Distributed Data Sources Research Articles

RNEP: Random Node Entropy Pairing for Efficient Decentralized Training with Non-IID Local Data

The proliferation of edge devices and advancements in Internet of Things technology have created a vast array of distributed data sources, necessitating machine learning models that can operate closer to the point of data generation. Traditional centralized machine learning approaches often struggle with real-time big data applications, such as climate prediction and traffic simulation, owing to high communication costs. In this study, we introduce random node entropy pairing, a novel distributed learning method for artificial neural networks tailored to distributed computing environments. This method reduces communication overhead and addresses data imbalance by enabling nodes to exchange only the weights of their local models with randomly selected peers during each communication round, rather than sharing the entire dataset. Our findings indicate that this approach significantly reduces communication costs while maintaining accuracy, even when learning from non-IID local data. Furthermore, we explored additional learning strategies that enhance system accuracy by leveraging the characteristics of this method. The results demonstrate that random node entropy pairing is an effective and efficient solution for distributed learning in environments where communication costs and data distribution present significant challenges.

A Hierarchical Machine Learning Method for Detection and Visualization of Network Intrusions from Big Data

Machine learning is regarded as an effective approach in network intrusion detection, and has gained significant attention in recent studies. However, few intrusion detection methods have been successfully applied to detect anomalies in large-scale network traffic data, and low explainability of the complex algorithms has caused concerns about fairness and accountability. A further problem is that many intrusion detection systems need to work with distributed data sources in the cloud. In this paper, we propose an intrusion detection method based on distributed computing to learn the latent representations from large-scale network data with lower computation time while improving the intrusion detection accuracy. Our proposed classifier, based on a novel hierarchical algorithm combining adaptability and visualization ability from a self-structured unsupervised learning algorithm and achieving explainability from self-explainable supervised algorithms, is able to enhance the understanding of the model and data. The experimental results show that our proposed method is effective, efficient, and scalable in capturing the network traffic patterns and detecting detailed network intrusion information such as type of attack with high detection performance, and is an ideal method to be applied in cloud-computing environments.

Ranking and Combining Latent Structured Predictive Scores without Labeled Data

Combining multiple predictors obtained from distributed data sources to an accurate meta-learner is promising to achieve enhanced performance in lots of prediction problems. As the accuracy of each predictor is usually unknown, integrating the predictors to achieve better performance is challenging. Conventional ensemble learning methods assess the accuracy of predictors based on extensive labeled data. In practical applications, however, the acquisition of such labeled data can prove to be an arduous task. Furthermore, the predictors under consideration may exhibit high degrees of correlation, particularly when similar data sources or machine learning algorithms were employed during their model training. In response to these challenges, this paper introduces a novel structured unsupervised ensemble learning model (SUEL) to exploit the dependency between a set of predictors with continuous predictive scores, rank the predictors without labeled data and combine them to an ensembled score with weights. Two novel correlation-based decomposition algorithms are further proposed to estimate the SUEL model, constrained quadratic optimization (SUEL.CQO) and matrix-factorization-based (SUEL.MF) approaches. The efficacy of the proposed methods is rigorously assessed through both simulation studies and real-world application of risk genes discovery. The results compellingly demonstrate that the proposed methods can efficiently integrate the dependent predictors to an ensemble model without the need of ground truth data.

V2X Communication Computing Resource Collaboration Technology Based on Deep Reinforcement Learning

In traditional cloud computing, data needs to be transferred from distributed data sources to remote cloud data centers for high-performance computing. However, tasks often experience network transmission delays of hundreds of milliseconds or more from data sources to cloud data centers, which does not meet the need for low latency in V2X (Vehicle to Everything) systems. On the basis of the existing heterogeneous task scenario, this paper proposes a communication computing resource collaboration technology scheme based on heterogeneous task, which can meet the requirements of delay and cost when facing tasks with different delay requirements and different divisibility. This scheme uses the communication computing resources of the roadside unit and the service vehicle, so that the computing task of the task vehicle can be completed within the delay requirement and the cost is minimal. We use the deep reinforcement learning method to study, and finally the performance of the proposed scheme is verified by simulation.

