Adaptive Search Research Articles

Utilizing Heuristics and Metaheuristics for Solving the Set Covering Problem

A basic combinatorial optimization problem, the Set Covering Problem (SCP) finds extensive use in computer science, operations research, and logistics, among other domains. The SCP’s goal is to determine the smallest number of subsets, or sets, needed to cover every element precisely once given a finite set of items and a collection of subsets of these elements. Numerous practical uses for the SCP exist, such as crew scheduling, truck routing, and facility locating. This paper focuses on obtaining feasible solutions, applying to the obtained solutions constructive heuristics (CH), followed by a redundancy elimination procedure to remove unnecessary sets. To further optimize the quality of the solution, a local search method is also implemented based on the First and Best improvement algorithms. Additionally, the Greedy Randomized Adaptive Search Procedure (GRASP) and Variable Neighborhood Search (VNS) metaheuristics are designed and implemented. Each implemented heuristic underwent testing across 42 instances, with the average deviation from the optimal solution calculated for each instance. The GRASP heuristic demonstrated the most favorable performance, achieving a maximum deviation of 2.26% from the optimal solution, while the VNS approach yielded a maximum deviation of 11.46% from the optimal solution at its best.

Modified Whale Algorithm and Morley PSO-ML-Based Hyperparameter Optimization for Intrusion Detection

Intrusion detection averts a network from probable intrusions by inspecting network traffic to ensure its integrity, availability, and confidentiality. Though IDS seems to eliminate malicious traffic, intruders have endeavored to use different approaches for undertaking attacks. Hence, effective intrusion detection is vital to detect attacks. Concurrently, the evolvement of machine learning (ML), attacks could be identified by evaluating the patterns and learning from them. Considering this, conventional works have attempted to perform intrusion detection. Nevertheless, they lacked about high false alarm rate (FAR) and low accuracy rate due to inefficient feature selection. To resolve these existing pitfalls, this research proposed a modified whale algorithm (MWA) based on nonlinear information gain to select significant and relevant features. This algorithm assures huge initialization to improve local search ability as the agent’s positions are usually near the optimal solution. It is also utilized for an adaptive search for an optimal combination of features. Following this, the research proposes Morlet particle swarm optimization hyperparameter optimization (MPSO-HO) to improve the convergence rate of the algorithm by consenting it to produce from the local optimization by improving its capability. Standard metrics assess the proposed system to confirm the optimal performance of the proposed system. Outcomes explore the effective ability of the proposed system in intrusion detection.

Adaptive diversity-based quantum circuit architecture search

Quantum variational algorithms (VQAs) are highly promising to realize quantum advantages on near-term quantum devices. Existing VQAs based on a manually fixed quantum are computationally inefficient due to noise and the limited coupling maps of these devices. Previous work considers various quantum architecture search (QAS) algorithms to autodesign a quantum based on specific questions to improve the performance of VQAs. Compared to manual design, autodesign can more efficiently explore the large space of a possible and achieve better performance. However, two main challenges in utilizing QAS to design quantum circuits efficiently are the tremendous amount of space required for candidate quantum circuits, and the disconnection between quantum devices and autodesign in terms of qubit mapping and quantum noise. To address these issues, we propose an adaptive diversity-based quantum search algorithm to efficiently generate the optimal quantum circuit based on device qubit mapping and noise. By considering the diversity among different candidate circuits and adaptively adding circuit depths, our approach only needs to focus on a small optimization space at each iteration step. In addition, the synchronization of optimizing circuit structure and aligning qubit mapping enables us to generate quantum circuits while avoiding additional mapping overhead. We evaluate the performance of our algorithm on simulators and real quantum devices for quantum eigenvalue problems and classification tasks. Results demonstrate that quantum circuits generated by our method outperform both a fixed hardware-efficient and randomly generated quantum circuits in terms of final performance and resource-saving. Our algorithm provides a flexible way to efficiently generate excellent quantum circuits for significantly improving the performances of VQAs on near-term quantum devices. Published by the American Physical Society 2024

An Enhanced Tunicate Swarm Algorithm with Symmetric Cooperative Swarms for Training Feedforward Neural Networks

