Exploitation Capabilities Research Articles

Cluster-Guided Contrastive Graph Clustering Network

Benefiting from the intrinsic supervision information exploitation capability, contrastive learning has achieved promising performance in the field of deep graph clustering recently. However, we observe that two drawbacks of the positive and negative sample construction mechanisms limit the performance of existing algorithms from further improvement. 1) The quality of positive samples heavily depends on the carefully designed data augmentations, while inappropriate data augmentations would easily lead to the semantic drift and indiscriminative positive samples. 2) The constructed negative samples are not reliable for ignoring important clustering information. To solve these problems, we propose a Cluster-guided Contrastive deep Graph Clustering network (CCGC) by mining the intrinsic supervision information in the high-confidence clustering results. Specifically, instead of conducting complex node or edge perturbation, we construct two views of the graph by designing special Siamese encoders whose weights are not shared between the sibling sub-networks. Then, guided by the high-confidence clustering information, we carefully select and construct the positive samples from the same high-confidence cluster in two views. Moreover, to construct semantic meaningful negative sample pairs, we regard the centers of different high-confidence clusters as negative samples, thus improving the discriminative capability and reliability of the constructed sample pairs. Lastly, we design an objective function to pull close the samples from the same cluster while pushing away those from other clusters by maximizing and minimizing the cross-view cosine similarity between positive and negative samples. Extensive experimental results on six datasets demonstrate the effectiveness of CCGC compared with the existing state-of-the-art algorithms. The code of CCGC is available at https://github.com/xihongyang1999/CCGC on Github.

A novel multimodal multi-objective optimization algorithm for multi-robot task allocation

Multi-robot task allocation (MRTA) is widely used in various fields and plays an important role in some complex task environments due to its ability to distribute parallel processing tasks. However, the multi-robot cooperative system is susceptible to actual environments or preferences of decision-makers. Therefore, providing enough solutions/schemes in the MRTA is important. To improve the reliability and feasibility of obtained solution set, an improved multimodal multi-objective differential evolution algorithm hybrid with a simulated annealing algorithm (IMMODE-SA) is proposed to solve MRTA problems in this study. In the proposed IMMODE-SA, a novel population initialization method is used to improve the population quality, and a redundant solution deletion method is employed to delete redundant solutions during the search process. Moreover, a simulated annealing algorithm is utilized to improve the exploitation capability in the last generation of evolutionary process. To verify the performance of the proposed algorithm, extensive simulation experiments are conducted on three MRTA instances. Experimental results show that the proposed algorithm performs better than other competitors on MRTA instances in terms of Hypervolume (HV). Also, the validity of the proposed algorithm is demonstrated via three experiments and experimental analysis results indicate that the IMMODE-SA can provide more equivalent optimal schemes to decision makers. Finally, it is crucial to solve MRTA problems with time window constraints.

Special Forces Algorithm: A novel meta-heuristic method for global optimization

This paper proposes a novel swarm intelligence optimizer inspired by human behavior called the Special Forces Algorithm (SFA). SFA is inspired by the missions of modern Special Forces in real life. First of all, in the initial stage of algorithm iteration, the speed of light mechanism is proposed for simulating the UAV-assisted search of special forces, and the loss probability mechanism is proposed for simulating the loss of contact due to force majeure during the search of special forces. The algorithm can more fully explore the solution space and enhance the ability of an algorithm to jump out of a local optimum. Secondly, by simulating the combat tactics of special forces, the algorithm uses command parameters to control the three stages of large-scale search, transitional stage search and small-scale precise search, making the balance between the exploration stage and the exploitation stage more reasonable. Finally, SFA inspired by special forces operations are presented. To verify the effectiveness of the proposed algorithm, SFA is compared with 6 classical algorithms in 23 benchmark functions. In addition, the algorithm is applied to practical engineering problems. Experimental results show that SFA has shown great potential and competitive results. SFA can achieve good search performance and optimization accuracy based on a better balance of exploration and exploitation capabilities.