Deformation depth decoupling network for point cloud domain adaptation

Recently, point cloud domain adaptation (DA) practices have been implemented to improve the generalization ability of deep learning models on point cloud data. However, variations across domains often result in decreased performance of models trained on different distributed data sources. Previous studies have focused on output-level domain alignment to address this challenge. But this approach may increase the amount of errors experienced when aligning different domains, particularly for targets that would otherwise be predicted incorrectly. Therefore, in this study, we propose an input-level discretization-based matching to enhance the generalization ability of DA. Specifically, an efficient geometric deformation depth decoupling network (3DeNet) is implemented to learn the knowledge from the source domain and embed it into an implicit feature space, which facilitates the effective constraint of unsupervised predictions for downstream tasks. Secondly, we demonstrate that the sparsity within the implicit feature space varies between domains, rendering domain differences difficult to support. Consequently, we match sets of neighboring points with different densities and biases by differentiating the adaptive densities. Finally, inter-domain differences are aligned by constraining the loss originating from and between the target domains. We conduct experiments on point cloud DA datasets PointDA-10 and PointSegDA, achieving advanced results (over 1.2% and 1% on average).

Evaluating Federated Learning Simulators: A Comparative Analysis of Horizontal and Vertical Approaches.

Federated learning (FL) is a decentralized machine learning approach whereby each device is allowed to train local models, eliminating the requirement for centralized data collecting and ensuring data privacy. Unlike typical typical centralized machine learning, collaborative model training in FL involves aggregating updates from various devices without sending raw data. This ensures data privacy and security while collecting a collective learning from distributed data sources. These devices in FL models exhibit high efficacy in terms of privacy protection, scalability, and robustness, which is contingent upon the success of communication and collaboration. This paper explore the various topologies of both decentralized or centralized in the context of FL. In this respect, we investigated and explored in detail the evaluation of four widly used end-to-end FL frameworks: FedML, Flower, Flute, and PySyft. We specifically focused on vertical and horizontal FL systems using a logistic regression model that aggregated by the FedAvg algorithm. specifically, we conducted experiments on two images datasets, MNIST and Fashion-MNIST, to evaluate their efficiency and performance. Our paper provides initial findings on how to effectively combine horizontal and vertical solutions to address common difficulties, such as managing model synchronization and communication overhead. Our research indicates the trade-offs that exist in the performance of several simulation frameworks for federated learning.

Distributed optimal subsampling for quantile regression with massive data

Methods for reducing distributed subsample sizes have increasingly become popular statistical problems in the big data era. Existing works of optimal subsample selection on the massive linear and generalized linear models with distributed data sources have been solidly investigated and widely applied. Nevertheless, few studies have developed distributed optimal subsample selection procedures for quantile regression in massive data. In such settings, the distributed optimal subsampling probabilities and subset sizes selection criteria need to be established simultaneously. In this work, we propose a distributed subsampling technique for the quantile regression models. The estimation approach is based on a two-step algorithm for the distributed subsampling procedures. Furthermore, the theoretical results, such as consistency and asymptotic normality of resultant estimators, are rigorously established under some regularity conditions. The empirical evaluation and performance of the proposed subsampling method are conducted in simulation experiments and real data applications.

Optimized Federated Learning Algorithm for Breast Cancer Detection Using the Marine Predators Algorithm

Breast cancer stands as the leading cause of cancer-related fatalities among women worldwide, necessitating effective detection methods. However, the current landscape of breast cancer detection poses several challenges, including high costs, complexity, and suboptimal accuracy rates. In response, this paper presents a pioneering approach to breast cancer detection leveraging federated learning, a paradigm that allows model training across distributed data sources without centralized data sharing. Central to this novel detection model is the integration of a Convolutional Neural Network (CNN) architecture and a meta-heuristic optimization algorithm known as the marine predator's algorithm (MPA). CNNs have emerged as powerful tools for biomedical image analysis, enabling automatic feature extraction crucial for detecting abnormalities in medical images. However, optimizing CNNs for detection tasks requires meticulous tuning of hyperparameters across different layers, a process impractical to perform manually due to its complexity and time-intensive nature. To address this challenge, the paper proposes the utilization of the MPA as an optimization algorithm within the federated learning framework. The MPA, inspired by the foraging behaviour of marine predators, enhances the exploration-exploitation trade-off to prevent the model from getting stuck in local optima during training. By incorporating the MPA into the CNN architecture, the proposed model achieves remarkable testing accuracy, surpassing the performance of traditional DCNN models. During testing, the proposed model attained an impressive accuracy rate of 98.32%, showcasing its superior performance compared to the DCNN model, which achieved a 95.95% accuracy. Moreover, the proposed approach outperforms existing algorithms, achieving an accuracy rate of 98%. These results underscore the effectiveness of the federated learning-based approach in enhancing breast cancer detection accuracy. the proposed breast cancer detection model represents a significant advancement in the field, offering a highly accurate and efficient solution to overcome the challenges associated with traditional detection methods. By leveraging federated learning and innovative optimization techniques, this model holds promise for improving early detection rates, ultimately contributing to better patient outcomes in the fight against breast cancer