The input layer, hidden layer, and output layer are three models of neural processors that comprise feedforward neural networks. In this paper, an enhanced tunicate swarm algorithm based on a differential sequencing alteration operator (ETSA) with symmetric cooperative swarms is presented to train feedforward neural networks. The objective is to accomplish minimum classification errors and the most appropriate neural network layout by regulating the layers’ connection weights and neurons’ deviation thresholds according to the transmission error between the anticipated input and the authentic output. The TSA mimics jet motorization and swarm scavenging to mitigate directional collisions and to maintain the greatest solution that is customized and regional. However, the TSA exhibits the disadvantages of low computational accuracy, a slow convergence speed, and easy search stagnation. The differential sequencing alteration operator has adaptable localized extraction and search screening to broaden the identification scope, enrich population creativity, expedite computation productivity, and avoid search stagnation. The ETSA integrates exploration and exploitation to mitigate search stagnation, which has sufficient stability and flexibility to acquire the finest solution. The ETSA was distinguished from the ETTAO, EPSA, SABO, SAO, EWWPA, YDSE, and TSA by monitoring seventeen alternative datasets. The experimental results confirm that the ETSA maintains profound sustainability and durability to avoid exaggerated convergence, locate the acceptable transmission error, and equalize extraction and prospection to yield a faster convergence speed, superior calculation accuracy, and greater categorization accuracy.

A study on multiple types of yard cranes rescheduling in ports considering carbon emission

ABSTRACT This paper investigates the rescheduling problem of multiple oil-driven and electric-driven yard cranes across multiple container yards in semi-automated container terminals under random faults. Efficient fault diagnosis and handling mechanisms are provided to mitigate the effects of faults on the performance of yard operations. At the same time, a rescheduling model is proposed, aiming to minimize weighted carbon emissions and completion time. By analyzing the features of the problem, a tailored adaptive large neighborhood search (ALNS) algorithm is designed to solve the model. The effectiveness of the ALNS is verified through problem instances generated from the operational data of the port of Dalian in China. The factors considered in this paper are relevant to actual port operations, thus offering reliable solutions for scheduling and greening of ports.

Performance Evaluation of Ultrasound Images Using Non-Local Means Algorithm with Adaptive Isotropic Search Window for Improved Detection of Salivary Gland Diseases: A Pilot Study.

Speckle noise in ultrasound images (UIs) significantly reduces the accuracy of disease diagnosis. The aim of this study was to quantitatively evaluate its feasibility in salivary gland ultrasound imaging by modeling the adaptive non-local means (NLM) algorithm. UIs were obtained using an open-source device provided by SonoSkills and FUJIFILM Healthcare Europe. The adaptive NLM algorithm automates optimization by modeling the isotropic search window, eliminating the need for manual configuration in conventional NLM methods. The coefficient of variation (COV), contrast-to-noise ratio (CNR), and edge rise distance (ERD) were used as quantitative evaluation parameters. UIs of the salivary glands revealed evident visualization of the internal echo shape of the malignant tumor and calcification line using the adaptive NLM algorithm. Improved COV and CNR results (approximately 4.62 and 2.15 times, respectively) compared with noisy images were achieved. Additionally, when the adaptive NLM algorithm was applied to the UIs of patients with salivary gland sialolithiasis, the noisy images and ERD values were calculated almost similarly. In conclusion, this study demonstrated the applicability of the adaptive NLM algorithm in optimizing search window parameters for salivary gland UIs.

An improved Bi-RRT*-based path planning algorithm with adaptive search strategy assignment mechanism for ultra-low-altitude penetration of fixed-wing aircraft

The ultra-low-altitude penetration with complex three-dimensional terrain environment usually requires the path planning algorithm to be computationally efficient to generate feasible optimized flight paths in a limited period of time. This paper investigates an improved bidirectional rapidly-exploring random tree* (RRT*) path planning algorithm with adaptive search strategy assignment mechanism to accelerate the exploration speed. The greedy optimization method and the three-dimensional Dubins method are utilized to reduce redundant nodes and optimize the flight path to satisfy the kinematic constraints of the fixed-wing aircraft. The model predictive control method is then employed to design the path-following controller, in which multiple types of constraints can be addressed. To demonstrate the superior planning efficiency of the proposed adaptive-alternating-exploration RRT* method, the existing widely-used path planning algorithms are used as benchmarks in the simulation studies. Simulation results show that the path planning time can be significantly reduced by up to 90% with the proposed adaptive-alternating-exploration RRT* method, simultaneously with optimized path length. Moreover, the designed model predictive path-following controller succeeds to track the planned collision-free path with maximum tracking errors of less than 2 meters. The effectiveness of the path planning algorithm and the designed controller is thoroughly demonstrated.

