Search

Balancing the contradiction between electricity demand and supply is the fundamental issue in demand side management (DSM). To address it, time-of-use (TOU) tariff has been studied extensively. In the TOU tariff, different prices are assigned to different periods of electricity consumption. The customers are implicitly encouraged to shift the consumption from peak to non-peak periods, resulting in the decrease of electricity supply cost and the increase of customer benefits. In this paper, the TOU tariff for a real-world thermal electricity company under dynamic electricity demand is studied. Specifically, a flexible TOU (FTOU) tariff model is proposed to optimize the electricity prices and their allocations to different time periods simultaneously, constrained by the dynamic demand of customers. A mixed artificial bee colony (mABC) approach is proposed to deal with the continuous prices and discrete allocations simultaneously, embedded with a transferred memory scheme (TMS) to achieve the flexible and smooth tariff design with dynamic demand. The experimental studies via the real-world scenarios are conducted to assess the performance of the proposal in comparison with various state-of-the-art approaches, including the standard and advanced variants. The effectiveness and applicability of TMS are also demonstrated by integrating into other advanced optimizers, such as L-SHADE and HCLPSO.

In recent years, ozone (O3) pollution in China has shown a worsening trend. Due to the vast territory of China, O3 pollution is a widespread and complex problem. It is vital to understand the current spatiotemporal distribution of O3 pollution in China. In this study, we collected hourly data on O3 concentrations in 338 cities from January 1, 2016, to February 28, 2019, to analyze O3 pollution in China from a spatiotemporal perspective. The spatial analysis showed that the O3 concentrations exceeded the limit in seven geographical regions of China to some extent, with more serious pollution in North, East, and Central China. The O3 concentrations in the eastern areas were usually higher than those in the western areas. The temporal analysis showed seasonal variations in O3 concentration, with the highest O3 concentration in the summer and the lowest in the winter. The weekend effect, which occurs in other countries (such as the USA), was found only in some cities in China. We also found that the highest O3 concentration usually occurred in the afternoon and the lowest was in the early morning. The comprehensive analysis in this paper could improve our understanding of the severity of O3 pollution in China.

As one of the most important research branches of evolutionary computation (EC), learning classifier system (LCS) is dedicated to discover decision making classifiers (“IF-THEN” type rules) via evolution and learning. Recent advances in LCS have shown distinguished generalization property over traditional approaches. In this paper, a novel LCS named niching genetic network programming with rule accumulation (nGNP-RA) is proposed. The unique features of the proposal arise from the following three points: First, it utilizes an advanced graph-based EC named GNP as the rule generator, resulting higher knowledge representation ability than traditional genetic algorithm (GA)-based LCSs; Second, a novel niching mechanism is developed in GNP to encourage the discovery of high-quality diverse rules; Third, a novel reinforcement learning (RL)-based mechanism is embedded to assign accurate credits to the discovered rules. To verify the effectiveness and robustness of nGNP-RA over traditional systems, two decision making testbeds are applied, including the benchmark tileworld problem and the real mobile robot control application.

Junrong Wang, Fenqin Liu, Peiran Ao, Xianneng Li, Haixiao Zheng, Di Wu, Nina Zhang, Junping She, Junhui Yuan, Xiuying Wu Department of Laboratory Medicine, Wenling Maternal and Child Health Care Hospital, Wenling, Zhejiang Province, People’s Republic of China Objective: To explore the clinical significance of 3-phosphoinositide-dependent protein kinase-1 (PDK1) expression in hepatocellular carcinoma (HCC) and its association with clinicopathologic features and prognosis in HCC patients.Materials and methods: A total of 128 HCC patients who received radical resection were enrolled from Wenling Maternal and Child Health Care Hospital between May 2005 and December 2008, and tumor and adjacent tissue samples were collected. Expression of PDK1 was detected by immunohistochemistry method. Correlation of PDK1 expression with clinicopathological features and prognosis was determined by Spearman’s correlation analysis. Impact of expression of PDK1 on overall survival and recurrence was determined by Kaplan–Meier analysis.Results: Immunohistochemistry results showed that PDK1 expression in HCC tissues was significantly higher than that in the corresponding adjacent cancer tissues. Univariate analysis showed that PDK1 messenger RNA expression can predict time to recurrence with diagnostic significance (P=0.001). Univariate analysis showed that alpha-fetoprotein level, tumor number, tumor encapsulation, microvascular invasion, and tumor–node–metastasis stage were also unfavorable prognostic variables for recurrence (P