Artificial Ecosystem-Based Optimization with Dwarf Mongoose Optimization for Feature Selection and Global Optimization Problems

Meta-Heuristic (MH) algorithms have recently proven successful in a broad range of applications because of their strong capabilities in picking the optimal features and removing redundant and irrelevant features. Artificial Ecosystem-based Optimization (AEO) shows extraordinary ability in the exploration stage and poor exploitation because of its stochastic nature. Dwarf Mongoose Optimization Algorithm (DMOA) is a recent MH algorithm showing a high exploitation capability. This paper proposes AEO-DMOA Feature Selection (FS) by integrating AEO and DMOA to develop an efficient FS algorithm with a better equilibrium between exploration and exploitation. The performance of the AEO-DMOA is investigated on seven datasets from different domains and a collection of twenty-eight global optimization functions, eighteen CEC2017, and ten CEC2019 benchmark functions. Comparative study and statistical analysis demonstrate that AEO-DMOA gives competitive results and is statistically significant compared to other popular MH approaches. The benchmark function results also indicate enhanced performance in high-dimensional search space.

Hierarchical learning particle swarm optimization using fuzzy logic

Particle swarm optimization (PSO) has been used extensively in numerical and engineering optimization problems in the last decades. However, due to drawbacks such as a single learning sample, PSO has the problems of loss of population diversity and easily falls into local optimum. To enhance optimization capability, a PSO based on fuzzy logic and hierarchical learning mechanism (FHPSO) is proposed. In FHPSO, the parameters are dynamically adjusted through fuzzy logic. The purpose of the fuzzy system is to generate appropriate parameters based on the performance metrics at each iteration, which better balances exploration and exploitation capability. Then particles are classified into different layers in terms of their fitness, and the particles in different layers perform different learning mechanisms. Each layer divides the particles into high-energy particles and low-energy particles. The high-energy particles in each layer are qualified to learn from the particles in the upper layer and the low-energy particles learn from the high-energy particles in their layer. This learning mechanism avoids all individuals to learn the global optimal individual at each iteration which will effectively reduce the speed and possibility of premature convergence and maintain population diversity. The FHPSO was compared with 8 well-known algorithms and 6 state-of-the-art PSO variants in the CEC 2022 and CEC 2021 test suites, respectively. The experimental results show significant performance of FHPSO. Simulation results for 5 complex engineering optimization problems and 3D path planning problem also show that the FHPSO can provides more competitive optimization results.

Enhancing feature selection with GMSMFO: A global optimization algorithm for machine learning with application to intrusion detection

Abstract The paper addresses the limitations of the Moth-Flame Optimization (MFO) algorithm, a meta-heuristic used to solve optimization problems. The MFO algorithm, which employs moths' transverse orientation navigation technique, has been used to generate solutions for such problems. However, the performance of MFO is dependent on the flame production and spiral search components, and the search mechanism could still be improved concerning the diversity of flames and the moths' ability to find solutions. The authors propose a revised version called GMSMFO, which uses a Novel Gaussian mutation mechanism and shrink MFO to enhance population diversity and balance exploration and exploitation capabilities. The study evaluates the performance of GMSMFO using the CEC 2017 benchmark and 20 datasets, including a high-dimensional intrusion detection system dataset. The proposed algorithm is compared to other advanced metaheuristics, and its performance is evaluated using statistical tests such as Friedman and Wilcoxon rank-sum. The study shows that GMSMFO is highly competitive and frequently superior to other algorithms. It can identify the ideal feature subset, improving classification accuracy and reducing the number of features used. The main contribution of this research paper includes the improvement of the exploration/exploitation balance and the expansion of the local search. The ranging controller and Gaussian mutation enhance navigation and diversity. The research paper compares GMSMFO with traditional and advanced metaheuristic algorithms on 29 benchmarks and its application to binary feature selection on 20 benchmarks, including intrusion detection systems. The statistical tests (Wilcoxon rank-sum and Friedman) evaluate the performance of GMSMFO compared to other algorithms. The algorithm source code is available at https://github.com/MohammedQaraad/GMSMFO-algorithm.

