To see the other types of publications on this topic, follow the link: Reinforcement Learning in Databases.
Journal articles on the topic 'Reinforcement Learning in Databases'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Reinforcement Learning in Databases.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Pakzad, Armie E., Raine Mattheus Manuel, Jerrick Spencer Uy, Xavier Francis Asuncion, Joshua Vincent Ligayo, and Lawrence Materum. "Reinforcement Learning-Based Television White Space Database." Baghdad Science Journal 18, no. 2(Suppl.) (2021): 0947. http://dx.doi.org/10.21123/bsj.2021.18.2(suppl.).0947.
Full textAbstract:
Television white spaces (TVWSs) refer to the unused part of the spectrum under the very high frequency (VHF) and ultra-high frequency (UHF) bands. TVWS are frequencies under licenced primary users (PUs) that are not being used and are available for secondary users (SUs). There are several ways of implementing TVWS in communications, one of which is the use of TVWS database (TVWSDB). The primary purpose of TVWSDB is to protect PUs from interference with SUs. There are several geolocation databases available for this purpose. However, it is unclear if those databases have the prediction feature that gives TVWSDB the capability of decreasing the number of inquiries from SUs. With this in mind, the authors present a reinforcement learning-based TVWSDB. Reinforcement learning (RL) is a machine learning technique that focuses on what has been done based on mapping situations to actions to obtain the highest reward. The learning process was conducted by trying out the actions to gain the reward instead of being told what to do. The actions may directly affect the rewards and future rewards. Based on the results, this algorithm effectively searched the most optimal channel for the SUs in query with the minimum search duration. This paper presents the advantage of using a machine learning approach in TVWSDB with an accurate and faster-searching capability for the available TVWS channels intended for SUs.
2
Nzenwata, Uchenna Jeremiah, Goodness Oluwamayokun Opateye, Noze-Otote Aisosa, et al. "Autonomous Database Systems – A Systematic Review of Self-Healing and Self-Tuning Database Systems." Asian Journal of Research in Computer Science 18, no. 7 (2025): 77–87. https://doi.org/10.9734/ajrcos/2025/v18i7721.
Full textAbstract:
Problem Statement: Autonomous database systems represent a significant change in the management of databases, utilizing Machine Learning (ML) and Artificial Intelligence (AI) in order to carry out self-healing and self-tuning with minimal human intervention. Objectives: This systematic review investigates the defining characteristics, AI/ML techniques, challenges and the future trends of self-healing and self-tuning autonomous databases. Methodology: The research questions were answered integrating findings from 35 current literatures between 2020 and 2025. These literatures were obtained from several reputable databases. Results: From the study, self-healing databases employ techniques such as autoencoders, hidden Markov models, clustering algorithms, reinforcement learning, Bayesian optimization, neural networks and surrogate models to detect and recover from faults, enhancing operational resilience. On the other hand, self-tuning databases employ reinforcement learning, neural networks, multi-armed bandit techniques, decision trees, regression models, Bayesian optimization, and anomaly detection to optimize query execution, indexing, and resource allocation. Challenges in applying AI/ML in autonomous databases study include data quality dependencies, and adaptation to dynamic workload still exists and integration into existing infrastructures. Conclusion: The deeper integration of deep learning techniques and predictive modelling serves as future trends to improve this autonomy.
3
Kumar, Ritesh. "AI-Augmented Database Indexing for High-Performance Query Optimization." International Scientific Journal of Engineering and Management 02, no. 11 (2023): 1–7. https://doi.org/10.55041/isjem01292.
Full textAbstract:
Abstract—Database indexing plays a crucial role in optimizing query performance, particularly in cloud-native and high-performance computing environments. Traditional indexing techniques often struggle to adapt dynamically to varying workloads, leading to suboptimal query execution times and increased computational overhead. This paper presents an AI-augmented approach to database indexing that leverages reinforcement learning-based adaptive indexing and machine learning-driven query optimization. By integrating AI models into indexing strategies, databases can dynamically adjust index structures, predict query access patterns, and optimize execution plans in real time. The proposed framework is evaluated using PostgreSQL, DocumentDB, and GraphDB, demonstrating significant improvements in query execution speed, resource utilization, and overall system efficiency. The paper also discusses the architectural considerations for deploying AI-augmented indexing in distributed database systems and explores its impact on read-heavy and write- intensive workloads. Experimental results highlight significant performance gains achieved through AI-driven indexing, paving the way for more intelligent and adaptive database systems. Keywords— AI-driven indexing, database optimization, adaptive indexing, reinforcement learning, query performance, PostgreSQL, DocumentDB, GraphDB, machine learning, cloud databases, high-performance computing
4
Bhattarai, Sushil, and Suman Thapaliya. "A Novel Approach to Self-tuning Database Systems Using Reinforcement Learning Techniques." NPRC Journal of Multidisciplinary Research 1, no. 7 (2024): 143–49. https://doi.org/10.3126/nprcjmr.v1i7.72480.
Full textAbstract:
The rapid evolution of data-intensive applications has intensified the need for efficient and adaptive database systems. Traditional database tuning methods, relying on manual interventions and rule-based optimizations, often fall short in handling dynamic workloads and complex parameter interdependencies. This paper introduces a novel approach to self-tuning database systems using reinforcement learning (RL) techniques, enabling databases to autonomously optimize configurations such as indexing strategies, memory allocation, and query execution plans. The proposed framework significantly enhances performance, scalability, and resource utilization by leveraging RL’s ability to learn from interactions and adapt to changing environments. Experimental evaluations demonstrate up to a 45% improvement in query execution times and superior adaptability to workload variations compared to traditional methods. This study highlights RL's potential to transform database management, setting the stage for next-generation intelligent and autonomous data systems. Modern database systems face increasing complexity due to the diverse workloads and dynamic environments they operate in. Traditional database tuning methods often require significant manual intervention and expertise, making them inefficient for large-scale systems. This paper presents a novel approach to self-tuning database systems using reinforcement learning (RL) techniques. By leveraging RL, databases can autonomously learn and adapt to changing conditions, optimizing configurations such as indexing, query execution plans, and memory allocation. We outline a framework for implementing RL-based self-tuning, discuss key challenges, and evaluate the approach against traditional methods. Results indicate significant improvements in performance, adaptability, and resource utilization, demonstrating the potential of RL for next-generation database systems.
5
Shi, Lei, Tian Li, Lin Wei, Yongcai Tao, Cuixia Li, and Yufei Gao. "FASTune: Towards Fast and Stable Database Tuning System with Reinforcement Learning." Electronics 12, no. 10 (2023): 2168. http://dx.doi.org/10.3390/electronics12102168.
Full textAbstract:
Configuration tuning is vital to achieving high performance for a database management system (DBMS). Recently, automatic tuning methods using Reinforcement Learning (RL) have been explored to find better configurations compared with database administrators (DBAs) and heuristics. However, existing RL-based methods still have several limitations: (1) Excessive overhead due to reliance on cloned databases; (2) trial-and-error strategy may produce dangerous configurations that lead to database failure; (3) lack the ability to handle dynamic workload. To address the above challenges, a fast and stable RL-based database tuning system, FASTune, is proposed. A virtual environment is proposed to evaluate configurations which is an equivalent yet more efficient scheme than the cloned database. To ensure stability during tuning, FASTune adopts an environment proxy to avoid dangerous configurations. In addition, a Multi-State Soft Actor–Critic (MS-SAC) model is proposed to handle dynamic workloads, which utilizes the soft actor–critic network to tune the database according to workload and database states. The experimental results indicate that, compared with the state-of-the-art methods, FASTune can achieve improvements in performance while maintaining stability in the tuning.
6
Blank, Sebastian, Florian Wilhelm, Hans-Peter Zorn, and Achim Rettinger. "Querying NoSQL with Deep Learning to Answer Natural Language Questions." Proceedings of the AAAI Conference on Artificial Intelligence 33 (July 17, 2019): 9416–21. http://dx.doi.org/10.1609/aaai.v33i01.33019416.