Graphical abstractDisplay Omitted HighlightsArtificial bee colony with memory algorithm (ABCM) is proposed.ABCM introduces the memory ability of natural honeybees to ABC.ABCM is designed as simply as possible for easy implementation.Experiments on the benchmark functions show the superiority of ABCM.It bridges the gap between ABC and the neuroscience research of real honeybees. Artificial bee colony algorithm (ABC) is a new type of swarm intelligence methods which imitates the foraging behavior of honeybees. Due to its simple implementation with very small number of control parameters, many efforts have been done to explore ABC research in both algorithms and applications. In this paper, a new ABC variant named ABC with memory algorithm (ABCM) is described, which imitates a memory mechanism to the artificial bees to memorize their previous successful experiences of foraging behavior. The memory mechanism is applied to guide the further foraging of the artificial bees. Essentially, ABCM is inspired by the biological study of natural honeybees, rather than most of the other ABC variants that integrate existing algorithms into ABC framework. The superiority of ABCM is analyzed on a set of benchmark problems in comparison with ABC, quick ABC and several state-of-the-art algorithms.

Serious PM2.5 air pollution has persistently plagued and endangered most urban areas in China in recent years, and targeted policies are necessary to improve urban air quality ranging from macro policy (national level) to medium policy (city level) to micro policy (site specific). However, the macro-pattern study of air pollution between Chinese cities is inadequate, and not conducive to the formulation of macro-policy. To bridge this gap, we applied a sequential pattern mining algorithm to analyze the spatial-temporal patterns of PM2.5 pollution across Chinese cities during the period 2015 to 2018. The sequential patterns were collected from three levels of granularity on geographic areas and ten temporal scenarios covering time intervals from 10 to 100 h. Many underlying associative relationships were revealed between different cities by the mined patterns. The patterns were heterogeneous and presented five characteristics (i.e., clustering, symmetry, imbalance, decay, and stability). Each of the urban areas under investigation at different granularities was analyzed to identify the occurrence of associative relationships between it and other urban areas; moreover, we determined the degree of severity of such relationships. Our research results provide solid data that can be used as a reference by the various levels of Chinese governments for decision-making; overall, they can be used to improve the design of joint policies to prevent and control PM2.5 pollution in Chinese urban areas.

Artificial bee colony (ABC) algorithm has attracted growing interest for the continuous global optimization problems (CGOPs), where numerous algorithmic extensions have been developed. However, existing studies generally employ identical population size to perform the comparison among different ABC variants, regardless a fact that the generally suitable population size should be algorithm-dependent. Here we focus on the analysis of population size. This study is conducted in several well-known ABC variants under a set of benchmark CGOPs. We demonstrate that i) with the independently optimal population size, standard ABC can perform competitively comparing with its advanced variants, and ii) the most remunerative population size is related to the algorithmic exploitation/exploration ability. We anticipate that this study will provide useful insights to guide the appropriate usage of ABC, as well as its further enhancements.

Numerous models have been proposed to forecast the future trends of oil production and almost all of them are based on some predefined assumptions with various uncertainties. In this study, we propose a novel data-driven approach that uses symbolic regression to model oil production. We validate our approach on both synthetic and real data, and the results prove that symbolic regression could effectively identify the true models beneath the oil production data and also make reliable predictions. Symbolic regression indicates that world oil production will peak in 2021, which broadly agrees with other techniques used by researchers. Our results also show that the rate of decline after the peak is almost half the rate of increase before the peak, and it takes nearly 12 years to drop 4% from the peak. These predictions are more optimistic than those in several other reports, and the smoother decline will provide the world, especially the developing countries, with more time to orchestrate mitigation plans.