DETDO: An adaptive hybrid dandelion optimizer for engineering optimization

Dandelion Optimizer (DO) is a recently proposed swarm intelligence algorithm that coincides with the process of finding the best reproduction site for dandelion seeds. Compared with the classical Meta-heuristic algorithms, DO exhibits strong competitiveness, but it also has some drawbacks. In this paper, we proposed an adaptive hybrid dandelion optimizer called DETDO by combining three strategies of adaptive tent chaotic mapping, differential evolution (DE) strategy, and adaptive t-distribution perturbation to address the shortcomings of weak DO development, easy to fall into local optimum and slow convergence speed. Firstly, the adaptive tent chaos mapping is used in the initialization phase to obtain a uniformly distributed high-quality initial population, which helps the algorithm to enter the correct search region quickly. Secondly, the DE strategy is introduced to increase the diversity of dandelion populations to avoid algorithm stagnation, which improves the exploitation capability and the accuracy of the optimal solution. Finally, adaptive t-distribution perturbation around the elite solution successfully balances the exploration and exploitation phases while improving the convergence speed through a reasonable conversion from Cauchy to Gaussian distribution. The proposed DETDO is compared with classical or advanced optimization algorithms on CEC2017 and CEC2019 test sets, and the experimental results and statistical analysis demonstrate that the algorithm has better optimization accuracy and speed. In addition, DETDO has obtained the best results in solving six real-world engineering design problems. Finally, DETDO is applied to two bar topology optimization cases. Under a series of complex constraints, DETDO produces a lighter bar structure than the current scheme. It further illustrates the effectiveness and applicability of DETDO in practical problems. The above results mean that DETDO with strong competitiveness will become a preferred swarm intelligence algorithm to cope with optimization problems.

An intelligent feature selection method using binary teaching-learning based optimization algorithm and ANN

The most challenging issue in dealing with big datasets is the large number of their dimensions. Feature selection is a technique for reducing the dimensionality of datasets by removing irrelevant and useless features from the dataset, finally selecting the most crucial features in the dataset, will ultimately increase the algorithm's efficiency. This paper presents a novel feature selection procedure that includes a binary-modified teaching learning-based optimization algorithm (BMTLBO). One of the most effective and popular methods is the TLBO algorithm. Although this algorithm has a good convergence rate, there is a chance to get stuck in a local optimum. Our goal is to balance between exploration and exploitation capabilities. The proposed method consists of two parts: First, the BMTLBO algorithm, which includes the improved binary version of the basic algorithm, is used for the feature selection problem. The idea of a pool is used in this algorithm that boosts the population's diversity while enhancing the algorithm's precision and convergence rate. Second, we are used from improved TLBO algorithm with the self-learning phase (SLTLBO) for neural network training to show the application of the classification problem to evaluate the performance of the procedures of the method. We are tested the proposed method on 14 datasets in the term of classification accuracy and the number of features. Additionally, a different chemical data set named Biodegradable is used to assess the proposed method. The evaluation results demonstrate that, in terms of accuracy, convergence rate, and success in achieving promising solutions, the proposed algorithm outperforms all other optimization algorithms compared. The results are very promising and close to optimal.

