Recently, a multitude of researchers have considered the fully connected topology (Gbest) as a default communication topology in particle swarm optimization (PSO). Despite many earlier studies of ...this issue indicating that the Gbest might favor unimodal problems, the topology with fewer connections, e.g., Lbest, might perform better on multimodal problems. It seems that different topologies make PSO a problem-related algorithm, while in this paper a problem-free PSO which integrates a reinforcement learning method has been proposed, referred to as QLPSO. In the new proposed algorithm, each particle acts as an agent independently, selecting the optimal topology under the control of
Q
-learning (QL) during each iteration. Two variants of QLPSO consider the different dimensions of the communication topology, respectively. In order to investigate the performance of QLPSO, experiments on 28 CEC 2013 benchmark functions are carried out when comparing with static and dynamic topologies. The reported computational results show that the proposed QLPSO is more superior compared with several state-of-the-art methods.
Omnipresent network/graph data generally have the characteristics of nonlinearity, sparseness, dynamicity and heterogeneity, which bring numerous challenges to network related analysis problem. ...Recently, influenced by the excellent ability of deep learning to learn representation from data, representation learning for network data has gradually become a new research hotspot. Network representation learning aims to learn a project from given network data in the original topological space to low-dimensional vector space, while encoding a variety of structural and semantic information. The vector representation obtained could effectively support extensive tasks such as node classification, node clustering, link prediction and graph classification. In this survey, we comprehensively present an overview of a large number of network representation learning algorithms from two clear points of view of homogeneous network and heterogeneous network. The corresponding algorithms are deeply analyzed. Extensive applications are introduced in an all-round way, and related experiments are conducted to validate the typical algorithms. Finally, we point out five future promising directions for next research in terms of theory and application.
Surface roughness is a key indicator of the quality of mechanical products, which can precisely portray the fatigue strength, wear resistance, surface hardness and other properties of the products. ...The convergence of current machine-learning-based surface roughness prediction methods to local minima may lead to poor model generalization or results that violate existing physical laws. Therefore, this paper combined physical knowledge with deep learning to propose a physics-informed deep learning method (PIDL) for milling surface roughness predictions under the constraints of physical laws. This method introduced physical knowledge in the input phase and training phase of deep learning. Data augmentation was performed on the limited experimental data by constructing surface roughness mechanism models with tolerable accuracy prior to training. In the training, a physically guided loss function was constructed to guide the training process of the model with physical knowledge. Considering the excellent feature extraction capability of convolutional neural networks (CNNs) and gated recurrent units (GRUs) in the spatial and temporal scales, a CNN-GRU model was adopted as the main model for milling surface roughness predictions. Meanwhile, a bi-directional gated recurrent unit and a multi-headed self-attentive mechanism were introduced to enhance data correlation. In this paper, surface roughness prediction experiments were conducted on the open-source datasets S45C and GAMHE 5.0. In comparison with the results of state-of-the-art methods, the proposed model has the highest prediction accuracy on both datasets, and the mean absolute percentage error on the test set was reduced by 3.029% on average compared to the best comparison method. Physical-model-guided machine learning prediction methods may be a future pathway for machine learning evolution.
Considerable research has been done on the complex stock market, however, there is very little systematic work on the impact of crisis on global stock markets. For filling in these gaps, we propose a ...complex network method, which analyzes the effects of the 2008 global financial crisis on global main stock index from 2005 to 2010. Firstly, we construct three weighted networks. The physics-derived technique of minimum spanning tree is utilized to investigate the networks of three stages. Regional clustering is found in each network. Secondly, we construct three average threshold networks and find the small-world property in the network before and during the crisis. Finally, the dynamical change of the network community structure is deeply analyzed with different threshold. The result indicates that for large thresholds, the network before and after the crisis has a significant community structure. Though this analysis, it would be helpful to investors for making decisions regarding their portfolios or to regulators for monitoring the key nodes to ensure the overall stability of the global stock market.
•A distributed fuzzy blocking flow-shop scheduling problem is investigated.•Two new constructive heuristics are proposed.•Two metaheuristics based on iterated greedy method are ...presented.•State-of-the-art results are obtained by the proposed methods.
In consideration of the uncertainty of manufacturing system, this paper investigates a distributed fuzzy blocking flow-shop scheduling problem (DFBFSP) in which there are multiple homogeneous factories and each one is set as a flow shop with no intermediate buffers between any consecutive machines. The processing time is uncertain and represented by the fuzzy number. The objective is to minimize the fuzzy makespan among all factories. To address this problem, two constructive heuristics (i.e., INEH and DPFNEH) are firstly proposed based on the problem-specific knowledge and the NEH heuristic. The INEH employs the spread value of fuzzy processing time to generate the initial job sequence. The DPFNEH assigns the partial jobs to factories by reducing the total expected idle time and blocking time. Afterwards, two iterated greedy (IG) methods are presented in which the proposed constructive heuristic is employed to generate the initial solution with high quality. A novel plateau exploration-based local search is incorporated to enhance the quality of solutions. To keep the search vitality, an improved acceptance criterion based on the fuzzy characteristic is designed to avoid falling into the local optimum. Finally, a comprehensive computational experiment and comparisons with the state-of-the-art methods in the literature are conducted based on an extended benchmark set and a new evaluation indicator. The results show that the proposed constructive heuristics and IG methods can effectively and efficiently solve the considered problem.