High Probability Complexity Bounds for Adaptive Step Search Based on Stochastic Oracles

High Probability Complexity Bounds for Adaptive Step Search Based on Stochastic Oracles

Time-series traction prediction of surrounding rock deformation in tunnel construction based on mechanical parameter inversion

The deformation of the surrounding rock serves as a macroscopic representation of the stability status of the tunnel, and is also an important indicator for stability evaluation. To address the difficulty of accurately predicting long-term deformation in tunnel surrounding rock with limited monitoring data, a time-series traction prediction method based on the inversion of mechanical parameters was proposed. Employing the adaptive vigilance chaotic sparrow search algorithm (ACSSA) to optimize initial parameters in extreme learning machines (ELM) and long short-term memory (LSTM) neural networks. It then constructed two deformation time-series prediction models and a rock mechanics parameter inversion model based on the ACSSA-ELM and ACSSA-AMLSTM algorithms. Based on the mechanical parameter inversion model and numerical simulation, the value of the surrounding rock deformation at the key construction nodes of the tunnel was calculated as the traction point, and the traction interval and traction control equation were defined. Cubic spline interpolation and wavelet decomposition were employed to preprocess the measured deformation data of the surrounding rock. Subsequently, the proposed time-series prediction model was utilized for prediction. The predicted results within the traction interval undergo correction based on the traction points, thereby achieving a more precise and intelligent prediction of the tunnel surrounding rock deformation. Based on literature cases and data from the Huayang Tunnel project in Chongqing, the proposed method was validated and applied. The model's accuracy has been validated and successfully guided construction and production. Finally, the impact of different methods on traction effectiveness and the distribution pattern of traction points on model performance was discussed.

Inversion of Seabed Geotechnical Properties in the Arctic Chukchi Deep Sea Basin Based on Time Domain Adaptive Search Matching Algorithm

Inversion of Seabed Geotechnical Properties in the Arctic Chukchi Deep Sea Basin Based on Time Domain Adaptive Search Matching Algorithm

An Approach to Solve the Heterogeneous Fixed Fleet Vehicle Routing Problem With Time Window Based on Adaptive Large Neighborhood Search Meta-Heuristic

An Approach to Solve the Heterogeneous Fixed Fleet Vehicle Routing Problem With Time Window Based on Adaptive Large Neighborhood Search Meta-Heuristic

Adaptive variable neighborhood search algorithm with Metropolis rule and tabu list for satellite range scheduling problem

Efficient scheduling of measurement and control resources plays a critical role in successful satellite operations. The tremendous growth in the number of satellites in orbit exacerbates resource scarcity, further enhancing the significance of the satellite range scheduling problem (SRSP). In order to maximize the benefits of measurement and control tasks, we propose an innovative algorithm to solve the SRSP with numerous constraints. Firstly, the SRSP operation flow is analyzed to establish a constraint satisfaction model. A task-resource matching algorithm based on fitness is then designed to generate an initial feasible solution with superior quality by heuristic criteria. Subsequently, an adaptive variable neighborhood search algorithm with Metropolis rule and tabu list (AVNS-MT) is proposed to solve the mathematical model. Three swap neighborhood structures are constructed to explore the solution space efficiently during the variable neighborhood descent search process. Meanwhile, three migration neighborhood structures are devised to enable the shaking of solutions and evasion from the local optimum. Moreover, the incorporation of the Metropolis rule and tabu search strategy will contribute to enhancing the algorithm convergence. Finally, we have conducted extensive simulations to verify the effectiveness and efficiency of the proposed AVNS-MT. Comparison experiments with several state-of-the-art methods validate the superiority of the proposed algorithm.