Business Digitization’s Edifying Effects on a Firm’s Ambidexterity

Improving a firm’s simultaneous capabilities to exploit the existing opportunities whilst also exploring future opportunities is critical for catalysing a firm’s ambidexterity and sustainability. In that context, this research evaluates how business digitisation edifies a firm’s ambidexterity in the increasingly more discontinuous modern business environment. Using a qualitative-Delphi Method, the study diagnoses the perceptions of about twenty expert panelists from a cross-section of twenty enterprises in Aberdeen-Scotland on how digitised enterprise systems are often utilised to discern how the existing as well as future trends can be maximised to leverage a firm’s ambidexterity and sustainability. Findings indicated some of the businesses to take the initiatives to leverage their exploitation and exploration capabilities. However, it was still highly evident from most of the narratives that as most of the businesses focused on leveraging their existing state of performance, cost savings or the use of rational plans that only aim to achieve short-term business quests, it tends to undermine data optimisation in the simultaneous improvement of a firm’s exploitation and exploration capabilities. This is because most quests for optimising the digitised business systems or to undertake the required changes to leverage ambidexterity are often constrained by a combination of different heterogeneous internal business conditions that either cause low investments in digitisation or inflexibility that constrains change. It is not only the level of digitisation’s optimisation which is low, but also most businesses’ greater preponderance to focus on exploitation at the expense of exploration. Such business approach was found to undermine most quests for bolstering a firm’s ambidexterity. Considering that this area had not been explored by most of the previous studies, the study concludes with certain propositions that can enrich the existing ambidexterity theories by offering new insights on how digitisation highlights a new paradigm that can be optimised to bolster a firm’s ambidexterity.

An intelligent hybrid prairie dog optimization algorithm‐based stable cluster reliable routing scheme for VANETs

SummaryVehicular ad hoc network (VANET) is most significant for supporting intelligent transportation system (ITS)‐based technologies, but it gets hurdled by sparse distribution of vehicles on highways, and dynamically challenging topology that arises due to increase in traffic. Hence, energy stable and optimized cluster construction maximizes the network lifetime. In this paper, Hybrid Prairie Dogs and Beluga Whale Optimization‐based Node Clustering (HPDBWOA‐NC) mechanism is proposed with the parameters of highway route, node velocity, number of vehicular nodes, and communication for achieving stable cluster construction in VANETs. It is proposed with the balanced exploration and exploitation potential of Prairie Dog Optimization Algorithm (PDOA) and Beluga Whale Optimization Algorithm (BWOA) for establishing optimal clusters that increase the network stability during the routing process. It integrated the exploration and exploitation capabilities of PDOA and BWOA and confirmed better optimized clusters which confirmed reliable data delivery by preventing the issue of premature convergence. It constructed clusters and selected cluster heads (CHs) depending on the fitness factors of energy, interdistance between vehicles, communication range, and vehicular density. The results of the proposed HPDBWOA‐NC generated optimal number of CHs in the network which is comparatively 34.21% better than the benchmarked mechanisms. The mean throughput and packet delivery ratio (PDR) achieved by the proposed HPDBWOA‐NC are identified to be significantly improved by 25.48% and 28.91% better than the investigated metaheuristic clustering protocols. The statistical study also guaranteed an increased factor of 81, during the processing of optimizing the clusters during the employment of ITS applications in VANETs.

Multi-Objective Framework for Optimal Placement of Distributed Generations and Switches in Reconfigurable Distribution Networks: An Improved Particle Swarm Optimization Approach

Distribution network operators and planners face a significant challenge in optimizing planning and scheduling strategies to enhance distribution network efficiency. Using improved particle swarm optimization (IPSO), this paper presents an effective method for improving distribution system performance by concurrently deploying remote-controlled sectionalized switches, distributed generation (DG), and optimal network reconfiguration. The proposed optimization problem’s main objectives are to reduce switch costs, maximize reliability, reduce power losses, and enhance voltage profiles. An analytical reliability evaluation is proposed for DG-enhanced reconfigurable distribution systems, considering both switching-only and repairs and switching interruptions. The problem is formulated in the form of a mixed integer nonlinear programming problem, which is known as an NP-hard problem. To solve the problem effectively while improving conventional particle swarm optimization (PSO) exploration and exploitation capabilities, a novel chaotic inertia weight and crossover operation mechanism is developed here. It is demonstrated that IPSO can be applied to both single- and multi-objective optimization problems, where distribution systems’ optimization strategies are considered sequentially and simultaneously. Furthermore, IPSO’s effectiveness is validated and evaluated against well-known state-of-the-art metaheuristic techniques for optimizing IEEE 69-node distribution systems.

