Pub Date : 2024-03-02DOI: 10.26599/TST.2023.9010118
Jie Yuan;Fangru Lin;Hae Yoon Kim
As living standards improve, the demand for artworks has been escalating, transcending beyond the realm of mere basic human necessities. However, amidst an extensive array of artwork choices, users often struggle to swiftly and accurately identify their preferred piece. In such scenarios, a recommendation system can be invaluable, assisting users in promptly pinpointing the desired artworks for better service design. Despite the escalating demand for artwork recommendation systems, current research fails to adequately meet these needs. Predominantly, existing artwork recommendation methodologies tend to disregard users' implicit interests, thereby overestimating their capability to articulate their preferences in full and often neglecting the nuances of their diverse interests. In response to these challenges, we have developed a weighted artwork correlation graph and put forth an embedding-based keyword-driven artwork search and recommendation methodology. Our approach transforms the keywords that delineate user interests into word embedding vectors. This allows for an effective distinction between the user's core and peripheral interests. Subsequently, we employ a dynamic programming algorithm to extract artworks from the correlation graph, thereby obtaining artworks that align with the user's explicit keywords and implicit interests. We have conducted an array of experiments using real-world datasets to validate our approach. The results attest to the superiority of our method in terms of its efficacy in searching and recommending artworks.
{"title":"Exploring Artistic Embeddings in Service Design: A Keyword-Driven Approach for Artwork Search and Recommendations","authors":"Jie Yuan;Fangru Lin;Hae Yoon Kim","doi":"10.26599/TST.2023.9010118","DOIUrl":"https://doi.org/10.26599/TST.2023.9010118","url":null,"abstract":"As living standards improve, the demand for artworks has been escalating, transcending beyond the realm of mere basic human necessities. However, amidst an extensive array of artwork choices, users often struggle to swiftly and accurately identify their preferred piece. In such scenarios, a recommendation system can be invaluable, assisting users in promptly pinpointing the desired artworks for better service design. Despite the escalating demand for artwork recommendation systems, current research fails to adequately meet these needs. Predominantly, existing artwork recommendation methodologies tend to disregard users' implicit interests, thereby overestimating their capability to articulate their preferences in full and often neglecting the nuances of their diverse interests. In response to these challenges, we have developed a weighted artwork correlation graph and put forth an embedding-based keyword-driven artwork search and recommendation methodology. Our approach transforms the keywords that delineate user interests into word embedding vectors. This allows for an effective distinction between the user's core and peripheral interests. Subsequently, we employ a dynamic programming algorithm to extract artworks from the correlation graph, thereby obtaining artworks that align with the user's explicit keywords and implicit interests. We have conducted an array of experiments using real-world datasets to validate our approach. The results attest to the superiority of our method in terms of its efficacy in searching and recommending artworks.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":null,"pages":null},"PeriodicalIF":6.6,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10517932","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140820354","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-02DOI: 10.26599/TST.2023.9010138
Yan Zhang;Lin Sun;Wen Sun;Fan Ma;Runlong Xiao;You Wu;He Huang
Green shipping and electrification have been the main topics in the shipping industry. In this process, the pure battery-powered ship is developed, which is zero-emission and well-suited for inland shipping. Currently, battery swapping stations and ships are being explored since battery charging ships may not be feasible for inland long-distance trips. However, improper infrastructure planning for battery swapping stations and ships will increase costs and decrease operation efficiency. Therefore, a bilevel optimal infrastructure planning method is proposed in this paper for battery swapping stations and ships. First, the energy consumption model for the battery swapping ship is established considering the influence of the sailing environment. Second, a bilevel optimization model is proposed to minimize the total cost. Specifically, the battery swapping station (BSS) location problem is investigated at the upper level. The optimization of battery size in each battery swapping station and ship and battery swapping scheme are studied at the lower level based on speed and energy optimization. Finally, the bilevel self-adaptive differential evolution algorithm (BlSaDE) is proposed to solve this problem. The simulation results show that total cost could be reduced by 5.9% compared to the original results, and the effectiveness of the proposed method is confirmed.