Scheduling in distributed production system has become an active research field in recent years. This paper investigates the distributed assembly blocking flow-shop scheduling problem (DABFSP), which ...consists of two stages: production and assembly. The first stage is processing jobs in several identical factories. Each factory has a series of machines no intermediate buffers existing between adjacent ones. The second stage assembles the processed jobs into the final products through a single machine. The objective is to minimize the maximum completion time or makespan of all products. To address this problem, a constructive heuristic is proposed based on a new assignment rule of jobs and a product-based insertion procedure. Afterwards, an iterated local search (ILS) is presented, which integrates an integrated encoding scheme, a multi-type perturbation procedure containing four kinds of perturbed operators based on problem-specific knowledge and a critical-job-based variable neighborhood search. Finally, a comprehensive computational experiment and comparisons with the closely related and well performing methods in the literature are carried out. The experimental and comparison results show that the proposed constructive heuristic and ILS can solve the DABFSP effectively and efficiently.
Object detection has been widely applied in various fields with the rapid development of deep learning in recent years. However, detecting small objects is still a challenging task because of the ...limited information in features and the complex background. To further enhance the detection accuracy of small objects, this paper proposes an efficient single-shot detector with weight-based feature fusion (WFFA-SSD). First, a weight-based feature fusion block is designed to adaptively fuse information from several multi-scale feature maps. The feature fusion block can exploit contextual information for feature maps with large resolutions. Then, a context attention block is applied to reinforce the local region in the feature maps. Moreover, a pyramids aggregation block is applied to combine the two feature pyramids to classify and locate target objects. The experimental results demonstrate that the proposed WFFA-SSD achieves higher mean Average Precision (mAP) under the premise of ensuring real-time performance. WFFA-SSD increases the mAP of the car by 4.12% on the test set of the CARPK.
Contemporary Smart Power Systems (SPNs) depend on Cyber-Physical Systems (CPSs) to connect physical devices and control tools. Developing a robust privacy-conserving intrusion detection method ...involves network and physical data regarding the setups, such as Supervisory Control and Data Acquisition (SCADA), for defending real data and recognizing cyber-attacks. A key issue in the implementation of SPNs is the security against cyber-attacks, targeting to interrupt SCADA operations and violate data privacy over the usage of penetration and data poisoning attacks. In this paper, a privacy-conserving framework, so-called PC-IDS, is proposed for realizing the privacy and safety features of SPNs through hybrid machine learning approach. The framework includes two key components. Primarily, a data pre-processing component is proposed for cleaning and transforming actual data into a different layout that accomplishes the aim of privacy conservation. Then, an intrusion detection component is proposed using a particle swarm optimization-based probabilistic neural network for the identification and recognition of malicious events. The performance of PC-IDS framework is evaluated by means of two commonly available datasets, i.e. the Power System and UNSW-NB15 datasets. The experimental outcomes highlight that the framework can proficiently protect data of SPNs and determine anomalous behaviours compared to numerous recent compelling state-of-the-art methods with respect to false positive rate (FPR), detection rate (DR) and computational processing time (CPT) by achieving
96.03%
of DR,
0.18%
FPR for Power System dataset and
95.91%
of DR,
0.14%
FPR for UNSW-NB15 dataset.
•Proposes a novel and generic heterogeneous network embedding approach.•Multi-source information in heterogeneous network is successfully modeled jointly.•The model is efficiently unified in the ...nonnegative matrix factorization framework.•Heterogeneous graph is transformed into homogeneous graph after semantic extraction.
Heterogeneous network embedding aims to learn a mapping between network data in original topological space and vectored data in low dimensional latent space, while encoding valuable information, such as structural and semantic information. The resulting vector representation has shown promising performance for extensive real-world applications, such as node classification and node clustering. However, most of existing methods merely focus on modeling network structural information, ignoring the rich multi-source information of different types of nodes. In this paper, we propose a novel Multi-source Information Fusion based Heterogeneous Network Embedding (MIFHNE) approach. We first capture the semantic information using the strategy of meta-graph based random walk. Subsequently, we jointly model the structural proximity, attribute information and label information in the framework of Nonnegative Matrix Factorization (NMF). Theoretical proofs and comprehensive experiments on two real-world heterogeneous network datasets demonstrate the feasibility and effectiveness of our approach.
Medication recommendation is attracting enormous attention due to its promise in effectively prescribing medicines and improving the survival rate of patients. Among all challenges, drug–drug ...interactions (DDI) related to undesired duplication, antagonism, or alternation between drugs could lead to fatal side effects. Previous researches usually provide models with DDI knowledge to achieve DDI reduction. However, the mixed use of patients with different DDI rates places stringent requirements on the generalization performance of models. In pursuit of a more effective method, we propose the adversarially regularized model for medication recommendation (ARMR). Specifically, ARMR firstly models temporal information from medical records to obtain patient representations and builds a key-value memory network based on information from historical admissions. Then, ARMR carries out multi-hop reading on the memory network to recommend medications. Meanwhile, ARMR uses a GAN model to adversarially regulate the distribution of patient representations by matching the distribution to a desired Gaussian distribution to achieve DDI reduction. Comparative evaluations between ARMR and baselines show that ARMR outperforms all baselines in terms of medication recommendation, achieving DDI reduction regardless of numbers of DDI types being considered.
PDF
