NSTL国家科技图书文献中心

1. Applying a modified adaptive large neighbourhood search for truck scheduling and pile assignment in a two-stage sorting system NSTL国家科技图书文献中心

James C. Chen | Tzu-Li Chen ... - 《European Journal of Industrial Engineering》 - 2025,19(2) - 128～161 - 共34页

摘要： two-stage semi-automatic sorting system, considering | objective is to integrate two* decision points - the* | large neighbourhood search* (MCMALNS) algorithm to* | In this study, we tackle the complexities of a | the diverse distribution requirements of parcels and

关键词： truck scheduling | two-stage sorting system | modified adaptive large neighbourhood search

2. Two-stage learning scatter search algorithm for the distributed hybrid flow shop scheduling problem with machine breakdown NSTL国家科技图书文献中心

Yang Zuo | Fuqing Zhao ... - 《Expert Systems with Application》 - 2025,259(Jan.) - 125344.1～125344.10 - 共10页

摘要：, a two-stage* learning scatter search (TLSS* | direction of global search. A two-stage* approach is* | two subproblems: the maintenance problem with | periods of learning. Finally, a hybrid search* strategy* | The distributed hybrid flow shop scheduling

关键词： Machine breakdown | Distributed hybrid flow scheduling | Reinforcement learning | Insufficient knowledge

3. Meal pickup and delivery problem with appointment time and uncertainty in order cancellation NSTL国家科技图书文献中心

Xue G. | Wang Z.... - 《Transportation research,Part E.Logistics and transportation review》 - 2025,193(Jan.) - 1.1～1.27 - 共27页

摘要： cancellations. The problem is formulated as a two-stage | parallel adaptive large neighborhood search* (pALNS) with* | © 2024 Elsevier LtdOnline-ordered meal | logistics services (OMLSs) that accept online bookings and | make vehicle plans to deliver meals from restaurants

关键词： Order cancellation | Parallel adaptive large neighborhood search | Sample average approximation | Two-stage stochastic programming

4. Min-Max Fairness-Based Beamforming Design for Coupled Phase Shift STAR-RIS-Assisted MIMO System NSTL国家科技图书文献中心

Shihan Huang | Weijiang Wang ... - 《IEEE internet of things journal》 - 2025,12(3) - 3145～3162 - 共18页

摘要： element-wise two-stage* search algorithm is proposed to* | Simultaneously transmitting and reflecting | reconfigurable intelligent surface (STAR-RIS) represents a | novel technology that extends communication coverage | to the entire space, compared to the conventional

关键词： Array signal processing | Reconfigurable intelligent surfaces | Wireless communication | MIMO communication | Stars | Optimization | Internet of Things | Signal to noise ratio | Resource management | NOMA

5. Two-stage multi-objective optimization based on knowledge-driven approach: A case study on production and transportation integration NSTL国家科技图书文献中心

Ziqi Ding | Zuocheng Li ... - 《Future generations computer systems》 - 2025,163(Feb.) - 107494.1～107494.22 - 共22页

摘要： time a two-stage* MOEA based on a knowledge-driven* | optimization problems. Existing search* models based on* | search process. In this paper, we propose for the first | approach (TMOK). The first stage* aims to find a rough* | algorithm, whereas the second stage* incorporates a dynamic*

关键词： Knowledge-driven | Two-stage multi-objective optimization | Markov chain | Distributed production and transportation | Integrated optimization

6. Specialized model initialization and architecture optimization for few-shot code search NSTL国家科技图书文献中心

Zhang F. | Wu Q.... - 《Information and software technology》 - 2025,177(Jan.) - 1.1～1.14 - 共14页

摘要： limited training data by proposing a novel two-stage | parameters. In the second stage, we first design a search | © 2024 Elsevier B.V.Context: Code search* aims* | data. We aim to address the challenges of code search | , few-shot code search* framework named SMIAO. Method*

关键词： AI for software engineering | Code search | Code understanding | Information retrieval | Neural architecture search

7. Artificial bee colony algorithm based on multiple indicators for many-objective optimization with irregular Pareto fronts NSTL国家科技图书文献中心