Enhancing generalization in Federated Learning with heterogeneous data: A comparative literature review

Federated Learning (FL) is a collaborative training paradigm whereby a global Machine Learning (ML) model is trained using typically private and distributed data sources without disclosing the raw data. The approach paves the way for better privacy guarantees, improved overall system scalability, and sustainability. In this context, Federated Averaging (FedAvg) is a representative FL algorithm adopting a client–server protocol that operates in synchronous rounds, where selected learners contribute to the global model via local model updates, trained using their private data, while a server entity aggregates the local contributions, producing the new-generation global model as a weighted average of the local ones. However, when clients possess (highly) dissimilar data, the FedAvg technique becomes ineffective due to divergence in client models. Consequently, FedAvg-trained models struggle to generalize when presented with unseen data from the global distribution. In this research paper, we conduct a systematic review of state-of-the-art approaches proposed to counteract global model performance degradation in the presence of heterogeneous data.To this end, we compile an original taxonomy, highlighting the main algorithmic approaches and mechanisms behind each identified category. Advancing the current body of knowledge, we empirically evaluate the generalization performance on visual tasks of various methods under moderate and significant levels of data heterogeneity, as common practice within the surveyed literature. In addition, the paper benchmarks the performance of hybrid techniques, resulting as a combination of client- and server-side algorithmic tweaks, by shedding light on some associated performance tradeoffs. While recognizing other relevant issues in FL, such as device heterogeneity and energy consumption, which have a non-negligible impact on the learning process, these well-investigated topics are not the main focus of this article.

FedCSCD-GAN: A secure and collaborative framework for clinical cancer diagnosis via optimized federated learning and GAN

Digital technologies present unrivaled opportunities to improve healthcare services worldwide. Medical devices and hospitals are now using innovative techniques to diagnose cancer patients. Despite the vast amount of data generated, stored, and communicated to the cloud and edge devices, patient data privacy remains a crucial concern. Federated learning (FL) is a revolutionary distributed learning method with significant potential in medical data processing. However, data privacy, data quality, and model performance issues can make it challenging to develop a resilient model. As a solution to the above-mentioned challenges, a secure and collaborative FedCSCD-GAN framework is proposed for clinical cancer diagnosis under the federated learning and GAN optimization principle. By leveraging the collective intelligence of distributed data sources, this framework seeks to improve cancer diagnosis accuracy while maintaining appropriate security measures for sensitive patient data. In the proposed system, the quasi-identifiers (QIden) are identifiedas independent QIden attributes in health data, while the others areclassified as confidential information (CI). Consequently, to enhance security and privacy f- differential privacy anonymization is performed on the QIden attributes, and the resulting data is mixed with the CI attribute. Using anonymized data, the Cramer GAN was trained using Cramer distance for efficiency, and privacy was assessed. Notably, the suggested architecture obtains diagnosis accuracy of 97.80 % for lung cancer, 96.95 % for prostate cancer, and 97 % for breast cancer. Based on the experimental analysis, the proposed architecture detects cancer accurately and addresses security and collaboration issues. This paradigm has the potential to transform healthcare and improve patient outcomes globally.

The impact of climate change on plant distribution and niche dynamics over the past 250 years in Switzerland

Herbarium specimens provide an irreplaceable source of historical plant distribution data, enabling analysis of changes in plant distribution spanning centuries. Most studies on plant distribution shifts focus on recent decades and rare species, especially along elevational gradients. We examined about 2000 historical herbarium specimens from the Botanical Garden of the University of Bern, representing 30 plant species from five Swiss lowland habitats (six species per habitat) dating back to 1768 and covering all Swiss cantons. All historical data were transcribed, georeferenced and then combined with current data resulting in about 170 000 plant records over 250 years. Combined with climatic data from the same period, we found that all habitats increased their potential distribution area with a significant gain in the semi-arid grasslands (+8.15 %, p-value = 0.031). On species level, 75 % of the selected species expanded their distribution, while 25 % of the species retracted. Despite these shifts, 90–99.6 % niche stability was observed between historical and current climatic niches across all species. Shifts in co-occurring species were specific to the species, not to the habitat. The consistent overlap in historical and current climatic niches suggest that distribution expansion is due to the growth of areas with suitable climates, pointing to climate change as a driving factor for plant distribution changes over the past 250 years.

