Percorrer por autor "Bernardo, Marco V."
A mostrar 1 - 6 de 6
Resultados por página
Opções de ordenação
- Adaptive and Scalable Database Management with Machine Learning Integration: A PostgreSQL Case StudyPublication . Abbasi, Maryam; Bernardo, Marco V.; Vaz, Paulo; Silva, José; Martins, Pedro; ANTUNES VAZ, PAULO JOAQUIM; Silva, JoséThe increasing complexity of managing modern database systems, particularly in terms of optimizing query performance for large datasets, presents significant challenges that traditional methods often fail to address. This paper proposes a comprehensive framework for integrating advanced machine learning (ML) models within the architecture of a database management system (DBMS), with a specific focus on PostgreSQL. Our approach leverages a combination of supervised and unsupervised learning techniques to predict query execution times, optimize performance, and dynamically manage workloads. Unlike existing solutions that address specific optimization tasks in isolation, our framework provides a unified platform that supports real-time model inference and automatic database configuration adjustments based on workload patterns. A key contribution of our work is the integration of ML capabilities directly into the DBMS engine, enabling seamless interaction between the ML models and the query optimization process. This integration allows for the automatic retraining of models and dynamic workload management, resulting in substantial improvements in both query response times and overall system throughput. Our evaluations using the Transaction Processing Performance Council Decision Support (TPC-DS) benchmark dataset at scale factors of 100 GB, 1 TB, and 10 TB demonstrate a reduction of up to 42% in query execution times and a 74% improvement in throughput compared with traditional approaches. Additionally, we address challenges such as potential conflicts in tuning recommendations and the performance overhead associated with ML integration, providing insights for future research directions. This study is motivated by the need for autonomous tuning mechanisms to manage large-scale, hetero geneous workloads while answering key research questions, such as the following: (1) How can machine learning models be integrated into a DBMS to improve query optimization and workload management? (2) What performance improvements can be achieved through dynamic configuration tuning based on real-time workload patterns? Our results suggest that the proposed framework significantly reduces the need for manual database administration while effectively adapting to evolving workloads, offering a robust solution for modern large-scale data environments.
- An Advertising Real-Time Intelligent and Scalable Framework for Profiling Customers EmotionsPublication . Alves, Leandro; Oliveira, Pedro; Henriques, João; Bernardo, Marco V.; Wanzeller, Cristina; Caldeira, FilipeThe advertising industry is continuously looking up for effective ways to communicate to customers to impact their purchasing. Usually, profiling them is a time-consuming offline activity. Therefore, it becomes necessary to reduce costs and time to address consumers’ needs. This work proposes a scalable framework enabled by a Machine Learning (ML) model to profile customers to identify their emotions to help to drive campaigns. A multi-platform mobile application continuously profiles consumers crossing the front stores. Profiling customers according to their age and hair color, the color of their eyes, and emotions (e.g. happiness, sadness, disgust, fear) will help companies to make the most suitable advertisement (e.g. to predict whether the advertising tones on the front store are the adequate ones). All that data are made available in web portal dashboards, wherein subscribers can take their analysis. Such results from the analysis data help them to identify tendencies regarding the culture and age, and drive companies to fit front stores accordingly (e.g. to discover the right tones for the season). This framework can help to develop new innovative cost-effective business models at scale by driving in real-time the advertisements to a huge number of consumers to maximize their impact and centralizing the data collected from a large number of stores to design future campaigns.
- A Cost-Effective Framework for Monitoring Disaster Recovery InfrastructuresPublication . Rocha, Júlio; Lucas, Marco; Figueiredo, Ricardo; Henriques, João; Bernardo, Marco V.; Wanzeller, Cristina; Caldeira, FilipeKeeping Disaster Recovery Infrastructures (DRI) operational is vital in case of incidents. Notwithstanding, continuously monitoring them keeps a costly activity. Therefore, it is essential to have cost-effective solutions while maintaining a continuous. In that aim, this work proposes a cost-effective framework for monitoring DRI supported by an Internet of Things (IoT) device collecting data from their sensors strategically installed in the facilities to protect. In case of incidents, the framework triggers the alerts. A mobile application presents graphically, in real-time, the collected data from sensors. The physical experimentation and achieved results demonstrate the effectiveness of the framework to protect DRI. The proposed framework enabled by software to the different layers (IoT, middleware, and mobile application), and the hardware with its schematic, can help to develop innovative business models for managing DRI. The prototype of the framework produced a large dataset that can help future research on finding anomalies.