{"title":"Bilevel Optimal Infrastructure Planning Method for the Inland Battery Swapping Stations and Battery-Powered Ships","authors":"Yan Zhang;Lin Sun;Wen Sun;Fan Ma;Runlong Xiao;You Wu;He Huang","doi":"10.26599/TST.2023.9010138","DOIUrl":"https://doi.org/10.26599/TST.2023.9010138","url":null,"abstract":"Green shipping and electrification have been the main topics in the shipping industry. In this process, the pure battery-powered ship is developed, which is zero-emission and well-suited for inland shipping. Currently, battery swapping stations and ships are being explored since battery charging ships may not be feasible for inland long-distance trips. However, improper infrastructure planning for battery swapping stations and ships will increase costs and decrease operation efficiency. Therefore, a bilevel optimal infrastructure planning method is proposed in this paper for battery swapping stations and ships. First, the energy consumption model for the battery swapping ship is established considering the influence of the sailing environment. Second, a bilevel optimization model is proposed to minimize the total cost. Specifically, the battery swapping station (BSS) location problem is investigated at the upper level. The optimization of battery size in each battery swapping station and ship and battery swapping scheme are studied at the lower level based on speed and energy optimization. Finally, the bilevel self-adaptive differential evolution algorithm (BlSaDE) is proposed to solve this problem. The simulation results show that total cost could be reduced by 5.9% compared to the original results, and the effectiveness of the proposed method is confirmed.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":null,"pages":null},"PeriodicalIF":6.6,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10517977","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140820226","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-02DOI: 10.26599/TST.2024.9010010
Abdul Basit Dogar;Sami Ullah;Yiran Zhang;Hisham Alasmary;Muhammad Waqas;Sheng Chen
Network updates have become increasingly prevalent since the broad adoption of software-defined networks (SDNs) in data centers. Modern TCP designs, including cutting-edge TCP variants DCTCP, CUBIC, and BBR, however, are not resilient to network updates that provoke flow rerouting. In this paper, we first demonstrate that popular TCP implementations perform inadequately in the presence of frequent and inconsistent network updates, because inconsistent and frequent network updates result in out-of-order packets and packet drops induced via transitory congestion and lead to serious performance deterioration. We look into the causes and propose a network update-friendly TCP (NUFTCP), which is an extension of the DCTCP variant, as a solution. Simulations are used to assess the proposed NUFTCP. Our findings reveal that NUFTCP can more effectively manage the problems of out-of-order packets and packet drops triggered in network updates, and it outperforms DCTCP considerably.
{"title":"Resilient TCP Variant Enabling Smooth Network Updates for Software-Defined Data Center Networks","authors":"Abdul Basit Dogar;Sami Ullah;Yiran Zhang;Hisham Alasmary;Muhammad Waqas;Sheng Chen","doi":"10.26599/TST.2024.9010010","DOIUrl":"https://doi.org/10.26599/TST.2024.9010010","url":null,"abstract":"Network updates have become increasingly prevalent since the broad adoption of software-defined networks (SDNs) in data centers. Modern TCP designs, including cutting-edge TCP variants DCTCP, CUBIC, and BBR, however, are not resilient to network updates that provoke flow rerouting. In this paper, we first demonstrate that popular TCP implementations perform inadequately in the presence of frequent and inconsistent network updates, because inconsistent and frequent network updates result in out-of-order packets and packet drops induced via transitory congestion and lead to serious performance deterioration. We look into the causes and propose a network update-friendly TCP (NUFTCP), which is an extension of the DCTCP variant, as a solution. Simulations are used to assess the proposed NUFTCP. Our findings reveal that NUFTCP can more effectively manage the problems of out-of-order packets and packet drops triggered in network updates, and it outperforms DCTCP considerably.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":null,"pages":null},"PeriodicalIF":6.6,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10517974","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140820178","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-03-02DOI: 10.26599/TST.2023.9010140
Lin Gui;Xinyu Li;Qingfu Zhang;Liang Gao
Meta-heuristic algorithms search the problem solution space to obtain a satisfactory solution within a reasonable timeframe. By combining domain knowledge of the specific optimization problem, the search efficiency and quality of meta-heuristic algorithms can be significantly improved, making it crucial to identify and summarize domain knowledge within the problem. In this paper, we summarize and analyze domain knowledge that can be applied to meta-heuristic algorithms in the job-shop scheduling problem (JSP). Firstly, this paper delves into the importance of domain knowledge in optimization algorithm design. After that, the development of different methods for the JSP are reviewed, and the domain knowledge in it for meta-heuristic algorithms is summarized and classified. Applications of this domain knowledge are analyzed, showing it is indispensable in ensuring the optimization performance of meta-heuristic algorithms. Finally, this paper analyzes the relationship among domain knowledge, optimization problems, and optimization algorithms, and points out the shortcomings of the existing research and puts forward research prospects. This paper comprehensively summarizes the domain knowledge in the JSP, and discusses the relationship between the optimization problems, optimization algorithms and domain knowledge, which provides a research direction for the metaheuristic algorithm design for solving the JSP in the future.