Cost-based Virtual Machine Scheduling for Data-as-a-Service

Data-as-a-Service (DaaS) is a branch of cloud computing that supports “querying the Web”. Due to its ultrahigh scale, it is essential to establish rules when defining resources’ costs and guidelines for infrastructure investments. Those decisions should prioritize minimizing the incidence of agreement breaches that compromise the performance of cloud services and optimize resources’ usage and services’ cost. This article aims to address the cost problem of DaaS by developing a model that optimizes the costs of querying distributed data sources over virtual machines spread across multisite data centers. We have designed and analyzed a cost model for DaaS, besides implementing a scheduling system to perform a cost-based VM assignment. To validate our model, we have studied and characterized a real-world DaaS system’s network and processing workloads. On average, our cost-based scheduling performs at least twice as well as the traditional round-robin approach. Our model also supports load balancing and infrastructure scalability when combined with an adaptive cost scheme that prioritizes VM allocation within the underutilized data centers and avoids sending VMs to data centers in the eminence of becoming over-utilized.

Editorial

Dear Readers,  At the end of this year, it gives me great pleasure to announce the eleventh regular issue of 2023. In this issue, various topical aspects of computer science are covered in 6 articles by 18 authors from 7 countries (Argentina, Brazil, China, France, Germany, Spain, and Turkey). I would like to thank all the authors for their sound research and the editorial board for the highly valuable review effort and comments for improvement. These contributions, together with the generous support of the consortium members, sustain the quality of our journal. I am looking forward to continuing my work as Managing Editor-in-Chief with the J.UCS community.  In an ongoing effort to further strengthen our journal, I would like to expand the editorial board: If you are a tenured associate professor or above with a strong publication record, you are welcome to apply to join our editorial board. We are also interested in high-quality proposals for special issues on new topics and trends. Please consider yourself and encourage your colleagues to submit high-quality articles or special issue proposals for our journal. Finally, we are looking for further financial support from potential consortium members to cover the costs of publishing the journal next year.  In this regular issue, I am very pleased to introduce the following 6 accepted articles: F. Kebire Bardak, M. Nuri Seyman, and Feyzullah Temurtaş from Turkey present in their research a hybrid algorithm for emotion classification based on electroencephalogram signals, which is composed of a radial basis function neural network and a probabilistic neural network. In a collaborative research effort between Spain and France, Anita Herrera, Ángel Arroyo, Alfredo Jiménez and Álvaro Herrero conduct a comprehensive review of the different techniques and models with regard to Artificial Intelligence when applied to the tourism industry. In a collaboration between researchers from Brazil and Germany, Ana Cristina Alves de Oliveira, Marco Aurélio Spohn, Christof Fetzer, Le Quoc Do, and André Martin aim to address the cost problem of DaaS by developing a model that optimizes the cost of querying distributed data sources over virtual machines spread across multisite data centers. Herminia Beatriz Parra and Marcela Vegetti from Argentina present in their article OntoFoCE, Ontology for Electronic Mail Forensics, which is a specific ontology for the forensic analysis of emails to help the computer expert in validating an email presented as judicial evidence. Valdicélio Santos and Michel S. Soares from Brazil propose a framework, and then the design and further evaluation of a web-based application to support software architects in using the activities and tasks of the architecture conceptualization clause based on the ISO/IEC/IEEE 42020 framework. Last but not least, Yunwu Xu and Yan Li from China contribute to the improvement of an existing wireless sensor network coverage optimization method which is based on the pigeon-inspired optimization algorithm.  Season greetings to all of you, relaxing holidays and ‘Enjoy Reading’!  Cordially,  Christian Gütl, Managing Editor  Graz University of Technology, Graz, Austria

Advancing Pandemic Preparedness in Healthcare 5.0: A Survey of Federated Learning Applications