Full textAbstract:
Almost all of today’s knowledge is stored in databases and thus can only be accessed with the help of domain specific query languages, strongly limiting the number of people which can access the data. In this work, we demonstrate an end-to-end trainable question answering (QA) system that allows a user to query an external NoSQL database by using natural language. A major challenge of such a system is the non-differentiability of database operations which we overcome by applying policy-based reinforcement learning. We evaluate our approach on Facebook’s bAbI Movie Dialog dataset and achieve a competitive score of 84.2% compared to several benchmark models. We conclude that our approach excels with regard to real-world scenarios where knowledge resides in external databases and intermediate labels are too costly to gather for non-end-to-end trainable QA systems.
7
Srikanth Reddy Keshireddy. "Reinforcement Learning Based Optimization of Query Execution Plans in Distributed Databases." Research Briefs on Information and Communication Technology Evolution 11 (March 11, 2025): 42–61. https://doi.org/10.69978/rebicte.v11i.211.
Full textAbstract:
Troublesome workloads, data heterogeneity, and shifting resource conditions make efficient query execution highly difficult to achieve in distributed database systems. Traditional optimizers will almost always rely on handcrafted methods or static cost models to achieve the desired results, resulting in adaptative failures along the way and serving at best subpar query execution plans (QEPs). This paper presents a new architecture meant to optimize QEPs by utilizing deep policy reinforcement learning (RL) for dynamically shifting execution strategy adaptations over distributed nodes. The proposed model considers and structures the optimization problem as a Markov Decision Process (MDP) with states available in the form of system and query profiles, actions available being the choices of QEPs, and the rewards acting as a mere performance measurement for execution. We analyze this approach with different combinations of queries and nodes through benchmark datasets and simulated environments. The objective of this evaluation is to test the model’s performance in regards to differing query kinds and node configurations. The experiments indicate remarkable advances in system throughput and execution time while achieving strong generalization to unfamiliar queries. These results support the hypothesized ability of query processing in future distributed databases to not have suggestion mechanisms reliant on rules or costs, unlike their predecessors, and instead implement optimizers that utilize RL.
8
Sharma, Manas. "Machine Learning-Based Inferential Statistics for Query Optimization: A Novel Approach." European Journal of Computer Science and Information Technology 13, no. 18 (2025): 76–90. https://doi.org/10.37745/ejcsit.2013/vol13n187690.
Full textAbstract:
The ML-based inferential statistics framework presents a novel solution for database query optimization that addresses critical challenges in statistics maintenance and cardinality estimation. By combining Bayesian learning and reinforcement learning modules, the framework enables continuous adaptation to changing data patterns while minimizing computational overhead. The solution offers improved query performance through better plan selection, reduced resource consumption, and enhanced accuracy in cardinality estimation. The framework's dynamic histogram redistribution mechanism ensures optimal statistics maintenance in high-throughput environments, making it particularly effective for enterprise-scale databases with rapidly evolving data distributions.
9
Sassi, Najla, and Wassim Jaziri. "Efficient AI-Driven Query Optimization in Large-Scale Databases: A Reinforcement Learning and Graph-Based Approach." Mathematics 13, no. 11 (2025): 1700. https://doi.org/10.3390/math13111700.
Full textAbstract:
As data-centric applications become increasingly complex, understanding effective query optimization in large-scale relational databases is crucial for managing this complexity. Yet, traditional cost-based and heuristic approaches simply do not scale, adapt, or remain accurate in highly dynamic multi-join queries. This research work proposes the reinforcement learning and graph-based hybrid query optimizer (GRQO), the first ever to apply reinforcement learning and graph theory for optimizing query execution plans, specifically in join order selection and cardinality estimation. By employing proximal policy optimization for adaptive policy learning and using graph-based schema representations for relational modeling, GRQO effectively traverses the combinatorial optimization space. Based on TPC-H (1 TB) and IMDB (500 GB) workloads, GRQO runs 25% faster in query execution time, scales 30% better, reduces CPU and memory use by 20–25%, and reduces the cardinality estimation error by 47% compared to traditional cost-based optimizers and machine learning-based optimizers. These findings highlight the ability of GRQO to optimize performance and resource efficiency in database management in cloud computing, data warehousing, and real-time analytics.
10
Sun, Jun, Feng Ye, Nadia Nedjah, Ming Zhang, and Dong Xu. "Workload-Aware Performance Tuning for Multimodel Databases Based on Deep Reinforcement Learning." International Journal of Intelligent Systems 2023 (September 5, 2023): 1–17. http://dx.doi.org/10.1155/2023/8835111.
Full textAbstract:
Currently, multimodel databases are widely used in modern applications, but the default configuration often fails to achieve the best performance. How to efficiently manage and tune the performance of multimodel databases is still a problem. Therefore, in this study, we present a configuration parameter tuning tool MMDTune+ for ArangoDB. First, the selection of configuration parameters is based on the random forest algorithm for feature selection. Second, a workload-aware mechanism is based on k-means++ and the Pearson correlation coefficient to detect workload changes and match the empirical knowledge of historically similar workloads. Finally, the ArangoDB configuration parameters are optimized based on the improved TD3 algorithm. The experimental results show that MMDTune+ can recommend higher-quality configuration parameters for ArangoDB compared to OtterTune and CDBTune in different scenarios.
11
Warveen, merza eido, and Maseeh Yasin Hajar. "Machine Learning Approaches for Enhancing Query Optimization in Large Databases." Engineering and Technology Journal 10, no. 03 (2025): 4326–49. https://doi.org/10.5281/zenodo.15105850.
Full textAbstract:
More effective query optimization strategies in large-scale databases are required due to the growing volume and complexity of data in contemporary applications. Performance inefficiencies result from traditional query optimization techniques, such as rule-based and cost-based approaches, which frequently find it difficult to manage dynamic and complicated workloads. By utilizing deep learning, reinforcement learning, and predictive analytics to enhance query execution plans, indexing, and workload management, machine learning (ML) has become a game-changing method for improving query optimization. With its many advantages—including workload-aware indexing, adaptive tuning, and real-time performance improvements—ML-driven optimization approaches are especially well-suited for distributed and cloud-based database setups. However, challenges remain, such as the need for more explainable AI-powered optimizers, security vulnerabilities, and the high computational costs of training machine learning models. To ensure reliable and efficient database management, future research should focus on creating hybrid optimization frameworks, strengthening security measures, and making machine learning-based decision-making more explainable. By addressing these challenges, machine learning-powered query optimization could open the door to smarter, more flexible, and scalable database systems.
12
Gerhard, Detlef, Julian Rolf, Pascalis Trentsios, and Jan Luca Siewert. "Machine Learning Methods for (Dis-)Assembly Sequence Planning - A Systematic Literature Review." International Journal of Advances in Production Research 1, no. 1 (2024): 83–98. http://dx.doi.org/10.62743/uad.8279.
Full textAbstract:
This paper presents a systematic literature review on the application of reinforcement learning in the domain of assembly and disassembly sequence planning. The authors conduct a keyword search to identify scientific publications in the desired field in three scientific databases. Web of Science, Scopus and IEEE-Xplore. The analysis covers two core aspects of reinforcement learning, namely the definition of the reward function and the representation of states. In total 23 publications are identified, and the content of the collected works is presented. An analysis of the selected publications is then carried out in relation to the questions posed in order to be able to make recommendations for the application of reinforcement learning methods for the generation of efficient assembly and demonstration sequences.
13
Liu, Siqi, Kay Choong See, Kee Yuan Ngiam, Leo Anthony Celi, Xingzhi Sun, and Mengling Feng. "Reinforcement Learning for Clinical Decision Support in Critical Care: Comprehensive Review." Journal of Medical Internet Research 22, no. 7 (2020): e18477. http://dx.doi.org/10.2196/18477.