{"title":"Domain Knowledge Used in Meta-Heuristic Algorithms for the Job-Shop Scheduling Problem: Review and Analysis","authors":"Lin Gui;Xinyu Li;Qingfu Zhang;Liang Gao","doi":"10.26599/TST.2023.9010140","DOIUrl":"https://doi.org/10.26599/TST.2023.9010140","url":null,"abstract":"Meta-heuristic algorithms search the problem solution space to obtain a satisfactory solution within a reasonable timeframe. By combining domain knowledge of the specific optimization problem, the search efficiency and quality of meta-heuristic algorithms can be significantly improved, making it crucial to identify and summarize domain knowledge within the problem. In this paper, we summarize and analyze domain knowledge that can be applied to meta-heuristic algorithms in the job-shop scheduling problem (JSP). Firstly, this paper delves into the importance of domain knowledge in optimization algorithm design. After that, the development of different methods for the JSP are reviewed, and the domain knowledge in it for meta-heuristic algorithms is summarized and classified. Applications of this domain knowledge are analyzed, showing it is indispensable in ensuring the optimization performance of meta-heuristic algorithms. Finally, this paper analyzes the relationship among domain knowledge, optimization problems, and optimization algorithms, and points out the shortcomings of the existing research and puts forward research prospects. This paper comprehensively summarizes the domain knowledge in the JSP, and discusses the relationship between the optimization problems, optimization algorithms and domain knowledge, which provides a research direction for the metaheuristic algorithm design for solving the JSP in the future.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":null,"pages":null},"PeriodicalIF":6.6,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10517918","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140820351","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
With continuous expansion of satellite applications, the requirements for satellite communication services, such as communication delay, transmission bandwidth, transmission power consumption, and communication coverage, are becoming higher. This paper first presents an overview of the current development status of Low Earth Orbit (LEO) satellite constellations, and then conducts a demand analysis for multi-satellite data transmission based on LEO satellite constellations. The problem is described, and the challenges and difficulties of the problem are analyzed accordingly. On this basis, a multi-satellite datatransmission mathematical model is then constructed. Combining classical heuristic allocating strategies on the features of the proposed model, with the reinforcement learning algorithm Deep Q-Network (DQN), a two-stage optimization framework based on heuristic and DON is proposed. Finally, by taking into account the spatial and temporal distribution characteristics of satellite and facility resources, a multi-satellite scheduling instance dataset is generated. Experimental results validate the rationality and correctness of the DQN algorithm in solving the collaborative scheduling problem of multi-satellite data transmission.
