Leon Tabaro, J. M. V. Kinani, A. J. Rosales-Silva, J. Salgado-Ramírez, Dante Mújica-Vargas, P. J. Escamilla-Ambrosio, Eduardo Ramos-Díaz
In this work, we explore the application of deep reinforcement learning (DRL) to algorithmic trading. While algorithmic trading is focused on using computer algorithms to automate a predefined trading strategy, in this work, we train a Double Deep Q-Network (DDQN) agent to learn its own optimal trading policy, with the goal of maximising returns whilst managing risk. In this study, we extended our approach by augmenting the Markov Decision Process (MDP) states with sentiment analysis of financial statements, through which the agent achieved up to a 70% increase in the cumulative reward over the testing period and an increase in the Calmar ratio from 0.9 to 1.3. The experimental results also showed that the DDQN agent’s trading strategy was able to consistently outperform the benchmark set by the buy-and-hold strategy. Additionally, we further investigated the impact of the length of the window of past market data that the agent considers when deciding on the best trading action to take. The results of this study have validated DRL’s ability to find effective solutions and its importance in studying the behaviour of agents in markets. This work serves to provide future researchers with a foundation to develop more advanced and adaptive DRL-based trading systems.
{"title":"Algorithmic Trading Using Double Deep Q-Networks and Sentiment Analysis","authors":"Leon Tabaro, J. M. V. Kinani, A. J. Rosales-Silva, J. Salgado-Ramírez, Dante Mújica-Vargas, P. J. Escamilla-Ambrosio, Eduardo Ramos-Díaz","doi":"10.3390/info15080473","DOIUrl":"https://doi.org/10.3390/info15080473","url":null,"abstract":"In this work, we explore the application of deep reinforcement learning (DRL) to algorithmic trading. While algorithmic trading is focused on using computer algorithms to automate a predefined trading strategy, in this work, we train a Double Deep Q-Network (DDQN) agent to learn its own optimal trading policy, with the goal of maximising returns whilst managing risk. In this study, we extended our approach by augmenting the Markov Decision Process (MDP) states with sentiment analysis of financial statements, through which the agent achieved up to a 70% increase in the cumulative reward over the testing period and an increase in the Calmar ratio from 0.9 to 1.3. The experimental results also showed that the DDQN agent’s trading strategy was able to consistently outperform the benchmark set by the buy-and-hold strategy. Additionally, we further investigated the impact of the length of the window of past market data that the agent considers when deciding on the best trading action to take. The results of this study have validated DRL’s ability to find effective solutions and its importance in studying the behaviour of agents in markets. This work serves to provide future researchers with a foundation to develop more advanced and adaptive DRL-based trading systems.","PeriodicalId":510156,"journal":{"name":"Information","volume":"32 8","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141923347","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Jan Gasienica-Józkowy, Bogusław Cyganek, Mateusz Knapik, Szymon Glogowski, Łukasz Przebinda
Accurately estimating the absolute distance and height of objects in open areas is quite challenging, especially when based solely on single images. In this paper, we tackle these issues and propose a new method that blends traditional computer vision techniques with advanced neural network-based solutions. Our approach combines object detection and segmentation, monocular depth estimation, and homography-based mapping to provide precise and efficient measurements of absolute height and distance. This solution is implemented on an edge device, allowing for real-time data processing using both visual and thermal data sources. Experimental tests on a height estimation dataset we created show an accuracy of 98.86%, confirming the effectiveness of our method.