Hui Wang | Dong Xiao ... - 《Expert Systems with Application》 - 2025,262(Mar.) - 125613.1～125613.17 - 共17页

摘要： two-stage environmental selection method is designed | based on the two* indicators. In the first stage, the* | (PFs). The possible reasons include two* aspects: (1* | improve the convergence. In the second stage, the Div | and exploitation during the search, multiple search

关键词： Artificial bee colony (ABC) | Many-objective optimization | Irregular pareto fronts | Multiple indicators | Multiple search strategies

8. Efficient sparse retrieval through embedding-based inverted index construction NSTL国家科技图书文献中心

Viacheslav Yu. Dobry... | Roman K. Abramovich ... - 《Научно-технический Вестник Информационных Технологий, Механики и Оптики》 - 2025,25(1) - 061～067 - 共7页

摘要：Modern search engines use a two-stage | architecture for efficient and high-quality search* over large* | volumes of data. In the first stage, simple and fast | algorithms like BM25 are applied, while in the second stage | first stage. To address this issue, we propose an

关键词： Inverted index | Vocabulary mismatch problem | Neural networks | Vector representations | Clusterization

9. A parallel improved variable neighborhood search algorithm for multi-depot multi-compartment simultaneous pickup and delivery problem with time windows and split demands NSTL国家科技图书文献中心

Jian Cao | Liyong Lin - 《Fourth International Conference on Intelligent Traffic Systems and Smart City (ITSSC 2024)》 - International Conference on Intelligent Traffic Systems and Smart City - 2025, - 134220X.1～134220X.14 - 共14页

摘要：, in this study, we propose a novel two-stage | enhanced variable neighborhood search* algorithm, which* | . In the initial stage, heuristic techniques are | . Subsequently, in the second stage, we introduce refined | neighborhood search* technology, which enables an in-depth*

关键词： Enhanced variable neighborhood search | Parallel computing | Vehicle routing optimization

10. A Reinforcement Learning Approach for Graph Rule Learning NSTL国家科技图书文献中心

Zhenzhen Mai | Wenjun Wang ... - 《Big Data Mining and Analytics》 - 2025,8(1) - 31～44 - 共14页

摘要：. Specifically, GraphRulRL follows a two-stage* framework. In* | search spaces due to the enumeration of all candidate | (RL) in reducing search* space, we implement a policy* | the first stage, we train a policy network for graph | training. In the second stage, we integrate the well

摘要： two-stage semi-automatic sorting system, considering | objective is to integrate two* decision points - the* | large neighbourhood search* (MCMALNS) algorithm to* | In this study, we tackle the complexities of a | the diverse distribution requirements of parcels and

关键词： truck scheduling | two-stage sorting system | modified adaptive large neighbourhood search

摘要：, a two-stage* learning scatter search (TLSS* | direction of global search. A two-stage* approach is* | two subproblems: the maintenance problem with | periods of learning. Finally, a hybrid search* strategy* | The distributed hybrid flow shop scheduling

关键词： Machine breakdown | Distributed hybrid flow scheduling | Reinforcement learning | Insufficient knowledge

摘要： cancellations. The problem is formulated as a two-stage | parallel adaptive large neighborhood search* (pALNS) with* | © 2024 Elsevier LtdOnline-ordered meal | logistics services (OMLSs) that accept online bookings and | make vehicle plans to deliver meals from restaurants

关键词： Order cancellation | Parallel adaptive large neighborhood search | Sample average approximation | Two-stage stochastic programming

摘要： element-wise two-stage* search algorithm is proposed to* | Simultaneously transmitting and reflecting | reconfigurable intelligent surface (STAR-RIS) represents a | novel technology that extends communication coverage | to the entire space, compared to the conventional

关键词： Array signal processing | Reconfigurable intelligent surfaces | Wireless communication | MIMO communication | Stars | Optimization | Internet of Things | Signal to noise ratio | Resource management | NOMA