Full textAbstract:
Background Decision support systems based on reinforcement learning (RL) have been implemented to facilitate the delivery of personalized care. This paper aimed to provide a comprehensive review of RL applications in the critical care setting. Objective This review aimed to survey the literature on RL applications for clinical decision support in critical care and to provide insight into the challenges of applying various RL models. Methods We performed an extensive search of the following databases: PubMed, Google Scholar, Institute of Electrical and Electronics Engineers (IEEE), ScienceDirect, Web of Science, Medical Literature Analysis and Retrieval System Online (MEDLINE), and Excerpta Medica Database (EMBASE). Studies published over the past 10 years (2010-2019) that have applied RL for critical care were included. Results We included 21 papers and found that RL has been used to optimize the choice of medications, drug dosing, and timing of interventions and to target personalized laboratory values. We further compared and contrasted the design of the RL models and the evaluation metrics for each application. Conclusions RL has great potential for enhancing decision making in critical care. Challenges regarding RL system design, evaluation metrics, and model choice exist. More importantly, further work is required to validate RL in authentic clinical environments.
14
Barbosa, Diogo, Le Gruenwald, Laurent D’Orazio, and Jorge Bernardino. "QRLIT: Quantum Reinforcement Learning for Database Index Tuning." Future Internet 16, no. 12 (2024): 439. http://dx.doi.org/10.3390/fi16120439.
Full textAbstract:
Selecting indexes capable of reducing the cost of query processing in database systems is a challenging task, especially in large-scale applications. Quantum computing has been investigated with promising results in areas related to database management, such as query optimization, transaction scheduling, and index tuning. Promising results have also been seen when reinforcement learning is applied for database tuning in classical computing. However, there is no existing research with implementation details and experiment results for index tuning that takes advantage of both quantum computing and reinforcement learning. This paper proposes a new algorithm called QRLIT that uses the power of quantum computing and reinforcement learning for database index tuning. Experiments using the database TPC-H benchmark show that QRLIT exhibits superior performance and a faster convergence compared to its classical counterpart.
15
Olayinka Akinbolajo. "Intelligent load balancing and concurrency control in cloud-based distributed databases: A machine learning approach." International Journal of Science and Research Archive 9, no. 1 (2023): 847–54. https://doi.org/10.30574/ijsra.2023.9.1.0350.
Full textAbstract:
Cloud-based distributed databases are critical for scalable modern applications, yet they struggle with uneven resource utilization and transaction conflicts. This paper introduces a machine learning (ML)driven framework combining reinforcement learning (RL) for dynamic load balancing and a hybrid concurrency control protocol. The RL agent optimizes query distribution by analyzing real-time node metrics, while the concurrency controller adaptively switches between optimistic and pessimistic strategies based on conflict predictions. Evaluations on AWS EC2 using the YCSB benchmark demonstrate a 30% improvement in throughput, 25% reduction in latency, and a 47% decrease in abort rates compared to traditional methods. The results validate the efficacy of AI-driven solutions in enhancing cloud database performance and scalability.
16
Warnke, Benjamin, Kevin Martens, Tobias Winker, et al. "ReJOOSp: Reinforcement Learning for Join Order Optimization in SPARQL." Big Data and Cognitive Computing 8, no. 7 (2024): 71. http://dx.doi.org/10.3390/bdcc8070071.
Full textAbstract:
The choice of a good join order plays an important role in the query performance of databases. However, determining the best join order is known to be an NP-hard problem with exponential growth with the number of joins. Because of this, nonlearning approaches to join order optimization have a longer optimization and execution time. In comparison, the models of machine learning, once trained, can construct optimized query plans very quickly. Several efforts have applied machine learning to optimize join order for SQL queries outperforming traditional approaches. In this work, we suggest a reinforcement learning technique for join optimization for SPARQL queries, ReJOOSp. SPARQL queries typically contain a much higher number of joins than SQL queries and so are more difficult to optimize. To evaluate ReJOOSp, we further develop a join order optimizer based on ReJOOSp and integrate it into the Semantic Web DBMS Luposdate3000. The evaluation of ReJOOSp shows its capability to significantly enhance query performance by achieving high-quality execution plans for a substantial portion of queries across synthetic and real-world datasets.
17
Choi, Seul-Gi, and Sung-Bae Cho. "Evolutionary Reinforcement Learning for Adaptively Detecting Database Intrusions." Logic Journal of the IGPL 28, no. 4 (2019): 449–60. http://dx.doi.org/10.1093/jigpal/jzz053.
Full textAbstract:
Abstract Relational database management system (RDBMS) is the most popular database system. It is important to maintain data security from information leakage and data corruption. RDBMS can be attacked by an outsider or an insider. It is difficult to detect an insider attack because its patterns are constantly changing and evolving. In this paper, we propose an adaptive database intrusion detection system that can be resistant to potential insider misuse using evolutionary reinforcement learning, which combines reinforcement learning and evolutionary learning. The model consists of two neural networks, an evaluation network and an action network. The action network detects the intrusion, and the evaluation network provides feedback to the detection of the action network. Evolutionary learning is effective for dynamic patterns and atypical patterns, and reinforcement learning enables online learning. Experimental results show that the performance for detecting abnormal queries improves as the proposed model learns the intrusion adaptively using Transaction Processing performance Council-E scenario-based virtual query data. The proposed method achieves the highest performance at 94.86%, and we demonstrate the usefulness of the proposed method by performing 5-fold cross-validation.
18
Binashir, Rofi'ah, Fakhrurroja Hanif, and Machbub Carmadi. "Dialogue management using reinforcement learning." TELKOMNIKA (Telecommunication, Computing, Electronics and Control) 19, no. 3 (2021): 931–38. https://doi.org/10.12928/telkomnika.v19i3.18319.
Full textAbstract:
Dialogue has been widely used for verbal communication between human and robot interaction, such as assistant robot in hospital. However, this robot was usually limited by predetermined dialogue, so it will be difficult to understand new words for new desired goal. In this paper, we discussed conversation in Indonesian on entertainment, motivation, emergency, and helping with knowledge growing method. We provided mp3 audio for music, fairy tale, comedy request, and motivation. The execution time for this request was 3.74 ms on average. In emergency situation, patient able to ask robot to call the nurse. Robot will record complaint of pain and inform nurse. From 7 emergency reports, all complaints were successfully saved on database. In helping conversation, robot will walk to pick up belongings of patient. Once the robot did not understand with patient’s conversation, robot will ask until it understands. From asking conversation, knowledge expands from 2 to 10, with learning execution from 1405 ms to 3490 ms. SARSA was faster towards steady state because of higher cumulative rewards. Q-learning and SARSA were achieved desired object within 200 episodes. It concludes that reinforcement learning (RL) method to overcome robot knowledge limitation in achieving new dialogue goal for patient assistant were achieved.
19
Rafea M. Ibrahim. "Exploring the Impact of Data Locality in Distributed Databases: A Machine Learning-Driven Approach to Optimizing Data Placement Strategies." Journal of Information Systems Engineering and Management 10, no. 11s (2025): 329–37. https://doi.org/10.52783/jisem.v10i11s.1595.
Full textAbstract:
Data locality significantly influences the performance of distributed databases, affecting query response times and resource utilization. This study investigates the role of data locality in enhancing the efficiency of distributed systems through a machine learning-driven approach to optimize data placement strategies. By analyzing access patterns, network latencies, and computational loads, we develop predictive models that inform dynamic data placement decisions. Utilizing reinforcement learning algorithms, the study adapts to fluctuating workloads, effectively minimizing data transfer times and maximizing throughput. Empirical results illustrate substantial improvements in query performance and resource management, highlighting the efficacy of intelligent data locality strategies. This study paves the way for future advancements in artificial intelligence-driven optimization for distributed database architectures.
20
Dabiri, Hamed, Visar Farhangi, Mohammad Javad Moradi, Mehdi Zadehmohamad, and Moses Karakouzian. "Applications of Decision Tree and Random Forest as Tree-Based Machine Learning Techniques for Analyzing the Ultimate Strain of Spliced and Non-Spliced Reinforcement Bars." Applied Sciences 12, no. 10 (2022): 4851. http://dx.doi.org/10.3390/app12104851.