- Optimizing Database Performance in Complex Event Processing through Indexing StrategiesPublication . Abbasi, Maryam; Bernardo, Marco V.; ANTUNES VAZ, PAULO JOAQUIM; Silva, José; Martins, PedroComplex event processing (CEP) systems have gained significant importance in various domains, such as finance, logistics, and security, where the real-time analysis of event streams is crucial. However, as the volume and complexity of event data continue to grow, optimizing the performance of CEP systems becomes a critical challenge. This paper investigates the impact of indexing strategies on the performance of databases handling complex event processing. We propose a novel indexing technique, called Hierarchical Temporal Indexing (HTI), specifically designed for the efficient processing of complex event queries. HTI leverages the temporal nature of event data and employs a multi-level indexing approach to optimize query execution. By combining temporal indexing with spatial- and attribute-based indexing, HTI aims to accelerate the retrieval and processing of relevant events, thereby improving overall query performance. In this study, we evaluate the effectiveness of HTI by implementing complex event queries on various CEP systems with different indexing strategies. We conduct a comprehensive performance analysis, measuring the query execution times and resource utilization (CPU, memory, etc.), and analyzing the execution plans and query optimization techniques employed by each system. Our experimental results demonstrate that the proposed HTI indexing strategy outperforms traditional indexing approaches, particularly for complex event queries involving temporal constraints and multi-dimensional event attributes. We provide insights into the strengths and weaknesses of each indexing strategy, identifying the factors that influence performance, such as data volume, query complexity, and event characteristics. Furthermore, we discuss the implications of our findings for the design and optimization of CEP systems, offering recommendations for indexing strategy selection based on the specific requirements and workload characteristics. Finally, we outline the potential limitations of our study and suggest future research directions in this domain.
- Playfulness and communication for children with autism spectrum disorder: guidelines for a videogamePublication . Alves, Valter; P. Duarte, Rui; Fonseca, F.; Bernardo, Marco V.; Barreto, Pedro; Silva, C.E.; Felizardo, Sara; Videira, I.; Matos, A.; Henriques, C.Autism Spectrum Disorder (ASD) affects sensory processing and conditions the development of communication skills and social interaction. Literature shows that children with ASD are fond of technologies and videogames in particular. The predictable and constant behaviour of technological components, the visual appeal, and the challenges are often highly appreciated (Zakari et al., 2014). Besides, videogames typically allow users to play alone, which is adequate to the profile of such an audience. The use of videogames by autistic children has shown to be relevant, and studies are evidencing gains in several areas (Malinverni et al., 2017; Hedges et al., 2018; Ng & Pera, 2018; Valencia et al., 2019; Baldassarri et al., 2020). Even so, existing solutions that were specifically developed for this audience have assumedly pedagogical goals, which systematically compromises their ludic dimension (Hirsh-Pasek et al., 2015). A study is being developed to design and implement a videogame that focuses on pure playfulness and provides an advantage to players who adopt specific strategies that rely on communicating with other players. This videogame is conceived for both intervention and research. The game mechanics explores the flow theory (Csikszentmihalyi, 2011), in order to dynamically adapt the challenges to the skills shown by the players, trying not to let them reach states of anxiety (due to lack of skills) or boredom (due to lack of challenge). This reasoning is extended to motor skills, as autistic people may have difficulties. In this context, it is important to clarify that the study is limited to children with ASD without associated intellectual development disorders that compromise the viability of the very act of playing. Also instrumental to the project, different scenarios are designed so that researchers can observe and collect scientific data, aiming at better understanding the related issues. Such scenarios support the analysis of the influence of physical proximity between the players, their prior level of familiarity, and their relative communicational abilities. Also under analysis is the impact of repeating the experience, both in terms of in-game performance and regarding a possible contribution to the relationship between participants and, eventually, with third parties. The core of this paper is the presentation of the design guidelines that were created to support the videogame. The guidelines result from the contributions of experts, organised according to a Delphi technique (Green, 2014). The set of experts cover the fields of ASD, game design, special education, occupational therapy, rehabilitation, and educational research. Also included is the description of the videogame development, which resorts to agile methodologies, allowing for an incremental and iterative production, supported by recurrent tests and consistently validated according to the intended objectives.
- Revisiting Database Indexing for Parallel and Accelerated Computing: A Comprehensive Study and Novel ApproachesPublication . Abbasi, Maryam; Bernardo, Marco V.; ANTUNES VAZ, PAULO JOAQUIM; Silva, José; Martins, PedroWhile 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.