摘要： time a two-stage* MOEA based on a knowledge-driven* | optimization problems. Existing search* models based on* | search process. In this paper, we propose for the first | approach (TMOK). The first stage* aims to find a rough* | algorithm, whereas the second stage* incorporates a dynamic*

关键词： Knowledge-driven | Two-stage multi-objective optimization | Markov chain | Distributed production and transportation | Integrated optimization

摘要： limited training data by proposing a novel two-stage | parameters. In the second stage, we first design a search | © 2024 Elsevier B.V.Context: Code search* aims* | data. We aim to address the challenges of code search | , few-shot code search* framework named SMIAO. Method*

关键词： AI for software engineering | Code search | Code understanding | Information retrieval | Neural architecture search

摘要： two-stage environmental selection method is designed | based on the two* indicators. In the first stage, the* | (PFs). The possible reasons include two* aspects: (1* | improve the convergence. In the second stage, the Div | and exploitation during the search, multiple search

关键词： Artificial bee colony (ABC) | Many-objective optimization | Irregular pareto fronts | Multiple indicators | Multiple search strategies

摘要：Modern search engines use a two-stage | architecture for efficient and high-quality search* over large* | volumes of data. In the first stage, simple and fast | algorithms like BM25 are applied, while in the second stage | first stage. To address this issue, we propose an

关键词： Inverted index | Vocabulary mismatch problem | Neural networks | Vector representations | Clusterization

摘要：, in this study, we propose a novel two-stage | enhanced variable neighborhood search* algorithm, which* | . In the initial stage, heuristic techniques are | . Subsequently, in the second stage, we introduce refined | neighborhood search* technology, which enables an in-depth*

关键词： Enhanced variable neighborhood search | Parallel computing | Vehicle routing optimization

摘要：. Specifically, GraphRulRL follows a two-stage* framework. In* | search spaces due to the enumeration of all candidate | (RL) in reducing search* space, we implement a policy* | the first stage, we train a policy network for graph | training. In the second stage, we integrate the well

关键词： Measurement | Training | Codes | Decision making | Reinforcement learning | Big Data | Iterative algorithms | Logic | Data mining

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： two-stage semi-automatic sorting system, considering | objective is to integrate two decision points - the | large neighbourhood search (MCMALNS) algorithm to | In this study, we tackle the complexities of a | the diverse distribution requirements of parcels and

关键词： truck scheduling | two-stage sorting system | modified adaptive large neighbourhood search

摘要：, a two-stage learning scatter search (TLSS | direction of global search. A two-stage approach is | two subproblems: the maintenance problem with | periods of learning. Finally, a hybrid search strategy | The distributed hybrid flow shop scheduling

关键词： Machine breakdown | Distributed hybrid flow scheduling | Reinforcement learning | Insufficient knowledge

摘要： cancellations. The problem is formulated as a two-stage | parallel adaptive large neighborhood search (pALNS) with | © 2024 Elsevier LtdOnline-ordered meal | logistics services (OMLSs) that accept online bookings and | make vehicle plans to deliver meals from restaurants

关键词： Order cancellation | Parallel adaptive large neighborhood search | Sample average approximation | Two-stage stochastic programming

摘要： element-wise two-stage search algorithm is proposed to | Simultaneously transmitting and reflecting | reconfigurable intelligent surface (STAR-RIS) represents a | novel technology that extends communication coverage | to the entire space, compared to the conventional

关键词： Array signal processing | Reconfigurable intelligent surfaces | Wireless communication | MIMO communication | Stars | Optimization | Internet of Things | Signal to noise ratio | Resource management | NOMA

摘要： time a two-stage MOEA based on a knowledge-driven | optimization problems. Existing search models based on | search process. In this paper, we propose for the first | approach (TMOK). The first stage aims to find a rough | algorithm, whereas the second stage incorporates a dynamic

关键词： Knowledge-driven | Two-stage multi-objective optimization | Markov chain | Distributed production and transportation | Integrated optimization

摘要： limited training data by proposing a novel two-stage | parameters. In the second stage, we first design a search | © 2024 Elsevier B.V.Context: Code search aims | data. We aim to address the challenges of code search | , few-shot code search framework named SMIAO. Method