Full textAbstract:
The performance of both non-spliced and spliced steel bars significantly affects the overall performance of structural reinforced concrete elements. In this context, the mechanical properties of reinforcement bars (i.e., their ultimate strength and strain) should be determined in order to evaluate their reliability prior to the construction procedure. In this study, the application of Tree-Based machine learning techniques is implemented to analyze the ultimate strain of non-spliced and spliced steel reinforcements. In this regard, a database containing the results of 225 experimental tests was collected based on the research investigations available in peer-reviewed international publications. The database included the mechanical properties of both non-spliced and mechanically spliced bars. For better accuracy, the databases of other splicing methods such as lap and welded-spliced methods were excluded from this research. The database was categorized as two sub-databases: training (85%) and testing (15%) of the developed models. Various effective parameters such as splice technique, steel grade of the bar, diameter of the steel bar, coupler geometry—including length and outer diameter along with the testing temperatures—were defined as the input variables for analyzing the ultimate strain using tree-based approaches including Decision Trees and Random Forest. The predicted outcomes were compared to the actual values and the precision of the prediction models was assessed via performance metrics, along with a Taylor diagram. Based on the reported results, the reliability of the proposed ML-based methods was acceptable (with an R2 ≥ 85%) and they were time-saving and cost-effective compared to more complicated, time-consuming, and expensive experimental examinations. More importantly, the models proposed in this study can be further considered as a part of a comprehensive prediction model for estimating the stress-strain behavior of steel bars.
21
Modrak, Vladimir, Ranjitharamasamy Sudhakarapandian, Arunmozhi Balamurugan, and Zuzana Soltysova. "A Review on Reinforcement Learning in Production Scheduling: An Inferential Perspective." Algorithms 17, no. 8 (2024): 343. http://dx.doi.org/10.3390/a17080343.
Full textAbstract:
In this study, a systematic review on production scheduling based on reinforcement learning (RL) techniques using especially bibliometric analysis has been carried out. The aim of this work is, among other things, to point out the growing interest in this domain and to outline the influence of RL as a type of machine learning on production scheduling. To achieve this, the paper explores production scheduling using RL by investigating the descriptive metadata of pertinent publications contained in Scopus, ScienceDirect, and Google Scholar databases. The study focuses on a wide spectrum of publications spanning the years between 1996 and 2024. The findings of this study can serve as new insights for future research endeavors in the realm of production scheduling using RL techniques.
22
Mehmood, Saba, and Syaharuddin Syaharuddin. "Reinforcement Learning for Automated Systems: Review of Concepts and Implementations." Jurnal Pemikiran dan Penelitian Pendidikan Matematika (JP3M) 7, no. 2 (2025): 146–66. https://doi.org/10.36765/jp3m.v7i2.734.
Full textAbstract:
Abstrak: Studi ini bertujuan untuk melakukan kajian mendalam terhadap implementasi dan konsep Reinforcement Learning (RL) dalam sistem otomatis melalui pendekatan Systematic Literature Review. Penelitian ini menggunakan sumber literatur dari database seperti Scopus, DOAJ, dan Google Scholar dengan rentang tahun 2014-2024. Tinjauan ini menyoroti aplikasi RL dalam berbagai domain sistem otomatis seperti robotika, kendaraan otonom, manajemen lalu lintas, kedirgantaraan, manajemen energi, dan perawatan kesehatan. Hasil tinjauan menunjukkan bahwa RL memberikan kontribusi signifikan dalam meningkatkan efisiensi, adaptabilitas, dan kecerdasan sistem otomatis. Namun, implementasi RL juga dihadapkan pada tantangan seperti efisiensi data yang buruk, biaya komputasi yang tinggi, dan ketergantungan pada infrastruktur teknologi yang memadai. Berbagai solusi telah diusulkan, seperti pengoptimalan perangkat keras, metode hemat data, dan integrasi informasi struktural tambahan, untuk mengatasi tantangan ini. Meskipun demikian, masih diperlukan penelitian lanjutan untuk mengembangkan teknik-teknik yang lebih efisien dan adaptif dalam penggunaan data serta integrasi RL dengan infrastruktur otomatisasi yang lebih luas. Penelitian ini mengidentifikasi kesenjangan dalam literatur dan merumuskan topik riset mendesak untuk mengeksplorasi solusi-solusi inovatif guna memperluas aplikasi RL di masa mendatang. Abstract: This study aims to conduct an in-depth review of the implementation and concepts of Reinforcement Learning (RL) in automated systems through a Systematic Literature Review approach. The research utilizes literature sources from databases such as Scopus, DOAJ, and Google Scholar spanning the years 2014 to 2024. The review highlights RL applications in various domains of automated systems including robotics, autonomous vehicles, traffic management, aerospace, energy management, and healthcare. The findings reveal that RL significantly contributes to enhancing efficiency, adaptability, and intelligence in automated systems. However, RL implementation faces challenges such as poor data efficiency, high computational costs, and dependence on adequate technological infrastructure. Various solutions have been proposed, such as hardware optimization, data-efficient methods, and the integration of additional structural information, to address these challenges. Nevertheless, further research is needed to develop more efficient and adaptive techniques in data utilization and the integration of RL with broader automation infrastructure. This study identifies gaps in the literature and formulates urgent research topics to explore innovative solutions for expanding RL applications in the future.
23
Salieva, A. R., N. A. Verzun, and M. O. Kolbanev. "Strategy Optimization in Reinforcement Learning Algorithms in Logistic Decision-Making Systems." LETI Transactions on Electrical Engineering & Computer Science 18, no. 3 (2025): 65–77. https://doi.org/10.32603/2071-8985-2025-18-3-65-77.
Full textAbstract:
This review paper aims to analyze and systematize the current research in the field of strategy optimization of reinforcement learning algorithms used in logistic decision-making systems. In the course of the review we have considered scientific publications for the last 5 years, indexed in the leading databases, devoted to the application of reinforcement learning methods in logistics. Particular attention is paid to papers describing Policy Gradient and Proximal Policy Optimization (PPO) algorithms. The methodology of the review includes comparative analysis, classification of approaches and evaluation of their effectiveness. The main trends in the development of policy optimization methods for logistics systems are identified. The key advantages and limitations of different approaches are identified. It is found that PPO-based methods demonstrate the highest efficiency in complex dynamic environments. A growing interest in hybrid approaches combining reinforcement learning and classical optimization methods is found. Promising directions for further research are highlighted, including adapting algorithms to specific logistics problems and improving their interpretability. The results obtained can serve as a basis for the development of new algorithms and their practical application in various sectors of logistics and supply chain management.
24
Huang, Honglan, and Henry V. Burton. "A database of test results from steel and reinforced concrete infilled frame experiments." Earthquake Spectra 36, no. 3 (2020): 1525–48. http://dx.doi.org/10.1177/8755293019899950.
Full textAbstract:
Extensive experimental investigations into the behavior of reinforcement concrete and steel frames with infill have been conducted worldwide. However, there are very few systematically created and publicly available databases on infilled frame experiments. This article assembles a database of 264 experiments on single-story infilled frames, which includes specimens with different types of frames and panels. It has been utilized by the authors (in separate studies) to develop (1) empirical equations for modeling the infill panels as equivalent struts and (2) machine learning models for failure mode classification. The intent is for the database to be augmented and further used in various other applications in studying the seismic behavior of masonry-infilled frames.
25
Gopikrishna Maddali. "Enhancing Database Architectures with Artificial Intelligence (AI)." International Journal of Scientific Research in Science and Technology 12, no. 3 (2025): 296–308. https://doi.org/10.32628/ijsrst2512331.