Enhancing radiographic image interpretation: WARES-PRS model for knee bone tumour detection

ABSTRACT The early diagnosis of tumour is significant in biomedical research field to lower the severity level and restrict the process extension from cancer. Moreover, the detection of early sign of cancer is undertaken with extensive research efforts that dedicated to the disclosure and recognition of tumours. However, the limited data size as well as diverse appearance of images lowered the detection performance and failed to detect complex stage of tumour. So to solve these issues, a Weighted Adaptive Random Ensemble Support Vector-based Partial Reinforcement Search (WARES-PRS) algorithm is proposed that detected bone lesions accurately and also predicted the severity level stage efficiently. Further, the detection is performed with varied stages to diminish the presence of noise and undertaken effective classification. The performance is validated with CNUH dataset that enhanced image pre-processing tasks. Despite the proposed method uncover the mutual relationships between each pixel’s local texture and the overall image’s global context. The detection and classification efficiency is validated with various measures and the experimental results revealed that the detection accuracy is enhanced for the proposed approach by 98.5%. The outcomes of our study have exhibited a substantial contribution to assisting physicians in the detection of knee bone tumours.

Correction: Enhanced coati optimization algorithm using elite opposition-based learning and adaptive search mechanism for feature selection

Correction: Enhanced coati optimization algorithm using elite opposition-based learning and adaptive search mechanism for feature selection

Gas identification using electronic nose via gramian-angular-field-based image conversion and convolutional neural networks architecture search

Recent years have witnessed the splendid performance of deep learning methods used in gas recognition for electronic noses (E-nose). In addition to effective feature extraction, the architecture of the deep neural network plays a vital role. Currently, most applied network structures are hand-crafted by human experts, which is time-consuming and problem-dependent, making it necessary to design the structures of neural networks according to specific demands. In this work, a genetic algorithm with particle swarm optimization (GA-PSO), which possesses promising optimization capabilities, is applied to search for effective deep convolutional neural networks (CNNs) for gas classification based on E-nose technology. A novel image transformation strategy using Gramian angular field and a hybrid cost-saving method is employed in the search process, enabling adaptive and efficient CNN search on gas datasets. With the proposed methods, we can achieve an average classification accuracy of over 90 % on two public gas datasets, while also significantly reducing the model size compared to state-of-the-art CNNs. By using these novel strategies, our approach surpasses random search and basic PSO algorithm in achieving the global optimal solution, higher and more stable accuracy, and faster convergence in pattern recognition using E-nose. Our work suggests that the proposed method can quickly identify excellent CNN structures for E-nose applications.

Strategic flood impact mitigation in developing countries’ urban road networks: Application to Hanoi

Due to climate change, the frequency and scale of flood events worldwide are increasing dramatically. Flood impacts are especially acute in developing countries, where they often revert years of progress in sustainable development and poverty reduction. This paper introduces an optimization-based decision support tool for selecting cost-efficient flood mitigation investments in developing countries’ urban areas. The core of the tool is a scenario-based, multi-period, bi-objective Mixed Integer Linear Programming model which minimizes infrastructure damage and traffic congestion in urban road networks. The tool was developed in collaboration with Vietnamese stakeholders (e.g., local communities and government authorities), and integrates data and inputs from other disciplines, including social science, transport economics, climatology and hydrology. A metaheuristic, combining a Greedy Randomized Adaptive Search Procedure with a Variable Neighborhood Descent algorithm, is developed to solve large scale problem instances. An extensive computational campaign on randomly generated instances demonstrates the efficiency of the metaheuristic in solving realistic problems with hundreds of interdependent flood mitigation interventions. Finally, the applicability of the interdisciplinary approach is demonstrated on a real case study to generate a 20-year plan of mitigation investments for the urban area of Hanoi. Policy implications and impacts of the study are also discussed.

