Multi-Objective Neural Evolutionary Algorithm for Combinatorial Optimization Problems

Deep Reinforcement Learning for Solving Vehicle Routing Problems With Backhauls

The vehicle routing problem with backhauls (VRPBs) is a challenging problem commonly studied in computer science and operations research. Featured by linehaul (or delivery) and backhaul (or pickup) customers, the VRPB has broad applications in real-world logistics. In this article, we propose a neural heuristic based on deep reinforcement learning (DRL) to solve the traditional and improved VRPB variants, with an encoder-decoder structured policy network trained to sequentially construct the routes for vehicles. Specifically, we first describe the VRPB based on a graph and cast the solution construction as a Markov decision process (MDP). Then, to identify the relationship among the nodes (i.e., linehaul and backhaul customers, and the depot), we design a two-stage attention-based encoder, including a self-attention and a heterogeneous attention for each stage, which could yield more informative representations of the nodes so as to deliver high-quality solutions. The evaluation on the two VRPB variants reveals that, our neural heuristic performs favorably against both the conventional and neural heuristic baselines on randomly generated instances and benchmark instances. Moreover, the trained policy network exhibits a desirable capability of generalization to various problem sizes and distributions.

Conditional Neural Heuristic for Multiobjective Vehicle Routing Problems

Existing neural heuristics for multiobjective vehicle routing problems (MOVRPs) are primarily conditioned on instance context, which failed to appropriately exploit preference and problem size, thus holding back the performance. To thoroughly unleash the potential, we propose a novel conditional neural heuristic (CNH) that fully leverages the instance context, preference, and size with an encoder-decoder structured policy network. Particularly, in our CNH, we design a dual-attention-based encoder to relate preferences and instance contexts, so as to better capture their joint effect on approximating the exact Pareto front (PF). We also design a size-aware decoder based on the sinusoidal encoding to explicitly incorporate the problem size into the embedding, so that a single trained model could better solve instances of various scales. Besides, we customize the REINFORCE algorithm to train the neural heuristic by leveraging stochastic preferences (SPs), which further enhances the training performance. Extensive experimental results on random and benchmark instances reveal that our CNH could achieve favorable approximation to the whole PF with higher hypervolume (HV) and lower optimality gap (Gap) than those of the existing neural and conventional heuristics. More importantly, a single trained model of our CNH can outperform other neural heuristics that are exclusively trained on each size. In addition, the effectiveness of the key designs is also verified through ablation studies.

Collaborative optimization of truck scheduling in container terminals using graph theory and DDQN

The container terminal is a key node in global trade and logistics, where trucks connect quay cranes, storage yards, and vessels. Optimizing truck scheduling is crucial for enhancing port efficiency by addressing issues such as low truck utilization, excessive quay crane waiting times, and extended equipment completion times. This paper develops a container terminal simulation model based on graph theory, with the objective of minimizing the maximum completion time of terminal equipment. A collaborative scheduling algorithm for truck fleets, based on Deep Double Q-Networks (DDQN), is proposed. The algorithm designs five heuristic rules as the action space and refines state features and reward functions to optimize scheduling effectively. Experimental results indicate that this algorithm consistently identifies optimal scheduling strategies, outperforming both the five heuristic rules and the Deep Q-Network (DQN) algorithm. It significantly reduces quay crane waiting times and equipment completion times, improves truck utilization, and enhances overall container terminal efficiency.

Deep Reinforcement Learning Versus Evolution Strategies: A Comparative Survey

Deep reinforcement learning (DRL) and evolution strategies (ESs) have surpassed human-level control in many sequential decision-making problems, yet many open challenges still exist. To get insights into the strengths and weaknesses of DRL versus ESs, an analysis of their respective capabilities and limitations is provided. After presenting their fundamental concepts and algorithms, a comparison is provided on key aspects, such as scalability, exploration, adaptation to dynamic environments, and multiagent learning. Current research challenges are also discussed, including sample efficiency, exploration versus exploitation, dealing with sparse rewards, and learning to plan. Then, the benefits of hybrid algorithms that combine DRL and ESs are highlighted.