Full textAbstract:
Artificial intelligence and Database Management Systems Integration bring intelligence, adaptability, and independence in the world of databases. Relational database management systems structure the data and have been the foundations for implementing them, although they face several challenges that have arisen from modern-day environments of computing and information processing, such as scalability, real-time processing, the incorporation of unstructured data, and capabilities for making proactive decisions. As a result, new approaches like NoSQL and NewSQL appeared to address various and scalable needs of the applications. AI concepts such as Machine learning (ML), Deep learning (DL), and Natural language processing (NLP) have brought about improvement of advanced functions and optimization of efficiency into current database systems. These are self-tuning, query optimization, predictive caching, and natural language interfaces that enable a database to work autonomously while offering high-performance and reliability service. This paper focuses on the traditional and advanced DBMS architectures, the development and integration of AI-based DBMS, and other novelties such as federated learning and reinforcement-based cache.
26
Yan, Yu, Shun Yao, Hongzhi Wang, and Meng Gao. "Index selection for NoSQL database with deep reinforcement learning." Information Sciences 561 (June 2021): 20–30. http://dx.doi.org/10.1016/j.ins.2021.01.003.
Full text
27
Wee, Chee Keong, and Richi Nayak. "Adaptive load forecasting using reinforcement learning with database technology." Journal of Information and Telecommunication 3, no. 3 (2019): 381–99. http://dx.doi.org/10.1080/24751839.2019.1596470.
Full text
28
Paludo Licks, Gabriel, Julia Colleoni Couto, Priscilla de Fátima Miehe, Renata de Paris, Duncan Dubugras Ruiz, and Felipe Meneguzzi. "SmartIX: A database indexing agent based on reinforcement learning." Applied Intelligence 50, no. 8 (2020): 2575–88. http://dx.doi.org/10.1007/s10489-020-01674-8.
Full text
29
Bai, Ruxue, Rongshang Chen, Xiao Lei, and Keshou Wu. "A Test Report Optimization Method Fusing Reinforcement Learning and Genetic Algorithms." Electronics 13, no. 21 (2024): 4281. http://dx.doi.org/10.3390/electronics13214281.
Full textAbstract:
Filtering high-variability and high-severity defect reports from large test report databases is a challenging task in crowdtesting. Traditional optimization algorithms based on clustering and distance techniques have made progress but are limited by initial parameter settings and significantly decrease in efficiency with an increasing number of reports. To address this issue, this paper proposes a method that integrates reinforcement learning with genetic algorithms for crowdsourced testing report optimization, called Reinforcement Learning-based Genetic Algorithm for Crowdsourced Testing Report Optimization (RLGA). Its core goal is to identify distinct, high-severity defect reports from a large set. The method uses genetic algorithms to generate the optimal report selection sequence and adjusts the crossover probability (Pc) and mutation probability (Pm) dynamically with reinforcement learning based on the population’s average fitness, best fitness, and diversity. The reinforcement learning component uses a hybrid SARSA and Q-Learning strategy to update the Q-value table, allowing the algorithm to learn quickly in early iterations and expand the search space later to avoid local optima, thereby improving efficiency. To validate the RLGA method, this paper uses four public datasets and compares RLGA with six classic methods. The results indicate that RLGA outperforms BDDIV in terms of execution time and is less sensitive to the total number of test reports. In terms of optimization objectives, the test reports selected by RLGA have higher levels of defect severity and diversity than those selected by the random choice, BDDIV, and TSE methods. Regarding population diversity, RLGA effectively enhances the uniformity and diversity of individuals compared to random initialization. In terms of convergence speed, RLGA is superior to the GA, GA-SARSA, and GA-Q methods.
30
Kovalov, Serhii, Viktor Aulin, Andriy Grynkiv, and Yuriy Kovalov. "Modeling the Stochastic State Matrix of a Production Line for Optimize its Operational Reliability Using Reinforcement Learning." Central Ukrainian Scientific Bulletin. Technical Sciences 2, no. 11(42) (2025): 195–203. https://doi.org/10.32515/2664-262x.2025.11(42).2.195-203.
Full textAbstract:
The development of a production line state determination model aims to create a universal tool for evaluating and optimizing industrial systems. The proposed approach enables real-time analysis of equipment states, prediction of potential failures, and enhancement of overall operational efficiency. The use of Markov chains allows for precise modeling of the sequence of production line states and the probabilities of transitions between them. This stochastic approach improves adaptability to real-world manufacturing conditions, surpassing the capabilities of traditional deterministic methods. The formation of a stochastic state matrix optimizes production processes through advanced data analytics and AI integration. This enables manufacturers to minimize downtime, enhance resource allocation, and improve overall productivity while maintaining operational stability. Transition probability estimation is based on both historical databases and real-time sensor measurements, allowing the model to adapt to various equipment types and operating conditions. AI-driven optimization enhances failure prediction accuracy, ensuring the production line remains efficient under diverse scenarios. By integrating Markov chains with data-driven insights, the approach supports proactive failure prevention and strategic resource management, ultimately improving the reliability and performance of industrial systems.
31
Zurita Álava, Susana Patricia. "El refuerzo académico una praxis docente: aportes para una propuesta a partir de la evaluación del aprendizaje: una revisión bibliográfica." KIRIA: Revista Científica Multidisciplinaria 3, no. 5 (2025): 111–28. https://doi.org/10.53877/p7stst02.
Full textAbstract:
Currently, teaching praxis, academic reinforcement and formative assessment are pillars of education. This literature review analyzes the functions of academic reinforcement as a teaching practice based on learning assessment. The PRISMA method was used to ensure clarity and transparency in the information, following four phases: identification, selection, eligibility and inclusion. The sources were databases such as Scopus and Google Scholar, using keywords such as academic performance, formative assessment, teaching practice, feedback, combined with Boolean operators OR and AND, reaching a total of 178 publications. In the selection phase, studies between 2015 and 2024 in English, Spanish and Portuguese were included, reducing to 92 records. After reviewing titles and abstracts. Of these, 66 studies were reviewed in detail. In the eligibility phase, the CASP checklist for qualitative articles was used excluding 40 studies that did not meet the quality criteria, leaving 26 for the final analysis. It was concluded that academic reinforcement in teaching practice is an intervention process aimed at improving students' academic performance generated from learning assessment and implemented through tutorial action.
32
Mr. Godly C Mathew Zachariah, Mr. Sachu Santhosh, Mr. Anandhrosh S, Mr. Shibin Thomas, and Cina Mathew. "Database and Modern Database Technology." International Research Journal on Advanced Engineering and Management (IRJAEM) 2, no. 12 (2024): 3680–86. https://doi.org/10.47392/irjaem.2024.0546.
Full textAbstract:
This paper articulates a holistic approach to study the future of database development as well as the interaction between AI and modern database technologies. Overall architecture is data-centric so that quality of data, security, and governance are enhanced. It addresses the scalability and cost-effectiveness of cloud-native versus serverless database solutions and introduces AI-powered approaches towards the management of databases like predictive maintenance, self-healing, and XAI toward transparency and accountability. Methodology: Real-time Data Analysis Real-time data analysis involving new tools such as Apache Kafka and Spark Streaming coupled with emerging AI techniques - GNNs, NLP, reinforcement learning, transfer learning, and quantum computing. Comparative analysis with Google Cloud AI Platform along with a comparison of its AI tools and platforms and even against another tool like Apache Cassandra that is used to implement such real-world applications, studying their efficiency in it. Finally, the research suggests strategies that will help in future-proofing database management with robust data governance, continuous learning, stakeholder collaboration, and adaptability to evolving technologies. This methodology is designed to draw on theoretical research, experimental validation, and practical case studies to provide a structured framework in which AI can be leveraged to drive innovation and sustainability in database systems.
33
Ager Meldgaard, Søren, Jonas Köhler, Henrik Lund Mortensen, Mads-Peter V. Christiansen, Frank Noé, and Bjørk Hammer. "Generating stable molecules using imitation and reinforcement learning." Machine Learning: Science and Technology 3, no. 1 (2021): 015008. http://dx.doi.org/10.1088/2632-2153/ac3eb4.
