Machine Unlearning (MU) is an emerging research area that enables models to selectively forget specific data, a critical requirement for privacy compliance (e.g., GDPR, CCPA) and security. However, the lack of standardized benchmarks makes evaluating and developing unlearning methods difficult. To address this gap, we introduce ERASURE, a benchmarking and development framework designed to systematically assess MU techniques. ERASURE provides a modular, extensible, open-source environment with real-world datasets and standardized unlearning measures. The framework is designed with configuration-driven workflows and an inversion of control architecture, allowing integration of new datasets, models, and evaluation measures. ERASURE advances trustworthy AI research as a tool for researchers to develop and benchmark new MU methods.

Forecasting surface water dynamics is crucial for water resource management and climate change adaptation. However, the field lacks comprehensive datasets and standardized benchmarks. In this paper, we introduce HydroChronos, a large-scale, multi-modal spatiotemporal dataset for surface water dynamics forecasting designed to address this gap. We couple the dataset with three forecasting tasks. The dataset includes over three decades of aligned Landsat 5 and Sentinel-2 imagery, climate data, and Digital Elevation Models for diverse lakes and rivers across Europe, North America, and South America. We also propose AquaClimaTempo UNet, a novel spatiotemporal architecture with a dedicated climate data branch, as a strong benchmark baseline. Our model significantly outperforms a Persistence baseline for forecasting future water dynamics by +14% and +11% F1 across change detection and direction of change classification tasks, and by +0.1 MAE on the magnitude of change regression. Finally, we conduct an Explainable AI analysis to identify the key climate variables and input channels that influence surface water change, providing insights to inform and guide future modeling efforts.

This paper presents a real-world deployment case study on using unsupervised anomaly detection for Anti-Money Laundering (AML).Using more than 2 billion anonymized bank transactions that Intesa Sanpaolo, a primary Italian financial institution, registered over 8 months, we developed, tuned and deployed a machine learning pipeline in production.Experts from Intesa Sanpaolo validated the performance of our approach against the institution's traditional rule-based system and checked new real-world cases the system allowed them to identify.Besides increasing both precision and recall by a factor of 6 in the detection of high-risk cases, our pipeline raises 200+ additional alerts during the 8-month period, manually identified by branch managers, but missed by the rulebased system.More importantly, a manual inspection of 100 new unseen cases revealed 28 significant previously unreported cases.The pipeline, now fully deployed in Intesa Sanpaolo's Transaction Monitoring system, highlights the advantages of machine learning over traditional approaches typically adopted in this traditionally very conservative sector.

Multimodal artificial intelligence promises deeper insights by analyzing data from diverse sources such as text, images, audio and more. However, efficiently processing and fusing large multimodal datasets remains an open challenge. This paper presents a Spark-based approach to parallelize multimodal encoding tasks. A key aspect is the use of late fusion with frozen backbone encoders, allowing encodings to be processed independently across cluster nodes. The encoded vectors can then be used for a variety of supervised and unsupervised tasks, regardless of whether they are gradient-based or not. Experimental results on image, text and audio datasets show that Spark clusters can offer competitive performance compared to GPUs, especially for I/O-intensive modalities. While GPUs outperform the Spark cluster when sufficient CPU cores are available, Spark makes it possible to use already available commodity hardware. The presented architecture demonstrates how distributed computing platforms like Spark can be effectively “repurposed” for multimodal AI, enhancing scalability and making such systems more accessible.

Understanding peculiar and anomalous behavior of machine learning models for specific data subgroups is a fundamental building block of model performance and fairness evaluation. The analysis of these data subgroups can provide useful insights into model inner working and highlight its potentially discriminatory behavior. Current approaches to subgroup exploration ignore the presence of hierarchies in the data, and can only be applied to discretized attributes. The discretization process required for continuous attributes may significantly affect the identification of relevant subgroups.We propose a hierarchical subgroup exploration technique to identify anomalous subgroup behavior at multiple granularity levels, along with a technique for the hierarchical discretization of data attributes. The hierarchical discretization produces, for each continuous attribute, a hierarchy of intervals. The subsequent hierarchical exploration can exploit data hierarchies, selecting for each attribute the optimal granularity to identify subgroups that are both anomalous, and with enough elements to be statistically and practically significant. Compared to non- hierarchical approaches, we show that our hierarchical approach is more powerful in identifying anomalous subgroups and more stable with respect to discretization and exploration parameters.