Adaptive search space for stochastic opposition-based learning in differential evolution

Differential evolution (DE) is a practical evolutionary algorithm (EA) widely employed for addressing continuous optimization problems. Opposition-based learning (OBL) emerges as a potent method among the techniques enhancing EA performance. The BetaCOBL variant represents a pinnacle in this domain. However, BetaCOBL’s utilization of the promising regions of the search space remains partial, owing to its dependence on a non-adaptive framework. Consequently, its efficacy might dwindle as optimization progresses. We aimed to introduce an enhanced version of BetaCOBL, termed adaptive BetaCOBL (ABetaCOBL). ABetaCOBL commences by adapting the search space based on population distribution and subsequently identifying opposite solutions. We evaluated the efficacy of embedding ABetaCOBL into DE algorithms through experiments. Our experimental results substantiate that ABetaCOBL outperforms its precursor and resilient OBL variants (e.g., ABetaCOBL outperforms iBetaCOBL-eig in 19 out of 58 problems with NL-SHADE-LBC and in 22 out of 58 problems with NL-SHADE-RSP).

Exploring master scenarios for autonomous driving tests from police-reported historical crash data using an adaptive search sampling framework

Crash scenario-based testing is crucial for assessing autonomous driving safety. However, existing studies on scenario generation tend to prioritize concrete scenarios for direct testing, neglecting the construction of fundamentally functional scenarios with a broader range. Police-reported historical crash data is a valuable supplement, yet detecting all potential crash scenarios is laborious. In order to address this issue, this study proposes an adaptive search sampling framework based on deep generative model and surrogate model (SM) to extract master scenario samples from police-reported historical crash data. The framework starts with selecting representative samples from the full crash dataset as initial master scenario samples using various sampling techniques. Evaluation indexes are then constructed, and derived scenario samples are synthesized using the deep generative model. To enhance efficiency, an SM is established to replace the generative model’s training and data generation process. Based on the SM, an adaptive search sampling method is developed, which iteratively adjusts the sampling strategy using the Similarity Score to achieve comprehensive sampling. Experimental results demonstrate the notable advantage of the adaptive search sampling method over other sampling methods. Furthermore, statistical analysis and visualization assessments confirm the effectiveness and accuracy of the proposed method.

Adaptive large neighborhood search algorithm with reinforcement search strategy for solving extended cooperative multi task assignment problem of UAVs

In response to the increasing complexity of military operations, the use of multiple heterogeneous unmanned aerial vehicles (UAVs) is essential for efficiently executing complex missions. This paper introduces an extended cooperative multi-task assignment problem (ECMTAP), which involves deploying heterogeneous UAVs from different base stations to accomplish specific missions, with a focus on minimizing overall mission completion time. ECMTAP categorizes targets into various types, each associated with unique task sets including {reconnaissance}, {attack, evaluation}, and {reconnaissance, attack, evaluation}. ECMTAP requires that attack tasks follow reconnaissance tasks, and evaluation tasks follow attack tasks, adding complexity due to specific timing constraints on each task. To tackle this problem, we propose a novel algorithm, the reinforcement search strategy-based adaptive large neighborhood search (RSALNS). To enhance the search capability, RASLNS utilizes two key destroy-repair operations: the intra-target tasks adjustment strategy and the evaluation tasks adjustment strategy. The former operation dismantles and reconstructs task sequences within a target, potentially resulting in suboptimal assignment of evaluation tasks, while the latter operation reassigns these tasks based on the first operation's output. Extensive experiments validate the effectiveness of the RSALNS algorithm in solving the ECMTAP, demonstrating its capability to generate high-quality solutions efficiently.

The low-carbon vehicle routing problem with dynamic speed on steep roads

The low-carbon vehicle routing problem with dynamic speeds on steep roads (LCVRPDS-SR) considers the combined effects of dynamic speeds, steep roads, and loads on carbon emissions. Earlier low-carbon vehicle routing problems typically assumed that vehicles travel at a constant speed on flat roads. However, such models do not apply in urban or rural areas with steep roads. Although the subsequent studies further explored the effect of steep roads, their performance are still suboptimal since they fail to take into account the varying speeds on the terrain. This paper proposes an extended LCVRPDS-SR model that tackles dynamic speed decisions on steep roads for the low-carbon vehicle routing problem. The objective function is non-linear and considers only environmental factors. Then an improved adaptive large neighborhood search algorithm is presented, including a new speed optimization algorithm and several improved removal and insertion operators. Extensive experiments are conducted on the generated instances to verify the effectiveness of the model and algorithm and derive managerial insights. The significant reduction in greenhouse gas emissions is achieved when considering dynamic speeds.