Full textAbstract:
Abstract Chemical space is routinely explored by machine learning methods to discover interesting molecules, before time-consuming experimental synthesizing is attempted. However, these methods often rely on a graph representation, ignoring 3D information necessary for determining the stability of the molecules. We propose a reinforcement learning (RL) approach for generating molecules in Cartesian coordinates allowing for quantum chemical prediction of the stability. To improve sample-efficiency we learn basic chemical rules from imitation learning (IL) on the GDB-11 database to create an initial model applicable for all stoichiometries. We then deploy multiple copies of the model conditioned on a specific stoichiometry in a RL setting. The models correctly identify low energy molecules in the database and produce novel isomers not found in the training set. Finally, we apply the model to larger molecules to show how RL further refines the IL model in domains far from the training data.
34
Martins, Miguel S. E., João M. C. Sousa, and Susana Vieira. "A Systematic Review on Reinforcement Learning for Industrial Combinatorial Optimization Problems." Applied Sciences 15, no. 3 (2025): 1211. https://doi.org/10.3390/app15031211.
Full textAbstract:
This paper presents a systematic review on reinforcement learning approaches for combinatorial optimization problems based on real-world industrial applications. While this topic is increasing in popularity, explicit implementation details are not always available in the literature. The main objective of this paper is characterizing the agent–environment interactions, namely, the state space representation, action space mapping and reward design. Also, the main limitations for practical implementation and the needed future developments are identified. The literature selected covers a wide range of industrial combinatorial optimization problems, found in the IEEE Xplore, Scopus and Web of Science databases. A total of 715 unique papers were extracted from the query. Then, out-of-scope applications, reviews, surveys and papers with insufficient implementation details were removed. This resulted in a total of 298 papers that align with the focus of the review with sufficient implementation details. The state space representation shows the most variety, while the reward design is based on combinations of different modules. The presented studies use a large variety of features and strategies. However, one of the main limitations is that even with state-of-the-art complex models the scalability issues of increasing problem complexity cannot be fully solved. No methods were used to assess risk of biases or automatically synthesize the results.
35
Aribisala, Adetoye Ayokunle, Usama Ali Salahuddin Ghori, and Cristiano A. V. Cavalcante. "The Application of Reinforcement Learning to Pumps—A Systematic Literature Review." Machines 13, no. 6 (2025): 480. https://doi.org/10.3390/machines13060480.
Full textAbstract:
Reinforcement learning, a subset of machine learning in the field of engineering informatics, has revolutionized the decision-making and control of industrial pumping systems. A set of 100 peer-reviewed papers on the application of reinforcement learning to pumps, sourced from the Scopus database, were selected. The selected papers were subjected to bibliometric and content analyses. The existing approaches in use, the challenges that have been experienced, and the future trends in the field are all explored in depth. The majority of the studies focused on developing a control system for pumps, with heat pumps being the most prevalent type, while also considering their economic impact on energy consumption in the industry. Future trends include the use of Internet-of-Things sensors on pumps, a hybrid of model-free and model-based reinforcement learning algorithms, and the development of “weighted” models. Finally, ideas for developing a practical reinforcement learning-bundled software for the industry are presented to create an effective system that includes a comprehensive reinforcement learning framework application.
36
Al-Nawashi, Malek M., Obaida M. Al-hazaimeh, Tahat M. Nedal, Nasr Gharaibeh, Waleed A. Abu-Ain, and Tarik Abu-Ain. "Deep Reinforcement Learning-Based Framework for Enhancing Cybersecurity." International Journal of Interactive Mobile Technologies (iJIM) 19, no. 03 (2025): 170–90. https://doi.org/10.3991/ijim.v19i03.50727.
Full textAbstract:
The detection of cyberattacks has been increasingly emphasized in recent years, focusing on both infrastructure and people. Conventional security measures such as intrusion detection, firewalls, and encryption are insufficient in protecting cyber systems against growing and changing threats. In order to address this problem, scholars have explored reinforcement learning (i.e., RL) as a potential solution for intricate cybersecurity decision-making difficulties. Nevertheless, the use of RL faces several obstacles, including dynamic attack scenarios, insufficient training data, and the challenge of replicating real-world complexities. This study presents a novel framework that uses deep reinforcement learning (i.e., DRL) to simulate harmful cyberattacks and improve cybersecurity. This study presents an agent-based framework that is capable of ongoing learning and adaptation in a dynamic network security environment. The agent determines the optimal course of action by considering the current state of the network and the rewards it receives for its decisions. The CIC-IDS-2018 database, constructed using Python 3.7 programming, was used. The conducted studies yielded outstanding results, with a detection accuracy of 98.82% achieved for the CIC-IDS-2018 database in cyberattack classification.
37
Bacha, Anis Mahmoud, Razika Boushaki Zamoum, and Fadhila Lachekhab. "Machine Learning Paradigms for UAV Path Planning: Review and Challenges." Journal of Robotics and Control (JRC) 6, no. 1 (2025): 215–33. https://doi.org/10.18196/jrc.v6i1.24097.
Full textAbstract:
Path planning is a crucial step in robotic navigation to satisfy: tasks safety, efficiency requirements and adapt to the complexity of environments. Path planning problem is particularly critical for Unmanned Aerial Vehicles (UAV), being increasingly involved within important tasks in diverse military and civil fields such as: inspection, search and rescue and communication, taking advantage of their high flexibility, maneuverability and cost-effective solutions. This continuous growth made the solution of UAV path planning problem an interesting research topic in recent years. In this scope, machine learning algorithms were a promising tool due to their continuous data-driven selfimprovement to adapt with the high dynamicity of environments where conventional programming fails. This paper provides a review on recent developments in machine learning-based UAV path planning issued from credible databases like: IEEE, Elsevier, Springer Links and MDPI. The main contribution of this paper is to delve through these recent works providing a taxonomy of algorithms into the fundamental paradigms: supervised, unsupervised and reinforcement, evaluating their efficiency and limitations under distinct scenarios. Despite the relative generalization of deep reinforcement learning to different environments, this study highlighted some active challenges about computational cost and real-time applications that remain open.
38
Kim, Hak Gu, Minho Park, Sangmin Lee, Seongyeop Kim, and Yong Man Ro. "Visual Comfort Aware-Reinforcement Learning for Depth Adjustment of Stereoscopic 3D Images." Proceedings of the AAAI Conference on Artificial Intelligence 35, no. 2 (2021): 1762–70. http://dx.doi.org/10.1609/aaai.v35i2.16270.
Full textAbstract:
Depth adjustment aims to enhance the visual experience of stereoscopic 3D (S3D) images, which accompanied with improving visual comfort and depth perception. For a human expert, the depth adjustment procedure is a sequence of iterative decision making. The human expert iteratively adjusted the depth until he is satisfied with the both levels of visual comfort and the perceived depth. In this work, we present a novel deep reinforcement learning (DRL)-based approach for depth adjustment named VCA-RL (Visual Comfort Aware Reinforcement Learning) to explicitly model human sequential decision making in depth editing operations. We formulate the depth adjustment process as a Markov decision process where actions are defined as camera movement operations to control the distance between the left and right cameras. Our agent is trained based on the guidance of an objective visual comfort assessment metric to learn the optimal sequence of camera movement actions in terms of perceptual aspects in stereoscopic viewing. With extensive experiments and user studies, we show the effectiveness of our VCA-RL model on three different S3D databases.
39
Li, Zhongliang, Yaofeng Tu, and Zongmin Ma. "A Sample-Aware Database Tuning System With Deep Reinforcement Learning." Journal of Database Management 35, no. 1 (2023): 1–25. http://dx.doi.org/10.4018/jdm.333519.