随着卫星应用的不断扩展,对卫星通信服务的要求也越来越高,如通信延迟、传输带宽、传输功耗和通信覆盖范围等。本文首先概述了低地球轨道(LEO)卫星星座的发展现状,然后对基于 LEO 卫星星座的多卫星数据传输进行了需求分析。对问题进行了描述,并相应分析了问题的挑战和难点。在此基础上,构建了多卫星数据传输数学模型。根据所提模型的特点,结合经典的启发式分配策略和强化学习算法深度 Q 网络(DQN),提出了基于启发式和 DON 的两阶段优化框架。最后,结合卫星和设施资源的时空分布特点,生成了多卫星调度实例数据集。实验结果验证了 DQN 算法在解决多卫星数据传输协同调度问题中的合理性和正确性。
{"title":"Data-Driven Collaborative Scheduling Method for Multi-Satellite Data-Transmission","authors":"Xiaoyu Chen;Weichao Gu;Guangming Dai;Lining Xing;Tian Tian;Weilai Luo;Shi Cheng;Mengyun Zhou","doi":"10.26599/TST.2023.9010131","DOIUrl":"https://doi.org/10.26599/TST.2023.9010131","url":null,"abstract":"With continuous expansion of satellite applications, the requirements for satellite communication services, such as communication delay, transmission bandwidth, transmission power consumption, and communication coverage, are becoming higher. This paper first presents an overview of the current development status of Low Earth Orbit (LEO) satellite constellations, and then conducts a demand analysis for multi-satellite data transmission based on LEO satellite constellations. The problem is described, and the challenges and difficulties of the problem are analyzed accordingly. On this basis, a multi-satellite datatransmission mathematical model is then constructed. Combining classical heuristic allocating strategies on the features of the proposed model, with the reinforcement learning algorithm Deep Q-Network (DQN), a two-stage optimization framework based on heuristic and DON is proposed. Finally, by taking into account the spatial and temporal distribution characteristics of satellite and facility resources, a multi-satellite scheduling instance dataset is generated. Experimental results validate the rationality and correctness of the DQN algorithm in solving the collaborative scheduling problem of multi-satellite data transmission.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":null,"pages":null},"PeriodicalIF":6.6,"publicationDate":"2024-03-02","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10517922","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"140820429","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-12DOI: 10.26599/TST.2023.9010109
Shunjun Luo;Xiaoge Zhu;Jiasen Ran
The development of society is inseparable from the use of traditional burning energy. However, people's excessive exploitation of fossil energy has led to the gradual shortage of fossil energy. It is essential to find New Energy (NE) and develop a new energy industry. The natural ecosystem has the characteristics of stable development. With the development of Artificial Intelligence (AI), the structure of the natural ecosystem has been applied to the NE industry, forming an NE industry ecological integration system. This paper uses Particle Swarm Optimization (PSO) algorithm to optimize the structure and resources of the NE industry, so that the NE industry has the capability of sustainable development. The traditional NE industry and the NE innovation industry ecological integration system based on PSO algorithm are compared. The experimental results show that in the NE vehicle industry, the average economic benefits of the traditional NE industry and the NE innovation industry ecosystem based on PSO algorithm are 63.6% and 77.2%, respectively. In the NE power generation industry, the average economic benefits of the traditional NE industry and the NE innovation industry ecosystem based on PSO algorithm are 67.6% and 80.4%, respectively. Therefore, in the context of AI, the application of PSO algorithm to the ecological integration system of NE industry could improve the economic benefits of NE industry.