Security Versus Accuracy: Trade-Off Data Modeling to Safe Fault Classification Systems

While the data-driven fault classification systems have achieved great success and been widely deployed, machine-learning-based models have recently been shown to be unsafe and vulnerable to tiny perturbations, i.e., adversarial attack. For the safety-critical industrial scenarios, the adversarial security (i.e., adversarial robustness) of the fault system should be taken into serious consideration. However, security and accuracy are intrinsically conflicting, which is a trade-off issue. In this article, we first study this new trade-off issue in the design of fault classification models and solve it from a brand new view, hyperparameter optimization (HPO). Meanwhile, to reduce the computational expense of HPO, we propose a new multiobjective (MO), multifidelity (MF) Bayesian optimization (BO) algorithm, MMTPE. The proposed algorithm is evaluated on safety-critical industrial datasets with the mainstream machine learning (ML) models. The results show that the following hold: 1) MMTPE is superior to other advanced optimization algorithms in both efficiency and performance and 2) fault classification models with optimized hyperparameters are competitive with advanced adversarially defensive methods. Moreover, insights into the model security are given, including the model intrinsic security properties and the correlations between hyperparameters and security.

A deep reinforcement learning algorithm framework for solving multi-objective traveling salesman problem based on feature transformation

As a special type of multi-objective combinatorial optimization problems (MOCOPs), the multi-objective traveling salesman problem (MOTSP) plays an important role in practical fields such as transportation and robot control. However, due to the complexity of its solution space and the conflicts between different objectives, it is difficult to obtain satisfactory solutions in a short time. This paper proposes an end-to-end algorithm framework for solving MOTSP based on deep reinforcement learning (DRL). By decomposing strategies, solving MOTSP is transformed into solving multiple single-objective optimization subproblems. Through linear transformation, the features of the MOTSP are combined with the weights of the objective function. Subsequently, a modified graph pointer network (GPN) model is used to solve the decomposed subproblems. Compared with the previous DRL model, the proposed algorithm can solve all the subproblems using only one model without adding weight information as input features. Furthermore, our algorithm can output a corresponding solution for each weight, which increases the diversity of solutions. In order to verify the performance of our proposed algorithm, it is compared with four classical evolutionary algorithms and two DRL algorithms on several MOTSP instances. The comparison shows that our proposed algorithm outperforms the compared algorithms both in terms of training time and the quality of the resulting solutions.

Multitask Learning for Joint Diagnosis of Multiple Mental Disorders in Resting-State fMRI

Facing the increasing worldwide prevalence of mental disorders, the symptom-based diagnostic criteria struggle to address the urgent public health concern due to the global shortfall in well-qualified professionals. Thanks to the recent advances in neuroimaging techniques, functional magnetic resonance imaging (fMRI) has surfaced as a new solution to characterize neuropathological biomarkers for detecting functional connectivity (FC) anomalies in mental disorders. However, the existing computer-aided diagnosis models for fMRI analysis suffer from unstable performance on large datasets. To address this issue, we propose an efficient multitask learning (MTL) framework for joint diagnosis of multiple mental disorders using resting-state fMRI data. A novel multiobjective evolutionary clustering algorithm is presented to group regions of interests (ROIs) into different clusters for FC pattern analysis. On the optimal clustering solution, the multicluster multigate mixture-of-expert model is used for the final classification by capturing the highly consistent feature patterns among related diagnostic tasks. Extensive simulation experiments demonstrate that the performance of the proposed framework is superior to that of the other state-of-the-art methods. Moreover, the potential for practical application of the framework is also validated in terms of limited computational resources, real-time analysis, and insufficient training data. The proposed model can identify the remarkable interpretative biomarkers associated with specific mental disorders for clinical interpretation analysis.