Full textAbstract:
Based on the relationship between client load and overall system performance, the authors propose a sample-aware deep deterministic policy gradient model. Specifically, they improve sample quality by filtering out sample noise caused by the fluctuations of client load, which accelerates the model convergence speed of the intelligent tuning system and improves the tuning effect. Also, the hardware resources and client load consumed by the database in the working process are added to the model for training. This can enhance the performance characterization ability of the model and improve the recommended parameters of the algorithm. Meanwhile, they propose an improved closed-loop distributed comprehensive training architecture of online and offline training to quickly obtain high-quality samples and improve the efficiency of parameter tuning. Experimental results show that the configuration parameters can make the performance of the database system better and shorten the tuning time.
40
Tanwir, Ahmad, Ashraf Adnan, Truscan Dragos, Domi Andi, and Porres Ivan. "Using Deep Reinforcement Learning for Exploratory Performance Testing of Software Systems With Multi-Dimensional Input Spaces." IEEEE Access 8 (October 26, 2020): 195000–195020. https://doi.org/10.1109/ACCESS.2020.3033888.
Full textAbstract:
During exploratory performance testing, software testers evaluate the performance of a software system with different input combinations in order to identify combinations that cause performance problems in the system under test. Performance problems such as low throughput, high response times, hangs, or crashes in software applications have an adverse effect on the customer’s satisfaction. Since many of today’s large-scale, complex software systems (e.g., eCommerce applications, databases, web servers) exhibit very large multi-dimensional input spaces with many input parameters and large ranges, it has become costly and inefficient to explore all possible combinations of inputs in order to detect performance problems. In order to address this issue, we introduce a method for identifying input combinations that trigger performance problems in the software system under test. Our method, under the name of iPerfXRL, employs deep reinforcement learning in order to explore a given large multi-dimensional input space efficiently. The main benefit of the approach is that, during the exploration process, it learns and recognizes the problematic regions of the input space that have a higher chance of triggering performance problems. It concentrates the search in those problematic regions to find as many input combinations as possible that can trigger performance problems while executing a limited number of input combinations against the system. In addition, our approach does not require prior domain knowledge or access to the source code of the system. Therefore, it can be applied to any software system where we can interactively execute different input combinations while monitoring their performance impact on the system. We implement iPerfXRL on top of the Soft Actor-Critic algorithm. We evaluate empirically the efficiency and effectiveness of our approach against alternative state-of-the-art approaches. Our results show that iPerfXRL accurately identifies the problematic regions of the input space and finds up to 9 times more input combinations that trigger performance problems on the system under test than the alternative approaches.
41
Wang, Sixuan, Cailong Ma, Wenhu Wang, et al. "Prediction of Failure Modes and Minimum Characteristic Value of Transverse Reinforcement of RC Beams Based on Interpretable Machine Learning." Buildings 13, no. 2 (2023): 469. http://dx.doi.org/10.3390/buildings13020469.
Full textAbstract:
Shear failure of reinforced concrete (RC) beams is a form of brittle failure and has always been a concern. This study adopted the interpretable machine-learning technique to predict failure modes and identify the boundary value between different failure modes to avoid diagonal splitting failure. An experimental database consisting of 295 RC beams with or without transverse reinforcements was established. Two features were constructed to reflect the design characteristics of RC beams, namely, the shear–span ratio and the characteristic value of transverse reinforcement. The characteristic value of transverse reinforcement has two forms: (i) λsv,ft=ρstpfsv/ft, from the China design code of GB 50010-2010; and (ii) λsv,fc′=ρstpfsv/fc′0.5, from the America design code of ACI 318-19 and Canada design code of CSA A23.3-14. Six machine-learning models were developed to predict failure modes, and gradient boosting decision tree and extreme gradient boosting are recommended after comparing the prediction performance. Then, shapley additive explanations (SHAP) indicates that the characteristic value of transverse reinforcement has the most significant effect on failure mode, follow by the shear–span ratio. The characteristic value of transverse reinforcement is selected as the form of boundary value. On this basis, an accumulated local effects (ALE) plot describes how this feature affects model prediction and gives the boundary value through numerical simulation, that is, the minimum characteristic value of transverse reinforcement. Compared with the three codes, the suggested value for λsv,fc′,min has higher reliability and security for avoiding diagonal splitting failure. Accordingly, the research approach in this case is feasible and effective, and can be recommended to solve similar tasks.
42
N.Vanitha*1, &. Dr T. Bhuvaneswari2. "SEMANTIC DATA ANONYMIZATION USING REINFORCEMENT LEARNING FOR CLOAKING GRAPH PERCOLATION OF SENSITIVE DATA." GLOBAL JOURNAL OF ENGINEERING SCIENCE AND RESEARCHES 5, no. 12 (2018): 46–54. https://doi.org/10.5281/zenodo.2156480.
Full textAbstract:
In the age of big data, preserving privacy is a challenging problem to tackle, especially when sharing the graph data generated through social network, users need to share for business analytics and social science research purposes. The top methods among privacy preservation techniques are k-anonymity, I-diversity, differential privacy etc., which prevents re-identification of essential structural nodes in the given graph data. Though the privacy models implemented through such methods may not be completely efficient as the attacker might infer the sensitive data if several nodes of graph database comprises of same labels or attributes. Also, these methods modify the edges between nodes which may significantly alter the essential properties of the database. In this study, we present an algorithm to overcome this challenges with the idea of blocking the graph traversal based on the probabilistic logic to forbid graph percolation which in turn is regulated by reinforcement learning method while ensuring the least amount of distortion in graph properties.
43
Montilla, Carlos, Renaud Ansart, Anass Majji, et al. "On Using CFD and Experimental Data to Train an Artificial Neural Network to Reconstruct ECVT Images: Application for Fluidized Bed Reactors." Processes 12, no. 2 (2024): 386. http://dx.doi.org/10.3390/pr12020386.
Full textAbstract:
Electrical capacitance volume tomography (ECVT) is an experimental technique capable of reconstructing 3D solid volume fraction distribution inside a sensing region. This technique has been used in fluidized beds as it allows for accessing data that are very difficult to obtain using other experimental devices. Recently, artificial neural networks have been proposed as a new type of reconstruction algorithm for ECVT devices. One of the main drawbacks of neural networks is that they need a database containing previously reconstructed images to learn from. Previous works have used databases with very simple or limited configurations that might not be well adapted to the complex dynamics of fluidized bed configurations. In this work, we study two different approaches: a supervised learning approach that uses simulated data as a training database and a reinforcement learning approach that relies only on experimental data. Our results show that both techniques can perform as well as the classical algorithms. However, once the neural networks are trained, the reconstruction process is much faster than the classical algorithms.
44
Zhou, Xuanhe, Lianyuan Jin, Ji Sun, et al. "DBMind." Proceedings of the VLDB Endowment 14, no. 12 (2021): 2743–46. http://dx.doi.org/10.14778/3476311.3476334.
Full textAbstract:
We demonstrate a self-driving system DBMind, which provides three autonomous capabilities in database, including self-monitoring, self-diagnosis and self-optimization. First, self-monitoring judiciously collects database metrics and detects anomalies (e.g., slow queries and IO contention), which can profile database status while only slightly affecting system performance (<5%). Then, self-diagnosis utilizes an LSTM model to analyze the root causes of the anomalies and automatically detect root causes from a pre-defined failure hierarchy. Next, self-optimization automatically optimizes the database performance using learning-based techniques, including deep reinforcement learning based knob tuning, reinforcement learning based index selection, and encoder-decoder based view selection. We have implemented DBMind in an open source database openGauss and demonstrated real scenarios.
45
Xiao, Congzhen, Baojuan Qiao, Jianhui Li, Zhiyong Yang, and Jiannan Ding. "Prediction of Transverse Reinforcement of RC Columns Using Machine Learning Techniques." Advances in Civil Engineering 2022 (November 22, 2022): 1–15. http://dx.doi.org/10.1155/2022/2923069.