Graphical abstractDisplay Omitted HighlightsThis paper proposes a novel continuous estimation of distribution algorithm (EDA).A recent EDA named PMBGNP is extended from discrete domain to continuous domain.Reinforcement Learning (RL) is applied to construct the probabilistic model.Experiments on real mobile robot control show the superiority of the proposed algorithm.It bridges the gap between EDA and RL. Recently, a novel probabilistic model-building evolutionary algorithm (so called estimation of distribution algorithm, or EDA), named probabilistic model building genetic network programming (PMBGNP), has been proposed. PMBGNP uses graph structures for its individual representation, which shows higher expression ability than the classical EDAs. Hence, it extends EDAs to solve a range of problems, such as data mining and agent control. This paper is dedicated to propose a continuous version of PMBGNP for continuous optimization in agent control problems. Different from the other continuous EDAs, the proposed algorithm evolves the continuous variables by reinforcement learning (RL). We compare the performance with several state-of-the-art algorithms on a real mobile robot control problem. The results show that the proposed algorithm outperforms the others with statistically significant differences.

As the new form of online reviews, supplemental reviews have attracted the attention of many scholars. Considering current studies do not take full consideration on the content of reviews, the study goes better maturely and thoroughly on all information in supplemental reviews. In detail, sentiments of supplemental reviews in terms of different features corresponding to product, service and logistics are quantitatively analyzed. Except for the sentiments of reviews, other important factors including the volume of supplemental reviews, price, and ratings are introduced into the designed log-linear regression model for estimation. To explore the impact of supplemental reviews on product sales, an empirical study is conducted. The selected product with high involvement is mobile phone covering 32 products. The related sales as well as initial reviews and supplemental reviews are crawled from tmall.com for experiments. The period of data is from July 5, 2018 to July 24, 2018. By regression analysis, the results show that the sentiments of product features in both initial reviews and supplemental reviews and the sentiments of logistics features in supplemental reviews have significant positive impact on product sales. The volume of supplemental reviews has a negative impact on product sales. Compared with initial reviews, the impact of sentiments of product features on sales in supplemental reviews is greater.

In this paper, we integrate variable neighborhood search (VNS) into artificial bee colony (ABC) algorithm so that the search ability under variable neighborhood structures and local search is accelerated. Two VNS methods, including the reduced VNS and basic VNS, are integrated to develop different versions. The proposed algorithm, named variable neighborhood ABC (VNABC), is verified in a comprehensive set of benchmark functions. The experimental results confirm that VNABC outperforms the state-of-the-art ABC and differential evolution (DE) algorithms in terms of the convergence speed.

In recent years, numerous studies have drawn the success of estimation of distribution algorithms (EDAs) to avoid the frequent breakage of building blocks of the conventional stochastic genetic operators-based evolutionary algorithms (EAs). In this paper, a novel graph-based EDA called probabilistic model building genetic network programming (PMBGNP) is proposed. Using the distinguished graph (network) structure of a graph-based EA called genetic network programming (GNP), PMBGNP ensures higher expression ability than the conventional EDAs to solve some specific problems. Furthermore, an extended algorithm called reinforced PMBGNP is proposed to combine PMBGNP and reinforcement learning to enhance the performance in terms of fitness values, search speed, and reliability. The proposed algorithms are applied to solve the problems of controlling the agents' behavior. Two problems are selected to demonstrate the effectiveness of the proposed algorithms, including the benchmark one, i.e., the Tileworld system, and a real mobile robot control.