Normal vibration distribution search-based differential evolution algorithm for multimodal biomedical image registration

In linear registration, a floating image is spatially aligned with a reference image after performing a series of linear metric transformations. Additionally, linear registration is mainly considered a preprocessing version of nonrigid registration. To better accomplish the task of finding the optimal transformation in pairwise intensity-based medical image registration, in this work, we present an optimization algorithm called the normal vibration distribution search-based differential evolution algorithm (NVSA), which is modified from the Bernstein search-based differential evolution (BSD) algorithm. We redesign the search pattern of the BSD algorithm and import several control parameters as part of the fine-tuning process to reduce the difficulty of the algorithm. In this study, 23 classic optimization functions and 16 real-world patients (resulting in 41 multimodal registration scenarios) are used in experiments performed to statistically investigate the problem solving ability of the NVSA. Nine metaheuristic algorithms are used in the conducted experiments. When compared to the commonly utilized registration methods, such as ANTS, Elastix, and FSL, our method achieves better registration performance on the RIRE dataset. Moreover, we prove that our method can perform well with or without its initial spatial transformation in terms of different evaluation indicators, demonstrating its versatility and robustness for various clinical needs and applications. This study establishes the idea that metaheuristic-based methods can better accomplish linear registration tasks than the frequently used approaches; the proposed method demonstrates promise that it can solve real-world clinical and service problems encountered during nonrigid registration as a preprocessing approach.The source code of the NVSA is publicly available at https://github.com/PengGui-N/NVSA.

MiniNet: Dense squeeze with depthwise separable convolutions for image classification in resource-constrained autonomous systems

In recent years, artificial intelligence (AI) has been developed vigorously, and a great number of AI autonomous applications have been proposed. However, how to decrease computations and shorten training time with high accuracy under the limited hardware resource is a vital issue. In this paper, on the basis of MobileNet architecture, the dense squeeze with depthwise separable convolutions model is proposed, viz. MiniNet. MiniNet utilizes depthwise and pointwise convolutions, and is composed of the dense connection technique and the Squeeze-and-Excitation operations. The proposed MiniNet model is implemented and experimented with Keras. In experimental results, MiniNet is compared with three existing models, i.e., DenseNet, MobileNet, and SE-Inception-Resnet-v1. To validate that the proposed MiniNet model is provided with less computation and shorter training time, two types as well as large and small datasets are used. The experimental results showed that the proposed MiniNet model significantly reduces the number of parameters and shortens training time efficiently. MiniNet is superior to other models in terms of the lowest parameters, shortest training time, and highest accuracy when the dataset is small, especially.

Complex ontology alignment for autonomous systems via the Compact Co-Evolutionary Brain Storm Optimization algorithm

Autonomous Systems (ASs) that work in the open, dynamic environment are required to share their data entities and semantics to implement the co-operations. Typically, AS's data schemas and semantics are described via ontology. Since ASs need to maintain their autonomy and conceptual specificity, their ontologies might define one concept with different terms or in different contexts, which yields the heterogeneity issue and hampers their co-operations. An effective solution is to establish a set of data entity's correspondences through the Ontology Alignment (OA). Sine the simple correspondence of one-to-one style lacks expressiveness and cannot completely cover different types of heterogeneity, ASs' co-operations require using the complex correspondence of one-to-many or many-to-may style. Inspired by the success of applying the Brain Storm Optimization algorithm (BSO) to solve diverse complex optimization problems, this work proposes a Compact Co-Evolutionary BSO (CCBSO) to face the challenge of aligning AS ontologies. In particular, the AS ontology aligning problem is formally defined, a hybrid confidence measure for distinguishing the simple and complex correspondences is proposed, and a problem-specific CCBSO is presented. The experiment tests CCBSO's performance on different AS ontology aligning tasks, which consist of two simple ontology aligning tasks and one complex ontology aligning track. The experimental results show that CCBSO outperforms the state-of-the-art ontology aligning techniques on all simple and complex ontology aligning tasks.