Full textAbstract:
Transverse reinforcement of reinforced concrete (RC) columns contributes greatly to the ductility deformation capacity of RC structures. The existing models to predict the amount of transverse reinforcement required are all empirical models with low accuracy and large dispersion and have not considered the real ductility demand of individual components. This paper proposes a ductility design method of RC structure based on component drift ratio demand obtained from nonlinear structural dynamic analysis. To establish the best transverse reinforcement ratio prediction model for RC columns, based on an experimental database consisting of 498 columns, 12 machine learning (ML) models are trained. To solve the over-fitting problem caused by the current situation of “few samples and big errors” of the experimental database, feature engineering aiming at dimension reduction is systematically carried out through an iterative process. Through comprehensive performance evaluation on the testing set, an XGBoost model is selected. To interpret the “black box” ML model, the SHAP method and partial dependence plots are used to analyse the correlation between the input parameters and the transverse reinforcement ratio. The interpretation results are consistent with mechanical laws and engineering experience, which prove the reliability of the selected ML model. Compared with two existing empirical models, the proposed XGBoost model shows higher accuracy and smaller deviation. After safety probability analysis, the trained XGBoost model is transformed into C code and integrated into seismic design software for productive practice. An open-source data-driven model to predict the transverse reinforcement ratio required for RC columns is provided worldwide, with the flexibility to account for additional experimental results.
46
Muthukumar, Yogita, and Topalli Krishnakumar. "Innovative Face Anti-Spoofing: A DRL Strategy for Enhanced Security." Journal of Research in Science and Engineering 6, no. 7 (2024): 59–62. http://dx.doi.org/10.53469/jrse.2024.06(07).10.
Full textAbstract:
Inspired by human perception, this framework first looks at the presented face example globally. This initial global observation provides a holistic understanding of the input image. Subsequently, the framework carefully observes local regions to gather more discriminative information related to face spoofing. To model the behavior of exploring face - spoofing - related information from image sub - patches, deep reinforcement learning is employed. This suggests that the model learns to make decisions on where to focus its attention within the image to gather relevant information. A recurrent mechanism, implemented with an RNN, is introduced to sequentially learn representations of local information from the explored sub - patches. This sequential learning allows the model to capture temporal dependencies in the data. For the final classification step, the framework fuses the locally learned information with the globally extracted features from the original input image using a CNN. This fusion of local and global information aims to create a comprehensive representation that enhances the model's ability to distinguish between genuine and spoofed faces. Extensive experiments, including ablation studies and visualization analysis, are conducted to evaluate the proposed framework. The experiments are carried out on various public databases to ensure the generalizability of the method. The experiment results indicate that your proposed method achieves state - of - the - art performance across different scenarios, demonstrating its effectiveness in the task of face anti - spoofing. In summary, your framework leverages a combination of deep learning techniques, reinforcement learning, and sequential information processing to effectively address the face anti - spoofing problem. The emphasis on both global and local information, as well as the integration of deep reinforcement learning and recurrent mechanisms.
47
Et.al, Susmita Goswami. "A Survey on Human Detection using Reinforcement Learning." Turkish Journal of Computer and Mathematics Education (TURCOMAT) 12, no. 6 (2021): 123–26. http://dx.doi.org/10.17762/turcomat.v12i6.1276.
Full textAbstract:
Human Detection - technology related to computer vision and image processing work by finding people in digital photos and videos and surveillance videos that are part of the observation. Single Shot Detector (SSD) is a deep learning method and is one of the fastest algorithms that use a single convolutional neural network to detect objects involving humans, cats, dogs, etc., and extract feature maps to classify the candidate object in the respective images. The advantage that SSD has is that it is quick to detect and has high accuracy in a given situation compared to regional suggested networks with smaller resolution images and smaller objects. However, it is still somewhat lagging in detecting large objects in larger images as compared to other algorithms that have been used to achieve better accuracy. It is a simple, end-to-end solution for a single network, and detection and extraction are done with one step forward single pass. The proposed system is to use the Optimized-SSD algorithm to detect human accuracy in the proposed database with good accuracy which will be the task of learning to increase SSD capacity as a detection system.
48
Yousra, Dahdouh, Anouar Boudhir Abdelhakim, and Ben Ahmed Mohamed. "A New Approach using Deep Learning and Reinforcement Learning in HealthCare." International journal of electrical and computer engineering systems 14, no. 5 (2023): 557–64. http://dx.doi.org/10.32985/ijeces.14.5.7.
Full textAbstract:
Nowadays, skin cancer is one of the most important problems faced by the world, due especially to the rapid development of skin cells and excessive exposure to UV rays. Therefore, early detection at an early stage employing advanced automated systems based on AI algorithms plays a major job in order to effectively identifying and detecting the disease, reducing patient health and financial burdens, and stopping its spread in the skin. In this context, several early skin cancer detection approaches and models have been presented throughout the last few decades to improve the rate of skin cancer detection using dermoscopic images. This work proposed a model that can help dermatologists to know and detect skin cancer in just a few seconds. This model combined the merits of two major artificial intelligence algorithms: Deep Learning and Reinforcement Learning following the great success we achieved in the classification and recognition of images and especially in the medical sector. This research included four main steps. Firstly, the pre-processing techniques were applied to improve the accuracy, quality, and consistency of a dataset. The input dermoscopic images were obtained from the HAM10000 database. Then, the watershed algorithm was used for the segmentation process performed to extract the affected area. After that, the deep convolutional neural network (CNN) was utilized to classify the skin cancer into seven types: actinic keratosis, basal cell carcinoma, benign keratosis, dermatofibroma melanocytic nevi, melanoma vascular skin lesions. Finally, in regards to the reinforcement learning part, the Deep Q_Learning algorithm was utilized to train and retrain our model until we found the best result. The accuracy metric was utilized to evaluate the efficacy and performance of the proposed method, which achieved a high accuracy of 80%. Furthermore, the experimental results demonstrate how reinforcement learning can be effectively combined with deep learning for skin cancer classification tasks.
49
Zhu, Xintong, Zongpu Jia, Xiaoyan Pang, and Shan Zhao. "Joint Optimization of Task Caching and Computation Offloading for Multiuser Multitasking in Mobile Edge Computing." Electronics 13, no. 2 (2024): 389. http://dx.doi.org/10.3390/electronics13020389.
Full textAbstract:
Mobile edge computing extends the capabilities of the cloud to the edge to meet the latency performance required by new types of applications. Task caching reduces network energy consumption by caching task applications and associated databases in advance on edge devices. However, determining an effective caching strategy is crucial since users generate numerous repetitive tasks, but edge devices and storage resources are limited. We aimed to address the problem of highly coupled decision variables in dynamic task caching and computational offloading for multiuser multitasking in mobile edge computing systems. This paper presents a joint computation and caching framework with the aim of minimizing delays and energy expenditure for mobile users and transforming the problem into a form of reinforcement learning. Based on this, an improved deep reinforcement learning algorithm, P-DDPG, is proposed to achieve efficient computation offloading and task caching decisions for mobile users. The algorithm integrates a deep and deterministic policy grading and a prioritized empirical replay mechanism to reduce system costs. The simulations show that the designed algorithm performs better in terms of task latencies and lower computing power consumption.
50
Rafi, Aisha, Ambreen Ansar, and Muneeza Amir Sami. "The Implication of Positive Reinforcement Strategy in dealing with Disruptive Behaviour in the Classroom: A Scoping Review." Journal of Rawalpindi Medical College 24, no. 2 (2020): 173–79. http://dx.doi.org/10.37939/jrmc.v24i2.1190.
Full textAbstract:
The scoping review study was carried out from January 18, 2019, to February 18, 2019, by following the Arksey and O'Malley method of scoping review. An extensive search in the bibliographic databases, PubMed, ERIC, and Google scholar for the gray literature was done. The search was narrowed by a set of inclusion and exclusion criteria. The studies included in the literature search were sort by the PRISMA flow chart. The selected studies address the use of a positive reinforcement strategy to manage disruptive behavior in the classroom. The positive reinforcement strategies identified were praise (41%), feedback (33%), and other classroom management studies (25%). Skinner's operant learning principle has a classroom implication for increasing the likelihood of the desired behavior. The results of the review can be used to implement evidence-based practice and policy regarding improving the desired behavior in the classroom.