{"title":"Deep Learning-Based Monocular Estimation of Distance and Height for Edge Devices","authors":"Jan Gasienica-Józkowy, Bogusław Cyganek, Mateusz Knapik, Szymon Glogowski, Łukasz Przebinda","doi":"10.3390/info15080474","DOIUrl":"https://doi.org/10.3390/info15080474","url":null,"abstract":"Accurately estimating the absolute distance and height of objects in open areas is quite challenging, especially when based solely on single images. In this paper, we tackle these issues and propose a new method that blends traditional computer vision techniques with advanced neural network-based solutions. Our approach combines object detection and segmentation, monocular depth estimation, and homography-based mapping to provide precise and efficient measurements of absolute height and distance. This solution is implemented on an edge device, allowing for real-time data processing using both visual and thermal data sources. Experimental tests on a height estimation dataset we created show an accuracy of 98.86%, confirming the effectiveness of our method.","PeriodicalId":510156,"journal":{"name":"Information","volume":"69 13","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141922518","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Traditional frame-based cameras, despite their effectiveness and usage in computer vision, exhibit limitations such as high latency, low dynamic range, high power consumption, and motion blur. For two decades, researchers have explored neuromorphic cameras, which operate differently from traditional frame-based types, mimicking biological vision systems for enhanced data acquisition and spatio-temporal resolution. Each pixel asynchronously captures intensity changes in the scene above certain user-defined thresholds, and streams of events are captured. However, the distinct characteristics of these sensors mean that traditional computer vision methods are not directly applicable, necessitating the investigation of new approaches before being applied in real applications. This work aims to fill existing gaps in the literature by providing a survey and a discussion centered on the different application domains, differentiating between computer vision problems and whether solutions are better suited for or have been applied to a specific field. Moreover, an extensive discussion highlights the major achievements and challenges, in addition to the unique characteristics, of each application field.
{"title":"An Application-Driven Survey on Event-Based Neuromorphic Computer Vision","authors":"Dario Cazzato, Flavio Bono","doi":"10.3390/info15080472","DOIUrl":"https://doi.org/10.3390/info15080472","url":null,"abstract":"Traditional frame-based cameras, despite their effectiveness and usage in computer vision, exhibit limitations such as high latency, low dynamic range, high power consumption, and motion blur. For two decades, researchers have explored neuromorphic cameras, which operate differently from traditional frame-based types, mimicking biological vision systems for enhanced data acquisition and spatio-temporal resolution. Each pixel asynchronously captures intensity changes in the scene above certain user-defined thresholds, and streams of events are captured. However, the distinct characteristics of these sensors mean that traditional computer vision methods are not directly applicable, necessitating the investigation of new approaches before being applied in real applications. This work aims to fill existing gaps in the literature by providing a survey and a discussion centered on the different application domains, differentiating between computer vision problems and whether solutions are better suited for or have been applied to a specific field. Moreover, an extensive discussion highlights the major achievements and challenges, in addition to the unique characteristics, of each application field.","PeriodicalId":510156,"journal":{"name":"Information","volume":"4 17","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-08-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141921549","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Methods for evaluating the fluctuation of texture patterns that are essentially regular have been proposed in the past, but the best method has not been determined. Here, as an attempt at this, we propose a method that applies AI technology (learning EfficientNet, which is widely used as a classification problem solving method) to determine when the fluctuation exceeds the tolerable limit and what the acceptable range is. We also apply this to clarify the tolerable limit of fluctuation in the “Kurume Kasuri” pattern, which is unique to the Chikugo region of Japan, and devise a method to evaluate the fluctuation in real time when weaving the Kasuri and keep it within the acceptable range. This study proposes a method for maintaining a unique faded pattern of woven textiles by utilizing EfficientNet for classification, fine-tuned with Optuna, and LightGBM for predicting subtle misalignments. Our experiments show that EfficientNet achieves high performance in classifying the quality of unique faded patterns in woven textiles. Additionally, LightGBM demonstrates near-perfect accuracy in predicting subtle misalignments within the acceptable range for high-quality faded patterns by controlling the weaving thread tension. Consequently, this method effectively maintains the quality of Kurume Kasuri patterns within the desired criteria.