A self-attention integrated spatiotemporal LSTM approach to edge-radar echo extrapolation in the Internet of Radars

In recent years, the number of weather-related disasters significantly increases across the world. As a typical example, short-range extreme precipitation can cause severe flooding and other secondary disasters, which therefore requires accurate prediction of extent and intensity of precipitation in a relatively short period of time. Based on the echo extrapolation of networked weather radars (i.e., the Internet of Radars), different solutions have been presented ranging from traditional optical-flow methods to recent deep neural networks. However, these existing networks focus on local features of echo variations to model the dynamics of holistic radar echo motion, so it often suffers from inaccurate extrapolation of the radar echo motion trend, trajectory, and intensity. To address the problem, this paper introduces the self-attention mechanism and an extra memory that saves global spatiotemporal feature into the original Spatiotemporal LSTM (ST-LSTM) to form a self-attention Integrated ST-LSTM recurrent unit (SAST-LSTM), capturing both spatial and temporal global features of radar echo motion. And several these units are stacked to build the radar echo extrapolation network SAST-Net. Comparative experiments show that the proposed model has better performance on different real world radar echo datasets over other recent methods.

Intelligent computational methods for multi-unmanned aerial vehicle-enabled autonomous mobile edge computing systems

This paper proposes a multi-unmanned aerial vehicle (UAV)-enabled autonomous mobile edge computing (MEC) system, in which several UAVs are deployed to provide services to user devices (UDs). The aim is to reduce/minimize the overall energy consumption of the autonomous system via designing the optimal trajectories of multiple UAVs. The problem is very complicated to be solved by traditional methods, as one has to take into account the deployment updation of stop points (SPs), the association of SPs with UDs and UAVs, and the optimal trajectories designing of UAVs. To tackle this problem, we propose a variable-length trajectory planning algorithm (VLTPA) consisting of three phases. In the first phase, the deployment of SPs is updated via presenting a genetic algorithm (GA) having variable-length individuals. Accordingly, the association between UDs and SPs is addressed by using a close rule. Finally, a multi-chrome GA is proposed to jointly handle the association of SPs with UAVs and their order for UAVs. The proposed VLTPA is tested via performing extensive experiments on eight instances ranging from 60 to 200 UDs, which reveal that the proposed VLTPA outperforms other compared state-of-the-art algorithms.

Fault Restoration of Six-Axis Force/Torque Sensor Based on Optimized Back Propagation Networks

Six-axis force/torque sensors are widely installed in manipulators to help researchers achieve closed-loop control. When manipulators work in comic space and deep sea, the adverse ambient environment will cause various degrees of damage to F/T sensors. If the disability of one or two dimensions is restored by self-restoration methods, the robustness and practicality of F/T sensors can be considerably enhanced. The coupling effect is an important characteristic of multi-axis F/T sensors, which implies that all dimensions of F/T sensors will influence each other. We can use this phenomenon to speculate the broken dimension by other regular dimensions. Back propagation neural network (BPNN) is a classical feedforward neural network, which consists of several layers and adopts the back-propagation algorithm to train networks. Hyperparameters of BPNN cannot be updated by training, but they impact the network performance directly. Hence, the particle swarm optimization (PSO) algorithm is adopted to tune the hyperparameters of BPNN. In this work, each dimension of a six-axis F/T sensor is regarded as an element in the input vector, and the relationships among six dimensions can be obtained using optimized BPNN. The average MSE of restoring one dimension and two dimensions over the testing data is 1.1693×10-5 and 3.4205×10-5, respectively. Furthermore, the average quote error of one restored dimension and two restored dimensions are 8.800×10-3 and 8.200×10-3, respectively. The analysis of experimental results illustrates that the proposed fault restoration method based on PSO-BPNN is viable and practical. The F/T sensor restored using the proposed method can reach the original measurement precision.

CED-Net: A more effective DenseNet model with channel enhancement

In recent years, deep convolutional neural network (CNN) has been applied more and more increasingly used in computer vision, natural language processing and other fields. At the same time, low-power platforms have more and more significant requirements for the size of the network. This paper proposed CED-Net (Channel enhancement DenseNet), a more efficient densely connected network. It combined the bottleneck layer with learned group convolution and channel enhancement module. The bottleneck layer with learned group convolution could effectively increase the network's accuracy without too many extra parameters and computation (FLOPs, Floating Point Operations). The channel enhancement module improved the representation of the network by increasing the interdependency between convolutional feature channels. CED-Net is designed regarding CondenseNet's structure, and our experiments show that the CED-Net is more effective than CondenseNet and other advanced lightweight CNNs. Accuracy on the CIFAR-10 dataset and CIFAR-100 dataset is 0.4 and 1% higher than that on CondenseNet, respectively, but they have almost the same number of parameters and FLOPs. Finally, the ablation experiment proves the effectiveness of the bottleneck layer used in CED-Net.

