Particle Swarm Optimization) is widely used in image detection. But it has several defects, such as being apt to plunge a local extremum and low target detection precision. In order to overcome these defects of the original algorithm, an improved algorithm, which is updated with the mechanism of SA (simulated annealing), is presented in this paper. In the improved algorithm, the output parameters of the Hough Transform was regarded as particle positions, and the opposite value of accumulation array in Hough Transform was employed as a fitness function of RPSO algorithm. Because the mechanism of the SA was involved, the velocities and positions of the particles are updated in real-time in the process of the crossover and Gaussian mutation. Consequently, the ability of converging to global optimum solution is obviously improved. Then, the comparison and analysis of the experiment results between the original algorithm and the improved one have been carried out in the application of the train wheel image detection. The experiment results demonstrate that the accuracy of image detection is evidently increased and the evolution speed is significantly boosted in the proposed algorithm, especially as the image has complex background or high level noise.

With the rapid development of national economy, the demand for electricity is more intense. There is a new demand for the security, reliability and applicability of the power distribution system. The power distribution system is an important component of power systems. It plays an important role in connecting power production and users. Now the most important problem is nonlinear combinatorial optimization in large-scale mixed lines and how to reconfigure the distribution network. However, by deeply analyzing and studying immune particle swarm optimization, the mathematical model of distribution network reconfiguration is established. By coding the characteristics of closed-loop design and open-loop operation, it aims to reduce the consumption of network, balance the grid load, eliminate the current overload and achieve the ultimate goal of improving the power supply reliability.