Computing generates intelligence. With this statement we do not mean computing’s capabilities of manipulating numbers, shapes, symbols, and even logics. What we mean is the ingenious design of computing structures which serve as the basis of intelligence generation during program running. In this panel discussion, we consider how to obtain such capabilities through some computing paradigms as examples, including principal computing, logic computing, discriminative computing, and generative computing. The panelists express their thoughts about the inherent advantages and disadvantages of each of these paradigms, in terms of their adaptivity, interpretability, generality and specificity, and dives into detailed discussions about Large Language Models (LLMs), a mainstream generative paradigm which leverages the strengths of large pre-trained models and downstream prompt tuning to deliver combined intelligence, superior to most existing frameworks in natural language processing. The panel outlines potential challenges of the generative paradigm, with a strong focus on LLMs, and emphasizes that future directions of such models will need to address (1) tackling bias, discrimination, and transparency challenges; (2) delivering logical answers with high specificity; (3) enabling personalized, lightweight, and rapid updating mechanisms; (4) assessing accreditation, tracing, and misusages; and (5) ensuring sustainable LLMs.

Transaction Monitoring is one of the main labor-intensive tasks of anti-financial crime and it requires to scrutinise billions of transactions per month against possible crimes. The first step in the process is the correct identification of the involved parties. This foundational step defines the focal entities on which transaction monitoring algorithms rely to spot suspicious events. Unfortunately, the loose syntax of protocols and the free text fields of inter-banking communications make party disambiguation particularly challenging. The first step of a fully automated data-driven strategy is thus the detection of the actual entity owning or using a given account.In this paper, we leverage data-driven techniques to identify and disambiguate the owners of accounts involved in cross-border international transactions when a Financial Institution only knows a minority fraction of such parties as its own customers. For this, we propose a data science pipeline relying on hierarchical clustering to capture similarities among names of parties involved in actual transactions. We test and tune the proposed approach using a large, real-world, multi-language, proprietary dataset of actual international transactions. Our highly parallel implementation completes the identification of parties that share an account and identifies all accounts owned by a party with f-score higher than 0.8.

The ability to correctly identify areas damaged by forest wildfires is essential to plan and monitor the restoration process and estimate the environmental damages after such catastrophic events. The wide availability of satellite data, combined with the recent development of machine learning and deep learning methodologies applied to the computer vision field, makes it extremely interesting to apply the aforementioned techniques to the field of automatic burned area detection. One of the main issues in such a context is the limited amount of labeled data, especially in the context of semantic segmentation. In this paper, we introduce a publicly available dataset for the burned area detection problem for semantic segmentation. The dataset contains 73 satellite images of different forests damaged by wildfires across Europe with a resolution of up to 10m per pixel. Data were collected from the Sentinel-2 L2A satellite mission and the target labels were generated from the Copernicus Emergency Management Service (EMS) annotations, with five different severity levels, ranging from undamaged to completely destroyed. Finally, we report the benchmark values obtained by applying a Convolutional Neural Network on the proposed dataset to address the burned area identification problem.