Classical estimation of distribution algorithms (EDAs) generally use truncation selection to estimate the distribution of the good individuals while ignoring the bad ones. However, various researches in evolutionary algorithms (EAs) have reported that the bad individuals may affect and help solving the problem. This paper proposes a new method to use the bad individuals by studying the substructures rather than the entire individual structures to solve reinforcement learning (RL) problems, which generally factorize their entire solutions to the sequences of state–action pairs. This work was studied in a recent graph-based EDA named probabilistic model building genetic network programming (PMBGNP), which could solve RL problems successfully, to propose an extended PMBGNP. The effectiveness of this work is verified in an RL problem, namely robot control. Compared to other related work, results show that the proposed method can significantly speed up the evolution efficiency. © 2013 Institute of Electrical Engineers of Japan. Published by John Wiley & Sons, Inc.

Objective To analyze the serotype distribution and drug resistance of Streptococcus pneumoniae isolated from pediatric patients in a Chinese hospital. Methods From October 2011 to May 2014, we collected 284 isolates (including 217 noninvasive and 67 invasive strains). We tested the antimicrobial susceptibility of these specimens using the Epsilomer test and disk diffusion method, and the expression of macrolide resistant genes ermB and mefA by polymerase chain reaction. Results The most common serotype for 217 noninvasive strains was 19F (31.3%). The coverage rates of the 7-, 10-, and 13-valent pneumococcal conjugate vaccines (PCV7, PCV10, and PCV13) were 53.9%, 53.9%, and 86.2%, respectively. For 67 invasive strains, the most common serotype was 23F (22.4%). The coverage rates of PCV7, PCV10, and PCV13 for invasive strains were 77.6%, 82.1%, and 91.0%, respectively. The susceptibility of strains isolated from nonmeningitis specimens to penicillin (PEN) was 97.2%. The rate of multidrug resistance in 284 isolates was 98.7%. All of these isolates were resistant to erythromycin (ERY) and had the ermB gene; 38.6% of those isolates had the mefA gene. Conclusions Compared with PCV7 and PCV10, the coverage rate of PCV13 was relatively higher for the S. pneumoniae isolates from pediatric patients. This finding suggests that PCV13 probably plays the strongest role in prevention of pneumococcal diseases and control of multidrug resistance. Because pneumococci were sensitive to PEN, this drug is still the preferred choice for clinical treatment of pediatric pneumococcal diseases.

Demand side management (DSM) is proposed to solve the contradiction between supply and demand of electricity market. To avoid the peak load, time-of-use (TOU) pricing strategy plays an important role in DSM to affect the behavior of using electricity by the users. In this paper, we proposed a mixed artificial bee colony (mABC) algorithm to TOU pricing optimization. Different from traditional research which optimizes the time division and electricity price separately, we consider these two factors together and optimize them simultaneously through the proposed mABC. The experimental results on a real-world scenario show the superiority of the mABC over traditional state-of-the-art methods.

Traditional accuracy-based XCS classifier system generally learns and evolves classifiers from scratch when facing each particular problem. Inspired by humans with the ability to learn new skills by inducing knowledge from related problems, transfer learning (TL) focuses on leveraging the knowledge of source domains to help the problem solving of another different but related domain. This paper attempts to combine XCS and TL to propose a novel extension transferable XCS (tXCS). tXCS utilizes the inherent characteristics of XCS, that naturally discovers expressive classifiers as the generalized knowledge of domains, to realize the classifier transfer from source domains to a target domain that makes it learn faster, which is conceptually different from the previous integrations between XCS and TL. The systematic study is presented to verify the ability of knowledge transfer between domains with different degrees of similarity, which has been pointed out to be the challenge of TL. We demonstrate that tXCS can significantly speed up the learning efficiency of canonical XCS in both of single-step and multi-step benchmark problems.

As a relatively new population-based technique for the continuous optimization problems, artificial bee colony algorithm (ABC) has verified its superiority and robustness over traditional evolutionary algorithms. However, regarding the wide variety of ABC extensions, the use of search experience produced during the search progress has been relatively unexplored to improve the performance. This results in an enormous waste of search resource to lower the search efficiency. In this paper, we develop a search experience-based search adaptation (SESA) approach to accelerate the search efficiency of ABC by taking three search resources into account, that is, the successful search directions, the fitness resource and the large number of failed solutions. The experiments over a comprehensive set of benchmark functions demonstrate that SESA can significantly accelerate the search efficiency of ABC.