{"title":"A Method for Maintaining a Unique Kurume Kasuri Pattern of Woven Textile Classified by EfficientNet by Means of LightGBM-Based Prediction of Misalignments","authors":"Kohei Arai, Jin Shimazoe, Mariko Oda","doi":"10.3390/info15080434","DOIUrl":"https://doi.org/10.3390/info15080434","url":null,"abstract":"Methods for evaluating the fluctuation of texture patterns that are essentially regular have been proposed in the past, but the best method has not been determined. Here, as an attempt at this, we propose a method that applies AI technology (learning EfficientNet, which is widely used as a classification problem solving method) to determine when the fluctuation exceeds the tolerable limit and what the acceptable range is. We also apply this to clarify the tolerable limit of fluctuation in the “Kurume Kasuri” pattern, which is unique to the Chikugo region of Japan, and devise a method to evaluate the fluctuation in real time when weaving the Kasuri and keep it within the acceptable range. This study proposes a method for maintaining a unique faded pattern of woven textiles by utilizing EfficientNet for classification, fine-tuned with Optuna, and LightGBM for predicting subtle misalignments. Our experiments show that EfficientNet achieves high performance in classifying the quality of unique faded patterns in woven textiles. Additionally, LightGBM demonstrates near-perfect accuracy in predicting subtle misalignments within the acceptable range for high-quality faded patterns by controlling the weaving thread tension. Consequently, this method effectively maintains the quality of Kurume Kasuri patterns within the desired criteria.","PeriodicalId":510156,"journal":{"name":"Information","volume":"23 18","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141800723","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Knowledge representation models that aim to present data in a structured and comprehensible manner have gained popularity as a research focus in the pursuit of achieving human-level intelligence. Humans possess the ability to understand, reason and interpret knowledge. They acquire knowledge through their experiences and utilize it to carry out various actions in the real world. Similarly, machines can also perform these tasks, a process known as knowledge representation and reasoning. In this survey, we present a thorough analysis of knowledge representation models and their crucial role in information management within the healthcare domain. We provide an overview of various models, including ontologies, first-order logic and rule-based systems. We classify four knowledge representation models based on their type, such as graphical, mathematical and other types. We compare these models based on four criteria: heterogeneity, interpretability, scalability and reasoning in order to determine the most suitable model that addresses healthcare challenges and achieves a high level of satisfaction.
{"title":"Survey on Knowledge Representation Models in Healthcare","authors":"Batoul Msheik, Mehdi Adda, H. Mcheick, M. Dbouk","doi":"10.3390/info15080435","DOIUrl":"https://doi.org/10.3390/info15080435","url":null,"abstract":"Knowledge representation models that aim to present data in a structured and comprehensible manner have gained popularity as a research focus in the pursuit of achieving human-level intelligence. Humans possess the ability to understand, reason and interpret knowledge. They acquire knowledge through their experiences and utilize it to carry out various actions in the real world. Similarly, machines can also perform these tasks, a process known as knowledge representation and reasoning. In this survey, we present a thorough analysis of knowledge representation models and their crucial role in information management within the healthcare domain. We provide an overview of various models, including ontologies, first-order logic and rule-based systems. We classify four knowledge representation models based on their type, such as graphical, mathematical and other types. We compare these models based on four criteria: heterogeneity, interpretability, scalability and reasoning in order to determine the most suitable model that addresses healthcare challenges and achieves a high level of satisfaction.","PeriodicalId":510156,"journal":{"name":"Information","volume":"43 41","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-26","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141800055","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
In the context of global economic digitalization, financial information is highly susceptible to internet financial public opinion due to the overwhelming and misleading nature of information on internet platforms. This paper delves into the core entities in the diffusion process of internet financial public opinions, including financial institutions, governments, media, and investors, and models the behavioral characteristics of these entities in the diffusion process. On this basis, we comprehensively use the multi-agent model and the SIR model to construct a dynamic evolution model of internet financial public opinion. We conduct a simulation analysis of the impact effects and interaction mechanisms of multi-agent behaviors in the financial market on the evolution of internet financial public opinion. The research results are as follows. Firstly, the financial institutions’ digitalization levels, government guidance, and the media authority positively promote the diffusion of internet financial public opinion. Secondly, the improvement of investors’ financial literacy can inhibit the diffusion of internet financial public opinion. Thirdly, under the interaction of multi-agent behaviors in the financial market, the effects of financial institutions’ digitalization level and investors’ financial literacy are more significant, while the effects of government guidance and media authority tend to converge.