{"title":"Key Technology Innovation Mode of New Energy Industry Ecological Integration System Based on Particle Swarm Optimization Algorithm","authors":"Shunjun Luo;Xiaoge Zhu;Jiasen Ran","doi":"10.26599/TST.2023.9010109","DOIUrl":"https://doi.org/10.26599/TST.2023.9010109","url":null,"abstract":"The development of society is inseparable from the use of traditional burning energy. However, people's excessive exploitation of fossil energy has led to the gradual shortage of fossil energy. It is essential to find New Energy (NE) and develop a new energy industry. The natural ecosystem has the characteristics of stable development. With the development of Artificial Intelligence (AI), the structure of the natural ecosystem has been applied to the NE industry, forming an NE industry ecological integration system. This paper uses Particle Swarm Optimization (PSO) algorithm to optimize the structure and resources of the NE industry, so that the NE industry has the capability of sustainable development. The traditional NE industry and the NE innovation industry ecological integration system based on PSO algorithm are compared. The experimental results show that in the NE vehicle industry, the average economic benefits of the traditional NE industry and the NE innovation industry ecosystem based on PSO algorithm are 63.6% and 77.2%, respectively. In the NE power generation industry, the average economic benefits of the traditional NE industry and the NE innovation industry ecosystem based on PSO algorithm are 67.6% and 80.4%, respectively. Therefore, in the context of AI, the application of PSO algorithm to the ecological integration system of NE industry could improve the economic benefits of NE industry.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":null,"pages":null},"PeriodicalIF":6.6,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10433471","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141435225","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-12DOI: 10.26599/TST.2023.9010039
Junkai Feng;Ruiqi Yang;Yapu Zhang;Zhenning Zhang
In this paper, we study a class of online continuous optimization problems. At each round, the utility function is the sum of a weakly diminishing-returns (DR) submodular function and a concave function, certain cost associated with the action will occur, and the problem has total limited budget. Combining the two methods, the penalty function and Frank-Wolfe strategies, we present an online method to solve the considered problem. Choosing appropriate stepsize and penalty parameters, the performance of the online algorithm is guaranteed, that is, it achieves sub-linear regret bound and certain mild constraint violation bound in expectation.
{"title":"Online Weakly DR-Submodular Optimization Under Stochastic Cumulative Constraints","authors":"Junkai Feng;Ruiqi Yang;Yapu Zhang;Zhenning Zhang","doi":"10.26599/TST.2023.9010039","DOIUrl":"https://doi.org/10.26599/TST.2023.9010039","url":null,"abstract":"In this paper, we study a class of online continuous optimization problems. At each round, the utility function is the sum of a weakly diminishing-returns (DR) submodular function and a concave function, certain cost associated with the action will occur, and the problem has total limited budget. Combining the two methods, the penalty function and Frank-Wolfe strategies, we present an online method to solve the considered problem. Choosing appropriate stepsize and penalty parameters, the performance of the online algorithm is guaranteed, that is, it achieves sub-linear regret bound and certain mild constraint violation bound in expectation.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":null,"pages":null},"PeriodicalIF":6.6,"publicationDate":"2024-02-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10433470","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141435367","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Lithological facies classification is a pivotal task in petroleum geology, underpinning reservoir characterization and influencing decision-making in exploration and production operations. Traditional classification methods, such as support vector machines and Gaussian process classifiers, often struggle with the complexity and nonlinearity of geological data, leading to suboptimal performance. Moreover, numerous prevalent approaches fail to adequately consider the inherent dependencies in the sequence of measurements from adjacent depths in a well. A novel approach leveraging an attention-based gated recurrent unit (AGRU) model is introduced in this paper to address these challenges. The AGRU model excels by exploiting the sequential nature of well-log data and capturing long-range dependencies through an attention mechanism. This model enables a flexible and context-dependent weighting of different parts of the sequence, enhancing the discernment of key features for classification. The proposed method was validated on two publicly available datasets. Results demonstrate a considerably improvement over traditional methods. Specifically, the AGRU model achieved superior performance metrics considering precision, recall, and F1-score.