关键词： AI for software engineering | Code search | Code understanding | Information retrieval | Neural architecture search

摘要： two-stage environmental selection method is designed | based on the two indicators. In the first stage, the | (PFs). The possible reasons include two aspects: (1 | improve the convergence. In the second stage, the Div | and exploitation during the search, multiple search

关键词： Artificial bee colony (ABC) | Many-objective optimization | Irregular pareto fronts | Multiple indicators | Multiple search strategies

摘要：Modern search engines use a two-stage | architecture for efficient and high-quality search over large | volumes of data. In the first stage, simple and fast | algorithms like BM25 are applied, while in the second stage | first stage. To address this issue, we propose an

关键词： Inverted index | Vocabulary mismatch problem | Neural networks | Vector representations | Clusterization

摘要：, in this study, we propose a novel two-stage | enhanced variable neighborhood search algorithm, which | . In the initial stage, heuristic techniques are | . Subsequently, in the second stage, we introduce refined | neighborhood search technology, which enables an in-depth

关键词： Enhanced variable neighborhood search | Parallel computing | Vehicle routing optimization

摘要：. Specifically, GraphRulRL follows a two-stage framework. In | search spaces due to the enumeration of all candidate | (RL) in reducing search space, we implement a policy | the first stage, we train a policy network for graph | training. In the second stage, we integrate the well

关键词： Measurement | Training | Codes | Decision making | Reinforcement learning | Big Data | Iterative algorithms | Logic | Data mining

4008-161-200 800-990-8900

国家科技图书文献中心

摘要： two-stage semi-automatic sorting system, considering | objective is to integrate two* decision points - the* | large neighbourhood search* (MCMALNS) algorithm to* | In this study, we tackle the complexities of a | the diverse distribution requirements of parcels and

摘要：, a two-stage* learning scatter search (TLSS* | direction of global search. A two-stage* approach is* | two subproblems: the maintenance problem with | periods of learning. Finally, a hybrid search* strategy* | The distributed hybrid flow shop scheduling

摘要： cancellations. The problem is formulated as a two-stage | parallel adaptive large neighborhood search* (pALNS) with* | © 2024 Elsevier LtdOnline-ordered meal | logistics services (OMLSs) that accept online bookings and | make vehicle plans to deliver meals from restaurants

摘要： element-wise two-stage* search algorithm is proposed to* | Simultaneously transmitting and reflecting | reconfigurable intelligent surface (STAR-RIS) represents a | novel technology that extends communication coverage | to the entire space, compared to the conventional

摘要： time a two-stage* MOEA based on a knowledge-driven* | optimization problems. Existing search* models based on* | search process. In this paper, we propose for the first | approach (TMOK). The first stage* aims to find a rough* | algorithm, whereas the second stage* incorporates a dynamic*

摘要： limited training data by proposing a novel two-stage | parameters. In the second stage, we first design a search | © 2024 Elsevier B.V.Context: Code search* aims* | data. We aim to address the challenges of code search | , few-shot code search* framework named SMIAO. Method*

摘要： two-stage environmental selection method is designed | based on the two* indicators. In the first stage, the* | (PFs). The possible reasons include two* aspects: (1* | improve the convergence. In the second stage, the Div | and exploitation during the search, multiple search

摘要：Modern search engines use a two-stage | architecture for efficient and high-quality search* over large* | volumes of data. In the first stage, simple and fast | algorithms like BM25 are applied, while in the second stage | first stage. To address this issue, we propose an

摘要：, in this study, we propose a novel two-stage | enhanced variable neighborhood search* algorithm, which* | . In the initial stage, heuristic techniques are | . Subsequently, in the second stage, we introduce refined | neighborhood search* technology, which enables an in-depth*

摘要：. Specifically, GraphRulRL follows a two-stage* framework. In* | search spaces due to the enumeration of all candidate | (RL) in reducing search* space, we implement a policy* | the first stage, we train a policy network for graph | training. In the second stage, we integrate the well