As an extension of Genetic Algorithm (GA) and Genetic Programming (GP), a new approach named Genetic Network Programming (GNP) has been proposed in the evolutionary computation field. GNP uses multiple reusable nodes to construct directed-graph structures to represent its solutions. Recently, many research has clarified that GNP can work well in data mining area. In this paper, a novel evolutionary paradigm named GNP with Estimation of Distribution Algorithms (GNP-EDAs) is proposed and used to solve traffic prediction problems using class association rule mining. In GNP-EDAs, a probabilistic model is constructed by estimating the probability distribution from the selected elite individuals of the previous generation to replace the conventional genetic operators, such as crossover and mutation. The probabilistic model is capable of enhancing the evolution to achieve the ultimate objective. In this paper, two methods are proposed based on extracting the probabilistic information on the node connections and node transitions of GNP-EDAs to construct the probabilistic model. A comparative study of the proposed paradigm and the conventional GNP is made to solve the traffic prediction problems using class association rule mining. The simulation results showed that GNP-EDAs can extract the class association rules more effectively, when the number of the candidate class association rules increases. And the classification accuracy of the proposed method shows good results in traffic prediction systems.

Artificial bee colony (ABC) algorithm is a relatively new optimization technique that simulates the intelligent foraging behavior of honey bee swarms. It has been applied to several optimization domains to show its efficient evolution ability. In this paper, ABC algorithm is applied for the first time to evolve a directed graph chromosome structure, which derived from a recent graph-based evolutionary algorithm called genetic network programming (GNP). Consequently, it is explored to new application domains which can be efficiently modeled by the directed graph of GNP. In this work, a problem of controlling the agents's behavior under a wellknown benchmark testbed called Tileworld are solved using the ABC-based evolution strategy. Its performance is compared with several very well-known methods for evolving computer programs, including standard GNP with crossover/mutation, genetic programming (GP) and reinforcement learning (RL).

Though there are numerous approaches developed currently, exploring the practical applications of estimation of distribution algorithm (EDA) has been reported to be one of the most important challenges in this field. This paper is dedicated to extend EDA to solve one of the most active research problems - stock trading, which has been rarely revealed in the EDA literature. A recent proposed graph-based EDA called reinforced probabilistic model building genetic network programming (RPMBGNP) is investigated to create stock trading rules. With its distinguished directed graph-based individual structure and the reinforcement learning-based probabilistic modeling, we demonstrate the effectiveness of RPMBGNP for the stock trading task through real-market stock data, where much higher profits are obtained than traditional non-EDA models.

Traditional evolutionary algorithms (EAs) generally starts evolution from scratch, in other words, randomly. However, this is computationally consuming, and can easily cause the instability of evolution. In order to solve the above problems, this paper describes a new method to improve the evolution efficiency of a recently proposed graph-based EA - genetic network programming (GNP) - by introducing knowledge transfer ability. The basic concept of the proposed method, named GNP-KT, arises from two steps: First, it formulates the knowledge by discovering abstract decision-making rules from source domains in a learning classifier system (LCS) aspect; Second, the knowledge is adaptively reused as advice when applying GNP to a target domain. A reinforcement learning (RL)-based method is proposed to automatically transfer knowledge from source domain to target domain, which eventually allows GNP-KT to result in better initial performance and final fitness values. The experimental results in a real mobile robot control problem confirm the superiority of GNP-KT over traditional methods.