岩性面分类是石油地质学的一项关键任务,它是储层特征描述的基础,影响着勘探和生产作业的决策。传统的分类方法,如支持向量机和高斯过程分类器,往往难以应对地质数据的复杂性和非线性,导致性能不理想。此外,许多流行的方法未能充分考虑油井相邻深度测量序列的内在依赖性。本文介绍了一种利用基于注意力的门控递归单元(AGRU)模型的新方法,以应对这些挑战。AGRU 模型充分利用了井记录数据的顺序性,并通过注意力机制捕捉长程依赖关系。该模型能够灵活地根据上下文对序列的不同部分进行加权,从而提高对分类关键特征的识别能力。我们在两个公开的数据集上对所提出的方法进行了验证。结果表明,与传统方法相比,该方法有了很大改进。具体来说,AGRU 模型在精确度、召回率和 F1 分数方面都取得了优异的性能指标。
{"title":"Lithological Facies Classification Using Attention-Based Gated Recurrent Unit","authors":"Yuwen Liu;Yulan Zhang;Xingyuan Mao;Xucheng Zhou;Jingwen Chang;Wenwei Wang;Pan Wang;Lianyong Qi","doi":"10.26599/TST.2023.9010077","DOIUrl":"https://doi.org/10.26599/TST.2023.9010077","url":null,"abstract":"Lithological facies classification is a pivotal task in petroleum geology, underpinning reservoir characterization and influencing decision-making in exploration and production operations. Traditional classification methods, such as support vector machines and Gaussian process classifiers, often struggle with the complexity and nonlinearity of geological data, leading to suboptimal performance. Moreover, numerous prevalent approaches fail to adequately consider the inherent dependencies in the sequence of measurements from adjacent depths in a well. A novel approach leveraging an attention-based gated recurrent unit (AGRU) model is introduced in this paper to address these challenges. The AGRU model excels by exploiting the sequential nature of well-log data and capturing long-range dependencies through an attention mechanism. This model enables a flexible and context-dependent weighting of different parts of the sequence, enhancing the discernment of key features for classification. The proposed method was validated on two publicly available datasets. Results demonstrate a considerably improvement over traditional methods. Specifically, the AGRU model achieved superior performance metrics considering precision, recall, and F1-score.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":null,"pages":null},"PeriodicalIF":6.6,"publicationDate":"2024-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10431751","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139715164","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Popularity plays a significant role in the recommendation system. Traditional popularity is only defined as a static ratio or metric (e.g., a ratio of users who have rated the item and the box office of a movie) regardless of the previous trends of this ratio or metric and the attribute diversity of items. To solve this problem and reach accurate popularity, we creatively propose to extract the popularity of an item according to the Proportional Integral Differential (PID) idea. Specifically, Integral (I) integrates a physical quantity over a time window, which agrees with the fact that determining the attributes of items also requires a long-term observation. The Differential (D) emphasizes an incremental change of a physical quantity over time, which coincidentally caters to a trend. Moreover, in the Session-Based Recommendation (SBR) community, many methods extract session interests without considering the impact of popularity on interest, leading to suboptimal recommendation results. To further improve recommendation performance, we propose a novel strategy that leverages popularity to enhance the session interest (popularity-aware interest). The proposed popularity by PID is further used to construct the popularity-aware interest, which consistently improves the recommendation performance of the main models in the SBR community. For STAMP, SRGNN, GCSAN, and TAGNN, on Yoochoose1/64, the metric P@20 is relatively improved by 0.93%, 1.84%, 2.02%, and 2.53%, respectively, and MRR@20 is relatively improved by 3.74%, 1.23%, 2.72%, and 3.48%, respectively. On Movieslen-1m, the relative improvements of P@20 are 7.41%, 15.52%, 8.20%, and 20.12%, respectively, and that of MRR@20 are 2.34%, 12.41%, 20.34%, and 19.21%, respectively.