A hybrid Genetic–Grey Wolf Optimization algorithm for optimizing Takagi–Sugeno–Kang fuzzy systems

Nature-inspired optimization techniques have been applied in various fields of study to solve optimization problems. Since designing a Fuzzy System (FS) can be considered one of the most complex optimization problems, many meta-heuristic optimizations have been developed to design FS structures. This paper aims to design a Takagi–Sugeno–Kang fuzzy Systems (TSK-FS) structure by generating the required fuzzy rules and selecting the most influential parameters for these rules. In this context, a new hybrid nature-inspired algorithm is proposed, namely Genetic–Grey Wolf Optimization (GGWO) algorithm, to optimize TSK-FSs. In GGWO, a hybridization of the genetic algorithm (GA) and the grey wolf optimizer (GWO) is applied to overcome the premature convergence and poor solution exploitation of the standard GWO. Using genetic crossover and mutation operators accelerates the exploration process and efficiently reaches the best solution (rule generation) within a reasonable time. The proposed GGWO is tested on several benchmark functions compared with other nature-inspired optimization algorithms. The result of simulations applied to the fuzzy control of nonlinear plants shows the superiority of GGWO in designing TSK-FSs with high accuracy compared with different optimization algorithms in terms of Root Mean Squared Error (RMSE) and computational time.

Venture financing risk assessment and risk control algorithm for small and medium-sized enterprises in the era of big data

The existing risk assessment and control methods of enterprise risk financing have a large error in mobile data, which leads to inaccurate risk assessment results and low-risk optimization control efficiency. In order to improve the accuracy of risk financing risk assessment for small and medium-sized enterprises (SMEs) and risk control optimization efficiency, this article proposes risk assessment and risk control algorithms for SMEs in the era of big data. Through verifying the information of the loan application and supplementing the data during the loan period, invoke the existing enterprise financing risk database, establish the SME venture financing risk assessment model; build the risk evaluation index system according to the characteristics of the enterprise production organization, process characteristics, and the development of the socioeconomic and technical environment; apply the GA–PSO algorithm to the design of the SME risk financing risk control scheme, and complete the SME risk financing risk assessment and risk control. The experimental results show that the risk optimization control efficiency of the control algorithm reaches more than 70%, and the risk assessment accuracy of SMEs reaches over 95%, and the runtime less than 80 ms, with good convergence performance of risk assessment and control, strong risk optimization control ability, and accurate evaluation effect.

An Intelligent Telugu Handwritten Character Recognition using Multi-Objective Mayfly Optimization with Deep Learning Based DenseNet Model

Handwritten character recognition process has gained significant attention among research communities due to the application in assistive technologies for visually impaired people, human robot interaction, automated registry for business document, and so on. Handwritten character recognition of Telugu language is hard owing to the absence of massive dataset and trained convolution neural network (CNN). Therefore, this paper introduces an intelligent Telugu character recognition using multi-objective mayfly optimization with deep learning (MOMFO-DL) model. The proposed MOMFO-DL technique involves DenseNet-169 model as a feature extractor to generate a useful set of feature vectors. Moreover, functional link neural network (FLNN) is used as a classification model to recognize and classify the printer characters. The design of MOMFO technique for the parameter optimization of DenseNet model and FLNN model shows the novelty of the work. The use of MOMFO technique helps to optimally tune the parameters in such a way that the overall performance can be improved. The extensive experimental analysis takes place on benchmark datasets and the outcomes are examined with respect to different measures. The experimental results pointed out the supremacy of the MOMFO technique over the recent state of art methods.