Genetic Network Programming (GNP) is derived from Genetic Algorithm (GA) and Genetic Programming (GP), which applies evolution theory to evolve a population of directed graph to model complex systems. It has been shown that GNP can solve typical control problems, as well as many real-world problems. However, studying GNP is mainly focused on the specific aspect, while the fundamental characteristics that ensure the success of GNP are rarely investigated in the previous research. This paper reveals an important feature of GNP - reusability of nodes - to efficiently identify and formulate the building blocks of evolution. Accordingly, adaptive GNP is developed which self-adapts both crossover and mutation probabilities of each search variable to circumstances. The adaptation allows the automatic adjustment of evolution bias toward the frequently reused nodes in high-quality individuals. The adaptive GNP is compared with traditional GNP in a benchmark control testbed to evaluate its superiority.

Recent advances in Learning Classifier Systems (LCSs) have shown their sequential decision-making ability with a generalization property. In this paper, a novel LCS named extended rule-based Genetic Network Programming (XrGNP) is proposed. Different from most of the current LCSs, the rules are represented and discovered through a graph-based evolutionary algorithm GNP, which consequently has the distinct expression ability to model and evolve the decision-making rules. XrGNP is described in details in which its unique features are explicitly mapped. Experiments on benchmark and real-world multi-step problems demonstrate the effectiveness of XrGNP.

Recent advances in rule-based systems, i.e., Learning Classifier Systems (LCSs), have shown their sequential decision-making ability with a generalization property. In this paper, a novel LCS named eXtended rule-based Genetic Network Programming (XrGNP) is proposed. Different from most of the current LCSs, the rules are represented and discovered through a graph-based evolutionary algorithm GNP, which consequently has the distinct expression ability to model and evolve the "if-then" decision-making rules. Experiments on a benchmark multi-step problem (so-called Reinforcement Learning problem) demonstrate its effectiveness.

Recently, a novel type of evolutionary algorithms EAs, called Genetic Network Programming GNP, has been proposed. Inspired by the complex human brain structures, GNP develops a distinguished directed graph structure for its individual representations, consequently showing an excellent expressive ability for modelling a range of complex problems. This paper is dedicated to reveal GNP's unique features. Accordingly, simplified genetic operators are proposed to highlight such features of GNP, reduce its computational effort and provide better results. Experimental results are presented to confirm its effectiveness over original GNP and several state-of-the-art algorithms.

Classical EDAs generally use truncation selection to estimate the distribution of the feasible (good) individuals while ignoring the infeasible (bad) ones. However, various research in EAs reported that the infeasible individuals may affect and help the problem solving. This paper proposed a new method to use the infeasible individuals by studying the sub-structures rather than the entire individual structures to solve Reinforcement Learning (RL) problems, which generally factorize their entire solutions to the sequences of state-action pairs. This work was studied in a recent graph-based EDA named Probabilistic Model Building Genetic Network Programming (PMBGNP) which can solve RL problems successfully. The effectiveness of this work is verified in a RL problem, i.e., robot control, comparing with some other related work.

This paper proposed a novel EDA, where a directed graph network is used to represent its chromosome. In the proposed algorithm, a probabilistic model is constructed from the promising individuals of the current generation using reinforcement learning, and used to produce the new population. The node connection probability is studied to develop the probabilistic model, therefore pairwise interactions can be demonstrated to identify and recombine building blocks in the proposed algorithm. The proposed algorithm is applied to a problem of agent control, i.e., autonomous robot control. The experimental results show the superiority of the proposed algorithm comparing with the conventional algorithms.

Time Related Association rule mining is a kind of sequence pattern mining for sequential databases. In this paper, a method of Generalized Association Rule Mining using Genetic Network Programming (GNP) with MBFP(Multi-Branch and Full-Pathes) processing mechanism has been introduced in order to find time related sequential rules more efficiently. GNP represents solutions as directed graph structures, thus has compact structure and partially observable Markov decision process. GNP has been applied to generate time related candidate association rules as a tool using the database consisting of a large number of time related attributes. The aim of this algorithm is to better handle association rule extraction from the databases in a variety of time-related applications, especially in the traffic volume prediction and its usage. The generalized algorithm which can find the important time related association rules has been proposed and experimental results are presented considering how to use the rules to predict the future traffic volume and also how to use the traffic prediction in the optimal search problem.