The intersection of Federated Learning (FL) and Healthcare 5.0 promises a transformative shift towards a more resilient future, particularly concerning pandemic preparedness. Within this context, Healthcare 5.0 signifies a holistic approach to healthcare delivery, where interconnected technologies enable data-driven decision-making, patient-centric care, and enhanced efficiency. This paper provides an in-depth exploration of FL’s role within the framework of Healthcare 5.0 and its implications for the pandemic response. Specifically, FL offers the potential to revolutionize pandemic preparedness within Healthcare 5.0 in several vital ways: it enables collaborative learning from distributed data sources without compromising individual data privacy, facilitates decentralized decision-making by empowering local healthcare institutions to contribute to a collective knowledge pool, and enhances real-time surveillance, enabling early detection of outbreaks and informed responses. We start by laying out the concepts of FL and Healthcare 5.0, followed by an analysis of current pandemic preparedness and response mechanisms. We delve into FL’s applications and case studies in healthcare, highlighting its potential benefits, including privacy protection, decentralized decision-making, and implementation challenges. By articulating how FL fits into Healthcare 5.0, we envisage future applications in a technologically integrated health system. By examining current applications and case studies of FL in healthcare, we highlight its potential benefits, including enhanced privacy protection and more effective decision support systems. Our findings demonstrate that FL can significantly improve pandemic response times and accuracy. Moreover, we speculate on the potential scenarios where FL could enhance pandemic preparedness and make healthcare more resilient. Finally, we recommend that policymakers, technologists, and educators address potential challenges and maximize the benefits of FL in Healthcare 5.0. This paper aims to contribute to the discourse on next-generation healthcare technologies, emphasizing FL’s potential to shape a more resilient healthcare future.

Evaluation of breeding distribution and chronology of North American scoters

North America's scoter species are poorly monitored relative to other waterfowl. Black Melanitta americana, surf M. perspicillata, and white‐winged M. deglandi scoter abundance and trend estimates are thus uncertain in many parts of these species' ranges. The most extensive source of waterfowl abundance and distribution data in North America is the Waterfowl breeding population and habitat survey (WBPHS). Although the WBPHS effectively monitors most species, both its timing and geographic coverage may preclude accurate scoter monitoring. Therefore, our goal was to better define when and where scoters breed to help interpret survey results and optimize potential supplemental survey efforts for scoters. We integrated satellite telemetry tracking data from scoters marked at multiple molting, staging, breeding, and wintering areas along the Atlantic and Pacific coasts to quantify continent‐wide breeding chronology and distribution. We also examined possible drivers of variation in timing of arrival, length of stay, and departure at nesting locations. We documented a northwest to southeast distribution of estimated breeding sites across Alaska and Canada. On average, scoters arrived at nest sites on 1 June. Surf scoters and Pacific black scoters arrived earliest and departed earliest. Pacific‐wintering black and white‐winged scoters began breeding earlier than Atlantic‐wintering birds. Additionally, birds arrived at nesting locations earlier in years with earlier snowmelt, and later snowmelt reduced lengths of stay for males. Breeding chronology also varied by age group, with adults arriving earlier than subadults. Our study is the first to comprehensively describe spatial variation in timing of breeding of both Atlantic and Pacific populations of all three scoter species across North America. Our results increase our understanding of how current surveys enumerate scoters and will inform possible supplemental efforts to improve continental monitoring of scoter populations.

Step towards secure and reliable smart grids in Industry 5.0: A federated learning assisted hybrid deep learning model for electricity theft detection using smart meters

The integration of Smart Grid technology and conceptual Industry 5.0 has paved the way for advanced energy management systems that enhance efficiency and revolutionized the parallel integration of power sources in a sustainable manner. However, this digitization has opened a new stream of the threat and opportunities of electricity theft posing a significant challenge to the security and reliability of Smart Grid networks. In this paper, we propose a secure and reliable theft detection technique using deep federated learning (FL) mechanism. The technique leverages the collaborative power of FL to train a Convolutional Gated Recurrent Unit (ConvGRU) model on distributed data sources without compromising data privacy. The training deep learning model backbone consists of a ConvGRU model that combines convolutional and gated recurrent units to capture spatial and temporal patterns in electricity consumption data. An improvised preprocessing mechanism and hyperparameter tuning is done to facilitate FL mechanism. The halving randomized search algorithm is used for hyperparameters tuning of the ConvGRU model. The impact of hyperparameters involved in the ConvGRU model such as number of layers, filters, kernel size, activation function, pooling, GRU layers, hidden state dimension, learning rate, and the dropout rate is elaborated. The proposed technique achieves promising results, with high accuracy, precision, recall, and F1 score, demonstrating its efficacy in detecting electricity theft in Smart Grid networks. Comparative analysis with existing techniques reveal the superior performance of the deep FL-based ConvGRU model. The findings highlight the potential of this approach in enhancing the security and efficiency of Smart Grid systems while preserving data privacy.