在全球经济数字化的背景下，由于互联网平台信息铺天盖地、误导性强，金融信息极易受到互联网金融舆情的影响。本文深入研究了互联网金融舆情扩散过程中的核心主体，包括金融机构、政府、媒体和投资者，并对这些主体在扩散过程中的行为特征进行了建模。在此基础上，综合运用多代理模型和 SIR 模型，构建了互联网金融舆情动态演化模型。我们对金融市场中多主体行为对互联网金融舆情演化的影响效应和互动机制进行了仿真分析。研究成果如下。首先，金融机构的数字化水平、政府引导和媒体权威对互联网金融舆情的扩散具有正向促进作用。第二，投资者金融素养的提升会抑制互联网金融舆情的扩散。第三，在金融市场多主体行为交互作用下，金融机构数字化水平和投资者金融素养的影响更为显著，而政府引导和媒体权威的影响趋于一致。
{"title":"Dynamic Evolution Model of Internet Financial Public Opinion","authors":"Chao Yu, Jianmin He, Qianting Ma, Xinyu Liu","doi":"10.3390/info15080433","DOIUrl":"https://doi.org/10.3390/info15080433","url":null,"abstract":"In the context of global economic digitalization, financial information is highly susceptible to internet financial public opinion due to the overwhelming and misleading nature of information on internet platforms. This paper delves into the core entities in the diffusion process of internet financial public opinions, including financial institutions, governments, media, and investors, and models the behavioral characteristics of these entities in the diffusion process. On this basis, we comprehensively use the multi-agent model and the SIR model to construct a dynamic evolution model of internet financial public opinion. We conduct a simulation analysis of the impact effects and interaction mechanisms of multi-agent behaviors in the financial market on the evolution of internet financial public opinion. The research results are as follows. Firstly, the financial institutions’ digitalization levels, government guidance, and the media authority positively promote the diffusion of internet financial public opinion. Secondly, the improvement of investors’ financial literacy can inhibit the diffusion of internet financial public opinion. Thirdly, under the interaction of multi-agent behaviors in the financial market, the effects of financial institutions’ digitalization level and investors’ financial literacy are more significant, while the effects of government guidance and media authority tend to converge.","PeriodicalId":510156,"journal":{"name":"Information","volume":"22 18","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141803093","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Nurhadhinah Nadiah Ridzuan, Masairol Masri, Muhammad Anshari, Norma Latif Fitriyani, Muhammad Syafrudin
This study examines the applications, benefits, challenges, and ethical considerations of artificial intelligence (AI) in the banking and finance sectors. It reviews current AI regulation and governance frameworks to provide insights for stakeholders navigating AI integration. A descriptive analysis based on a literature review of recent research is conducted, exploring AI applications, benefits, challenges, regulations, and relevant theories. This study identifies key trends and suggests future research directions. The major findings include an overview of AI applications, benefits, challenges, and ethical issues in the banking and finance industries. Recommendations are provided to address these challenges and ethical issues, along with examples of existing regulations and strategies for implementing AI governance frameworks within organizations. This paper highlights innovation, regulation, and ethical issues in relation to AI within the banking and finance sectors. Analyzes the previous literature, and suggests strategies for AI governance framework implementation and future research directions. Innovation in the applications of AI integrates with fintech, such as preventing financial crimes, credit risk assessment, customer service, and investment management. These applications improve decision making and enhance the customer experience, particularly in banks. Existing AI regulations and guidelines include those from Hong Kong SAR, the United States, China, the United Kingdom, the European Union, and Singapore. Challenges include data privacy and security, bias and fairness, accountability and transparency, and the skill gap. Therefore, implementing an AI governance framework requires rules and guidelines to address these issues. This paper makes recommendations for policymakers and suggests practical implications in reference to the ASEAN guidelines for AI development at the national and regional levels. Future research directions, a combination of extended UTAUT, change theory, and institutional theory, as well as the critical success factor, can fill the theoretical gap through mixed-method research. In terms of the population gap can be addressed by research undertaken in a nation where fintech services are projected to be less accepted, such as a developing or Islamic country. In summary, this study presents a novel approach using descriptive analysis, offering four main contributions that make this research novel: (1) the applications of AI in the banking and finance industries, (2) the benefits and challenges of AI adoption in these industries, (3) the current AI regulations and governance, and (4) the types of theories relevant for further research. The research findings are expected to contribute to policy and offer practical implications for fintech development in a country.