How does human resource management balance exploration and exploitation? The differential effects of intellectual capital‐enhancing HR practices on ambidexterity and firm innovation

AbstractAfter decades, dialogues on human resource management (HRM), intellectual capital (IC), and ambidexterity still continue, mirroring that the role of ambidextrous capability in translating the impact of HRM into superior performance remains unclarified. At this juncture, the current study proposes a novel theoretical framework to extend research on the relationship between IC‐enhancing HR practices and innovation. It is done sophisticatedly by examining how firm exploitative and exploratory capabilities mediate the relationship between different combinations of HR configurations and firm innovation. To this end, we designed rigorous time‐lagged research with three waves of data collection from the Iranian healthcare sector. Our analyses revealed that firm explorative and exploitative capabilities significantly mediate the relationship between human, social, and organizational capital‐enhancing HR configurations and firm innovation. More conspicuously, by unraveling interaction patterns among distinct HR configurations, our study revealed the intricacies of the functioning of IC‐enhancing HR practices in fueling firm ambidexterity. Hence, our study offers design options to navigate through exploitation and exploration in light of the firm's core innovation strategy. We discuss the theoretical and practical implications of our findings and suggest future research avenues.

Hybrid Genetic and Spotted Hyena Optimizer for Flow Shop Scheduling Problem

This paper presents a new hybrid algorithm that combines genetic algorithms (GAs) and the optimizing spotted hyena algorithm (SHOA) to solve the production shop scheduling problem. The proposed GA-SHOA algorithm incorporates genetic operators, such as uniform crossover and mutation, into the SHOA algorithm to improve its performance. We evaluated the algorithm on a set of OR library instances and compared it to other state-of-the-art optimization algorithms, including SSO, SCE-OBL, CLS-BFO and ACGA. The experimental results show that the GA-SHOA algorithm consistently finds optimal or near-optimal solutions for all tested instances, outperforming the other algorithms. Our paper contributes to the field in several ways. First, we propose a hybrid algorithm that effectively combines the exploration and exploitation capabilities of SHO and GA, resulting in a balanced and efficient search process for finding near-optimal solutions for the FSSP. Second, we tailor the SHO and GA methods to the specific requirements of the FSSP, including encoding schemes, objective function evaluation and constraint handling, which ensures that the hybrid algorithm is well suited to address the challenges posed by the FSSP. Third, we perform a comprehensive performance evaluation of the proposed hybrid algorithm, demonstrating its effectiveness in terms of solution quality and computational efficiency. Finally, we provide an in-depth analysis of the behavior of the hybrid algorithm, discussing the roles of the SHO and GA components and their interactions during the search process, which can help understand the factors contributing to the success of the algorithm and provide insight into potential improvements or adaptations to other combinatorial optimization problems.

An effective hybrid algorithm for joint scheduling of machines and AGVs in flexible job shop

Flexible job shops motivated by small batches and multiple orders require the collaboration of machines and automated guided vehicles (AGVs) scheduling to boost shop floor flexibility and productivity. The joint scheduling of machines and AGVs can better achieve global optimization. However, joint scheduling requires two NP hard problems to be solved simultaneously. Therefore, this paper employs a multi-AGV flexible job shop scheduling problem (MA-FJSP) with an effective hybrid algorithm. First of all, a model is established with the objectives of minimizing the makespan, the total AGV running time and the total machine load. To solve the MA-FJSP, high-quality initialization methods and improved elite strategies are designed to improve global convergence in the proposed algorithm. In addition, a problem-knowledge-based neighborhood search is integrated to improve its exploitation capability. At last, a series of comparative experimental studies were performed to exam the effectiveness of the improved algorithm. The results demonstrate that the solutions gained by the proposed algorithm perform well in respect of convergence, diversity and distribution.