Phase space load balancing priority scheduling algorithm for cloud computing clusters

Due to the development of new technologies such as the Internet and cloud computing, high requirements have been placed on the storage and management of big data. At the same time, new applications in the cloud computing environment also pose new requirements for cloud storage systems, such as strong scalability and high concurrency. Currently, the existing nosql database system is based on cloud computing virtual resources, supporting dynamic addition and deletion of virtual nodes. Based on the study of phase space reconstruction, the necessity of considering traffic flow as a chaotic time series is analyzed. In addition, offline data migration methods based on load balancing are also studied. Firstly, a data migration model is proposed through analysis, and the factors that affect migration performance are analyzed. Based on this, optimization objectives for migration are proposed. Then, the system design of data migration is presented, and optimization research is conducted from two aspects around the migration optimization objectives: optimizing from the data source layer, and proposing the LBS method to convert data sources into distributed data sources, ensuring the balanced distribution of data and meeting the scalability requirements of the system. This paper applies cloud computing technology and phase space reconstruction to load balancing scheduling algorithms to promote their development.

Multimodal Federated Learning: A Survey.

Federated learning (FL), which provides a collaborative training scheme for distributed data sources with privacy concerns, has become a burgeoning and attractive research area. Most existing FL studies focus on taking unimodal data, such as image and text, as the model input and resolving the heterogeneity challenge, i.e., the challenge of non-identical distribution (non-IID) caused by a data distribution imbalance related to data labels and data amount. In real-world applications, data are usually described by multiple modalities. However, to the best of our knowledge, only a handful of studies have been conducted to improve system performance utilizing multimodal data. In this survey paper, we identify the significance of this emerging research topic of multimodal federated learning (MFL) and present a literature review on the state-of-art MFL methods. Furthermore, we categorize multimodal federated learning into congruent and incongruent multimodal federated learning based on whether all clients possess the same modal combinations. We investigate the feasible application tasks and related benchmarks for MFL. Lastly, we summarize the promising directions and fundamental challenges in this field for future research.

Predicting anticancer drug sensitivity on distributed data sources using federated deep learning

Drug sensitivity prediction plays a crucial role in precision cancer therapy. Collaboration among medical institutions can lead to better performance in drug sensitivity prediction. However, patient privacy and data protection regulation remain a severe impediment to centralized prediction studies. For the first time, we proposed a federated drug sensitivity prediction model with high generalization, combining distributed data sources while protecting private data. Cell lines are first classified into three categories using the waterfall method. Focal loss for solving class imbalance is then embedded into the horizontal federated deep learning framework, i.e., HFDL-fl is presented. Applying HFDL-fl to homogeneous and heterogeneous data, we obtained HFDL-Cross and HFDL-Within. Our comprehensive experiments demonstrated that (i) collaboration by HFDL-fl outperforms private model on local data, (ii) focal loss function can effectively improve model performance to classify cell lines in sensitive and resistant categories, and (iii) HFDL-fl is not significantly affected by data heterogeneity. To summarize, HFDL-fl provides a valuable solution to break down the barriers between medical institutions for privacy-preserving drug sensitivity prediction and therefore facilitates the development of cancer precision medicine and other privacy-related biomedical research.

Logical big data integration and near real-time data analytics

In the context of decision-making, there is a growing demand for near real-time data that traditional solutions, like data warehousing based on long-running ETL processes, cannot fully meet. On the other hand, existing logical data integration solutions are challenging because users must focus on data location and distribution details rather than on data analytics and decision-making.EasyBDI is an open-source system that provides logical integration of data and high-level business-oriented abstractions. It uses schema matching, integration, and mapping techniques, to automatically identify partitioned data and propose a global schema. Users can then specify star schemas based on global entities and submit analytical queries to retrieve data from distributed data sources without knowing the organization and other technical details of the underlying systems.This work presents the algorithms and methods for global schema creation and query execution. Experimental results show that the overhead imposed by logical integration layers is relatively small compared to the execution times of distributed queries.