{"title":"AI in the Financial Sector: The Line between Innovation, Regulation and Ethical Responsibility","authors":"Nurhadhinah Nadiah Ridzuan, Masairol Masri, Muhammad Anshari, Norma Latif Fitriyani, Muhammad Syafrudin","doi":"10.3390/info15080432","DOIUrl":"https://doi.org/10.3390/info15080432","url":null,"abstract":"This study examines the applications, benefits, challenges, and ethical considerations of artificial intelligence (AI) in the banking and finance sectors. It reviews current AI regulation and governance frameworks to provide insights for stakeholders navigating AI integration. A descriptive analysis based on a literature review of recent research is conducted, exploring AI applications, benefits, challenges, regulations, and relevant theories. This study identifies key trends and suggests future research directions. The major findings include an overview of AI applications, benefits, challenges, and ethical issues in the banking and finance industries. Recommendations are provided to address these challenges and ethical issues, along with examples of existing regulations and strategies for implementing AI governance frameworks within organizations. This paper highlights innovation, regulation, and ethical issues in relation to AI within the banking and finance sectors. Analyzes the previous literature, and suggests strategies for AI governance framework implementation and future research directions. Innovation in the applications of AI integrates with fintech, such as preventing financial crimes, credit risk assessment, customer service, and investment management. These applications improve decision making and enhance the customer experience, particularly in banks. Existing AI regulations and guidelines include those from Hong Kong SAR, the United States, China, the United Kingdom, the European Union, and Singapore. Challenges include data privacy and security, bias and fairness, accountability and transparency, and the skill gap. Therefore, implementing an AI governance framework requires rules and guidelines to address these issues. This paper makes recommendations for policymakers and suggests practical implications in reference to the ASEAN guidelines for AI development at the national and regional levels. Future research directions, a combination of extended UTAUT, change theory, and institutional theory, as well as the critical success factor, can fill the theoretical gap through mixed-method research. In terms of the population gap can be addressed by research undertaken in a nation where fintech services are projected to be less accepted, such as a developing or Islamic country. In summary, this study presents a novel approach using descriptive analysis, offering four main contributions that make this research novel: (1) the applications of AI in the banking and finance industries, (2) the benefits and challenges of AI adoption in these industries, (3) the current AI regulations and governance, and (4) the types of theories relevant for further research. The research findings are expected to contribute to policy and offer practical implications for fintech development in a country.","PeriodicalId":510156,"journal":{"name":"Information","volume":"42 20","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141804016","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Celia Osorio, Noelia Fuster, Wenwen Chen, Yangchongyi Men, Angel A. Juan
This paper explores how the combination of artificial intelligence, simulation, and e-collaborative (AISEC) tools can support accessibility in analytics courses within higher education. In the era of online and blended learning, addressing the diverse needs of students with varying linguistic backgrounds and analytical proficiencies poses a significant challenge. This paper discusses how the combination of AISEC tools can contribute to mitigating barriers to accessibility for students undertaking analytics courses. Through a comprehensive review of existing literature and empirical insights from practical implementations, this paper shows the synergistic benefits of using AISEC tools for facilitating interactive engagement in analytics courses. Furthermore, the manuscript outlines practical strategies and best practices derived from real-world experiences carried out in different universities in Spain, Ireland, and Portugal.