Effective Feature Selection Strategy for Supervised Classification based on an Improved Binary Aquila Optimization Algorithm

Feature Selection (FS) is considered a crucial step in machine learning and data mining tasks, which facilitates minimizing the direct consequence of redundant and irrelevant attributes on the model’s accuracy. Hence, the researchers developed various algorithms to choose the most appropriate features for improving the accuracy rate of the presented dataset. Nevertheless, these algorithms may fall into local optima problems when applied to substantial feature sizes’ datasets. In this paper, for handling the FS strategy through dimensionality-lessening while improving the classification accuracy, an effective Aquila Optimization (AO) algorithm is introduced. AO has stable exploration and exploitation capabilities. It is enhanced by integrating a random position amendment approach with Local Search (LS) strategy to avoid local optima and then cloned into a binary version called Improved Binary AO (IBAO). Additionally, k-Nearest Neighbor (k-NN) and Support Vector Machine (SVM) are quality estimators. On 18 multi-scale benchmarks, the IBAO algorithm is compared with the original BAO algorithm and twelve recent algorithms, such as Binary Artificial Bee Colony (BABC), Binary Bat Algorithm (BBA), Binary Particle Swarm Optimization (BPSO), Binary Whale Optimization Algorithm (BWOA), Binary Grey Wolf Optimization (BGWO), Binary Sailfish Optimizer (BSFO), Binary Henry Gas Solubility Optimization (BHGSO), Binary Harris Hawks Optimization (BHHO). According to Wilcoxon’s rank-sum test (α=0.05), the dominance and significant influence of IBAO are apparent on both small and large dimensional benchmarks and obtained classification accuracy up to 100% in some of these benchmarks integrated with a feature reduction size down to 92%.

Set algebra — based algebraic evolutionary algorithm for binary optimization problems

In order to design algebraic evolutionary algorithms by set algebra, the intersection, union, complement, difference and symmetric difference operations of 0-1 vectors on {0,1}n are firstly defined based on set operations. Then, the isomorphism between algebraic system defined on {0,1}n and set algebra defined on power set P(Ω) of set Ω is proved. Therefrom a simple and fast implement method of set algebra is proposed. Third, symmetric difference operator and asymmetric mutation operator are successively proposed based on set algebra, they have global exploration and local exploitation capabilities respectively. On this basis, a novel algebraic evolutionary algorithm, named set algebra-based heuristic algorithm (SAHA), is proposed based on the operations of 0-1 vectors on {0,1}n for solving binary optimization problems. For verifying the performance of SAHA, it is used to solve 0-1 knapsack problem (0-1KP) and knapsack problem with single continuous variable (KPC), respectively. The comparison with the state-of-the-art algorithms of solving 0-1KP and KPC shows that SAHA can not only obtain excellent calculation results, but also is faster speed, it is most competitive for solving binary optimization problems.

Novel hybrid of AOA-BSA with double adaptive and random spare for global optimization and engineering problems

Archimedes Optimization Algorithm (AOA) is a new physics-based optimizer that simulates Archimedes principles. AOA has been used in a variety of real-world applications because of potential properties such as a limited number of control parameters, adaptability, and changing the set of solutions to prevent being trapped in local optima. Despite the wide acceptance of AOA, it has some drawbacks, such as the assumption that individuals modify their locations depending on altered densities, volumes, and accelerations. This causes various shortcomings such as stagnation into local optimal regions, low diversity of the population, weakness of exploitation phase, and slow convergence curve. Thus, the exploitation of a specific local region in the conventional AOA may be examined to achieve a balance between exploitation and exploration capabilities in the AOA. The bird Swarm Algorithm (BSA) has an efficient exploitation strategy and a strong ability of search process. In this study, a hybrid optimizer called AOA-BSA is proposed to overcome the limitations of AOA by replacing its exploitation phase with a BSA exploitation one. Moreover, a transition operator is used to have a high balance between exploration and exploitation. To test and examine the AOA-BSA performance, in the first experimental series, 29 unconstrained functions from CEC2017 have been used whereas the series of the second experiments use seven constrained engineering problems to test the AOA-BSA’s ability in handling unconstrained issues. The performance of the suggested algorithm is compared with 10 optimizers. These are the original algorithms and 8 other algorithms. The first experiment’s results show the effectiveness of the AOA-BSA in optimizing the functions of the CEC2017 test suite. AOABSA outperforms the other metaheuristic algorithms compared with it across 16 functions. The results of AOABSA are statically validated using Wilcoxon Rank sum. The AOABSA shows superior convergence capability. This is due to the added power to the AOA by the integration with BSA to balance exploration and exploitation. This is not only seen in the faster convergence achieved by the AOABSA, but also in the optimal solutions found by the search process. For further validation of the AOABSA, an extensive statistical analysis is performed during the search process by recording the ratios of the exploration and exploitation. For engineering problems, AOABSA achieves competitive results compared with other algorithms. the convergence curve of the AOABSA reaches the lowest values of the problem. It also has the minimum standard deviation which indicates the robustness of the algorithm in solving these problems. Also, it obtained competitive results compared with other counterparts algorithms regarding the values of the problem variables and convergence behavior that reaches the best minimum values.