{"title":"A Novel Popularity Extraction Method Applied in Session-Based Recommendation","authors":"Yuze Peng;Shengjun Xu;Qingkun Chen;Wenjin Huang;Yihua Huang","doi":"10.26599/TST.2023.9010061","DOIUrl":"https://doi.org/10.26599/TST.2023.9010061","url":null,"abstract":"Popularity plays a significant role in the recommendation system. Traditional popularity is only defined as a static ratio or metric (e.g., a ratio of users who have rated the item and the box office of a movie) regardless of the previous trends of this ratio or metric and the attribute diversity of items. To solve this problem and reach accurate popularity, we creatively propose to extract the popularity of an item according to the Proportional Integral Differential (PID) idea. Specifically, Integral (I) integrates a physical quantity over a time window, which agrees with the fact that determining the attributes of items also requires a long-term observation. The Differential (D) emphasizes an incremental change of a physical quantity over time, which coincidentally caters to a trend. Moreover, in the Session-Based Recommendation (SBR) community, many methods extract session interests without considering the impact of popularity on interest, leading to suboptimal recommendation results. To further improve recommendation performance, we propose a novel strategy that leverages popularity to enhance the session interest (popularity-aware interest). The proposed popularity by PID is further used to construct the popularity-aware interest, which consistently improves the recommendation performance of the main models in the SBR community. For STAMP, SRGNN, GCSAN, and TAGNN, on Yoochoose1/64, the metric P@20 is relatively improved by 0.93%, 1.84%, 2.02%, and 2.53%, respectively, and MRR@20 is relatively improved by 3.74%, 1.23%, 2.72%, and 3.48%, respectively. On Movieslen-1m, the relative improvements of P@20 are 7.41%, 15.52%, 8.20%, and 20.12%, respectively, and that of MRR@20 are 2.34%, 12.41%, 20.34%, and 19.21%, respectively.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":null,"pages":null},"PeriodicalIF":6.6,"publicationDate":"2024-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10431748","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139715228","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pub Date : 2024-02-09DOI: 10.26599/TST.2023.9010014
Pengfei Huang;Xiaojun Ren;Teng Huang;Arthur Sandor Voundi Koe;Duncan S Wong;Hai Jiang
Node synchronization is essential for the stability of the Bitcoin network. Critics have raised doubts about the ability of a new node to quickly and efficiently synchronize with the Bitcoin network and alleviate the storage pressure from existing full nodes to stockpile new data. Basic pruning and other techniques have been explored to address these concerns but have been insufficient to reduce node synchronization delay and effectively suppress the growth of synchronized data. In this study, we propose SnapshotPrune, a novel pruning and synchronization protocol that achieves fast node bootstrapping in the Bitcoin blockchain. Real Bitcoin historical data are leveraged to measure the synchronization time and monitor the network traffic during node bootstrapping. The protocol requires data downloads that are 99.70% less than Bitcoin Core, 81% less than CoinPrune, and 60% less than SnapshotSave, thereby saving 97.23% of download time. Findings show that the proposed design enhances the storage efficiency and reduces the node synchronization delay compared with existing techniques. We hypothesize that the efficiency of this protocol increases with the block height.
{"title":"SnapshotPrune: A Novel Bitcoin-Based Protocol Toward Efficient Pruning and Fast Node Bootstrapping","authors":"Pengfei Huang;Xiaojun Ren;Teng Huang;Arthur Sandor Voundi Koe;Duncan S Wong;Hai Jiang","doi":"10.26599/TST.2023.9010014","DOIUrl":"https://doi.org/10.26599/TST.2023.9010014","url":null,"abstract":"Node synchronization is essential for the stability of the Bitcoin network. Critics have raised doubts about the ability of a new node to quickly and efficiently synchronize with the Bitcoin network and alleviate the storage pressure from existing full nodes to stockpile new data. Basic pruning and other techniques have been explored to address these concerns but have been insufficient to reduce node synchronization delay and effectively suppress the growth of synchronized data. In this study, we propose SnapshotPrune, a novel pruning and synchronization protocol that achieves fast node bootstrapping in the Bitcoin blockchain. Real Bitcoin historical data are leveraged to measure the synchronization time and monitor the network traffic during node bootstrapping. The protocol requires data downloads that are 99.70% less than Bitcoin Core, 81% less than CoinPrune, and 60% less than SnapshotSave, thereby saving 97.23% of download time. Findings show that the proposed design enhances the storage efficiency and reduces the node synchronization delay compared with existing techniques. We hypothesize that the efficiency of this protocol increases with the block height.","PeriodicalId":48690,"journal":{"name":"Tsinghua Science and Technology","volume":null,"pages":null},"PeriodicalIF":6.6,"publicationDate":"2024-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"https://ieeexplore.ieee.org/stamp/stamp.jsp?tp=&arnumber=10431727","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139715230","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":1,"RegionCategory":"计算机科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}