{"title":"Enhancing Accessibility to Analytics Courses in Higher Education through AI, Simulation, and e-Collaborative Tools","authors":"Celia Osorio, Noelia Fuster, Wenwen Chen, Yangchongyi Men, Angel A. Juan","doi":"10.3390/info15080430","DOIUrl":"https://doi.org/10.3390/info15080430","url":null,"abstract":"This paper explores how the combination of artificial intelligence, simulation, and e-collaborative (AISEC) tools can support accessibility in analytics courses within higher education. In the era of online and blended learning, addressing the diverse needs of students with varying linguistic backgrounds and analytical proficiencies poses a significant challenge. This paper discusses how the combination of AISEC tools can contribute to mitigating barriers to accessibility for students undertaking analytics courses. Through a comprehensive review of existing literature and empirical insights from practical implementations, this paper shows the synergistic benefits of using AISEC tools for facilitating interactive engagement in analytics courses. Furthermore, the manuscript outlines practical strategies and best practices derived from real-world experiences carried out in different universities in Spain, Ireland, and Portugal.","PeriodicalId":510156,"journal":{"name":"Information","volume":"32 5","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141803071","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Maryam Abbasi, Marco V. Bernardo, Paulo Váz, J. Silva, Pedro Martins
While the importance of indexing strategies for optimizing query performance in database systems is widely acknowledged, the impact of rapidly evolving hardware architectures on indexing techniques has been an underexplored area. As modern computing systems increasingly leverage parallel processing capabilities, multi-core CPUs, and specialized hardware accelerators, traditional indexing approaches may not fully capitalize on these advancements. This comprehensive experimental study investigates the effects of hardware-conscious indexing strategies tailored for contemporary and emerging hardware platforms. Through rigorous experimentation on a real-world database environment using the industry-standard TPC-H benchmark, this research evaluates the performance implications of indexing techniques specifically designed to exploit parallelism, vectorization, and hardware-accelerated operations. By examining approaches such as cache-conscious B-Tree variants, SIMD-optimized hash indexes, and GPU-accelerated spatial indexing, the study provides valuable insights into the potential performance gains and trade-offs associated with these hardware-aware indexing methods. The findings reveal that hardware-conscious indexing strategies can significantly outperform their traditional counterparts, particularly in data-intensive workloads and large-scale database deployments. Our experiments show improvements ranging from 32.4% to 48.6% in query execution time, depending on the specific technique and hardware configuration. However, the study also highlights the complexity of implementing and tuning these techniques, as they often require intricate code optimizations and a deep understanding of the underlying hardware architecture. Additionally, this research explores the potential of machine learning-based indexing approaches, including reinforcement learning for index selection and neural network-based index advisors. While these techniques show promise, with performance improvements of up to 48.6% in certain scenarios, their effectiveness varies across different query types and data distributions. By offering a comprehensive analysis and practical recommendations, this research contributes to the ongoing pursuit of database performance optimization in the era of heterogeneous computing. The findings inform database administrators, developers, and system architects on effective indexing practices tailored for modern hardware, while also paving the way for future research into adaptive indexing techniques that can dynamically leverage hardware capabilities based on workload characteristics and resource availability.
{"title":"Revisiting Database Indexing for Parallel and Accelerated Computing: A Comprehensive Study and Novel Approaches","authors":"Maryam Abbasi, Marco V. Bernardo, Paulo Váz, J. Silva, Pedro Martins","doi":"10.3390/info15080429","DOIUrl":"https://doi.org/10.3390/info15080429","url":null,"abstract":"While the importance of indexing strategies for optimizing query performance in database systems is widely acknowledged, the impact of rapidly evolving hardware architectures on indexing techniques has been an underexplored area. As modern computing systems increasingly leverage parallel processing capabilities, multi-core CPUs, and specialized hardware accelerators, traditional indexing approaches may not fully capitalize on these advancements. This comprehensive experimental study investigates the effects of hardware-conscious indexing strategies tailored for contemporary and emerging hardware platforms. Through rigorous experimentation on a real-world database environment using the industry-standard TPC-H benchmark, this research evaluates the performance implications of indexing techniques specifically designed to exploit parallelism, vectorization, and hardware-accelerated operations. By examining approaches such as cache-conscious B-Tree variants, SIMD-optimized hash indexes, and GPU-accelerated spatial indexing, the study provides valuable insights into the potential performance gains and trade-offs associated with these hardware-aware indexing methods. The findings reveal that hardware-conscious indexing strategies can significantly outperform their traditional counterparts, particularly in data-intensive workloads and large-scale database deployments. Our experiments show improvements ranging from 32.4% to 48.6% in