Microalgae from Cold Environments and Their Possible Biotechnological Applications.

Cold environments include deep ocean, alpine, and polar areas. Even if the cold conditions are harsh and extreme for certain habitats, various species have been adapted to survive in them. Microalgae are among the most abundant microbial communities which have adapted to live in low light, low temperature, and ice coverage conditions typical of cold environments by activating different stress-responsive strategies. These species have been shown to have bioactivities with possible exploitation capabilities for human applications. Even if they are less explored compared to species living in more accessible sites, various activities have been highlighted, such as antioxidant and anticancer activities. This review is focused on summarizing these bioactivities and discussing the possible exploitation of cold-adapted microalgae. Thanks to the possibility of mass cultivating algae in controlled photobioreactors, eco-sustainable exploitation is in fact possible by sampling a few microalgal cells without impacting the environment.

Learning ambidexterity and innovation in creative industries. the role of enabling formalisation

ABSTRACT This study analyzed the impact of learning ambidexterity on innovation and tested the mediating effect of enabling formalisation on this relationship in creative industries. Polynomial regressions were used to test the hypothesised relationships on a sample consisting of 379 medium and large sized Romanian firms. The results demonstrate that the learning ambidexterity improves innovation, while enabling formalisation is mediating the effects of exploratory and exploitative learning capabilities on innovation. By examining the relationships between learning ambidexterity and innovation, it extends other studies findings. The paper contributes to deeper examination of formalisation on innovation outcomes by focusing on enabling formalisation. The study is performed in creative industries and in medium and large sized companies, usually poorly researched contexts in relation with learning ambidexterity. The study contributes to ambidexterity literature by focusing specifically on learning capability, a new type of organisational capability. Due to the relative lack of validated understanding of the learning ambidexterity impact on innovation, this study contributes to the development of theory explaining this interaction and its effects. Finally, the results demonstrate complementarity between exploratory and exploitative learning capabilities.

A Hybrid Two-Stage Teaching-Learning-Based Optimization Algorithm for Feature Selection in Bioinformatics.

The "curse of dimensionality" brings new challenges to the feature selection (FS) problem, especially in bioinformatics filed. In this paper, we propose a hybrid Two-Stage Teaching-Learning-Based Optimization (TS-TLBO) algorithm to improve the performance of bioinformatics data classification. In the selection reduction stage, potentially informative features, as well as noisy features, are selected to effectively reduce the search space. In the following comparative self-learning stage, the teacher and the worst student with self-learning evolve together based on the duality of the FS problems to enhance the exploitation capabilities. In addition, an opposition-based learning strategy is utilized to generate initial solutions to rapidly improve the quality of the solutions. We further develop a self-adaptive mutation mechanism to improve the search performance by dynamically adjusting the mutation rate according to the teacher's convergence ability. Moreover, we integrate a differential evolutionary method with TLBO to boost the exploration ability of our algorithm. We conduct comparative experiments on 31 public data sets with different data dimensions, including 7 bioinformatics datasets, and evaluate our TS-TLBO algorithm compared with 11 related methods. The experimental results show that the TS-TLBO algorithm obtains a good feature subset with better classification performance, and indicates its generality to the FS problems.