query execution time, depending on the specific technique and hardware configuration. However, the study also highlights the complexity of implementing and tuning these techniques, as they often require intricate code optimizations and a deep understanding of the underlying hardware architecture. Additionally, this research explores the potential of machine learning-based indexing approaches, including reinforcement learning for index selection and neural network-based index advisors. While these techniques show promise, with performance improvements of up to 48.6% in certain scenarios, their effectiveness varies across different query types and data distributions. By offering a comprehensive analysis and practical recommendations, this research contributes to the ongoing pursuit of database performance optimization in the era of heterogeneous computing. The findings inform database administrators, developers, and system architects on effective indexing practices tailored for modern hardware, while also paving the way for future research into adaptive indexing techniques that can dynamically leverage hardware capabilities based on workload characteristics and resource availability.","PeriodicalId":510156,"journal":{"name":"Information","volume":"86 12","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141807829","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
M. V. Bourganou, Y. Kiouvrekis, Dimitrios C. Chatzopoulos, Sotiris Zikas, A. Katsafadou, Dimitra V. Liagka, N. Vasileiou, G. Fthenakis, D. T. Lianou
The present study is an evaluation of published papers on machine learning as employed in mastitis research. The aim of this study was the quantitative evaluation of the scientific content and the bibliometric details of these papers. In total, 69 papers were found to combine machine learning in mastitis research and were considered in detail. There was a progressive yearly increase in published papers, which originated from 23 countries (mostly from China or the United States of America). Most original articles (n = 59) referred to work involving cattle, relevant to mastitis in individual animals. Most articles described work related to the development and diagnosis of the infection. Fewer articles described work on the antibiotic resistance of pathogens isolated from cases of mastitis and on the treatment of the infection. In most studies (98.5% of published papers), supervised machine learning models were employed. Most frequently, decision trees and support vector machines were employed in the studies described. ‘Machine learning’ and ‘mastitis’ were the most frequently used keywords. The papers were published in 39 journals, with most frequent publications in Computers and Electronics in Agriculture and Journal of Dairy Science. The median number of cited references in the papers was 39 (interquartile range: 31). There were 435 co-authors in the papers (mean: 6.2 per paper, median: 5, min.–max.: 1–93) and 356 individual authors. The median number of citations received by the papers was 4 (min.–max.: 0–70). Most papers (72.5%) were published in open-access mode. This study summarized the characteristics of papers on mastitis and artificial intelligence. Future studies could explore using these methodologies at farm level, and extending them to other animal species, while unsupervised learning techniques might also prove to be useful.
{"title":"Assessment of Published Papers on the Use of Machine Learning in Diagnosis and Treatment of Mastitis","authors":"M. V. Bourganou, Y. Kiouvrekis, Dimitrios C. Chatzopoulos, Sotiris Zikas, A. Katsafadou, Dimitra V. Liagka, N. Vasileiou, G. Fthenakis, D. T. Lianou","doi":"10.3390/info15080428","DOIUrl":"https://doi.org/10.3390/info15080428","url":null,"abstract":"The present study is an evaluation of published papers on machine learning as employed in mastitis research. The aim of this study was the quantitative evaluation of the scientific content and the bibliometric details of these papers. In total, 69 papers were found to combine machine learning in mastitis research and were considered in detail. There was a progressive yearly increase in published papers, which originated from 23 countries (mostly from China or the United States of America). Most original articles (n = 59) referred to work involving cattle, relevant to mastitis in individual animals. Most articles described work related to the development and diagnosis of the infection. Fewer articles described work on the antibiotic resistance of pathogens isolated from cases of mastitis and on the treatment of the infection. In most studies (98.5% of published papers), supervised machine learning models were employed. Most frequently, decision trees and support vector machines were employed in the studies described. ‘Machine learning’ and ‘mastitis’ were the most frequently used keywords. The papers were published in 39 journals, with most frequent publications in Computers and Electronics in Agriculture and Journal of Dairy Science. The median number of cited references in the papers was 39 (interquartile range: 31). There were 435 co-authors in the papers (mean: 6.2 per paper, median: 5, min.–max.: 1–93) and 356 individual authors. The median number of citations received by the papers was 4 (min.–max.: 0–70). Most papers (72.5%) were published in open-access mode. This study summarized the characteristics of papers on mastitis and artificial intelligence. Future studies could explore using these methodologies at farm level, and extending them to other animal species, while unsupervised learning techniques might also prove to be useful.","PeriodicalId":510156,"journal":{"name":"Information","volume":"2 15","pages":""},"PeriodicalIF":0.0,"publicationDate":"2024-07-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"141807482","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：