Timeline summarization aims at presenting long news stories in a compact manner. State-of-the-art approaches first select the most relevant dates from the original event timeline then produce per-date news summaries. Date selection is driven by either per-date news content or date-level references. When coping with complex event data, characterized by inherent news flow redundancy, this pipeline may encounter relevant issues in both date selection and summarization due to a limited use of news content in date selection and no use of high-level temporal references (e.g., the past month). This paper proposes a paradigm shift in timeline summarization aimed at overcoming the above issues. It presents a new approach, namely Summarize Date First, which focuses on first generating date-level summaries then selecting the most relevant dates on top of summarized knowledge. In the latter stage, it performs date aggregations to consider high-level temporal references as well. The proposed pipeline also supports frequent incremental timeline updates more efficiently than previous approaches. We tested our unsupervised approach both on existing benchmark datasets and on a newly proposed benchmark dataset describing the COVID-19 news timeline. The achieved results were superior to state-of-the-art unsupervised methods and competitive against supervised ones.

Machine learning models may perform differently on different data subgroups, which we represent as itemsets (i.e., conjunctions of simple predicates). The identification of these critical data subgroups plays an important role in many applications, for example model validation and testing, or evaluation of model fairness. Typically, domain expert help is required to identify relevant (or sensitive) subgroups.

We present DivExplorer, a tool that enables users to explore datasets and find subgroups of data for which a classifier behaves in an anomalous manner. These subgroups, denoted as divergent subgroups, may exhibit, for example, higher-than-normal false positive or negative rates. DivExplorer can be used to analyze and debug classifiers. If the data has ethical or social implications, DivExplorer can be also used to identify bias in classifiers.

Uncontrolled wildfires are dangerous events capable of harming people safety. To contrast their increasing impact in recent years, a key task is an accurate detection of the affected areas and their damage assessment from satellite images. Current state-of-the-art solutions address such problem through a double convolutional neural network able to automatically detect wildfires in satellite acquisitions and associate a damage index from a defined scale. However, such deep-learning model performance is strongly dependent on many factors. In this work, we specifically focus on a key parameter, i.e., the loss function, exploited in the underlying neural networks. Besides the state-of-the-art solutions based on the Dice-MSE, among the many loss functions proposed in literature, we focus on the Binary Cross-Entropy (BCE) and the Intersection over Union (IoU), as two representatives of the distribution-based and region-based categories, respectively. Experiments show that the BCE loss function coupled with a double-step U-Net architecture provides better results than current state-of-the-art solutions on a public labeled dataset of European wildfires.

Exploring and understanding the motivations behind black-box model predictions is becoming essential in many different applications. X-PLAIN is an interactive tool that allows human-in-the-loop inspection of the reasons behind model predictions. Its support for the local analysis of individual predictions enables users to inspect the local behavior of different classifiers and compare the knowledge different classifiers are exploiting for their prediction. The interactive exploration of prediction explanation provides actionable insights for both trusting and validating model predictions and, in case of unexpected behaviors, for debugging and improving the model itself.

Self-organizing maps are an unsupervised machine learning technique that offers interpretable results by identifying topological properties in high-dimensional datasets and projecting them on a 2-dimensional grid. An important problem of self-organizing maps is the computational expensiveness of their training phase. In this paper, we propose a fast approach to train self-organizing maps. The approach consists of 2 steps. First, a small map identifies the most relevant areas from the entire high-dimensional input space. Then a larger map (initialized from the small one) is fine-tuned to further explore the local areas identified in the first step. The resulting map has performance (measured in terms of accuracy and quantization error) on par with self-organizing maps trained with the standard approach, but with a significantly reduced training time.

More than 2 millions of new books are published every year and choosing a good book among the huge amount of available options can be a challenging endeavor. Recommender systems help in choosing books by providing personalized suggestions based on the user reading history. However, most book recommender systems are based on collaborative filtering, involving a long onboarding process that requires to rate many books before providing good recommendations. Tinderbook provides book recommendations, given a single book that the user likes, through a card-based playful user interface that does not require an account creation. Tinderbook is strongly rooted in semantic technologies, using the DBpedia knowledge graph to enrich book descriptions and extending a hybrid state-of-the-art knowledge graph embeddings algorithm to derive an item relatedness measure for cold start recommendations. Tinderbook is publicly available ( http://www.tinderbook.it ) and has already generated interest in the public, involving passionate readers, students, librarians, and researchers. The online evaluation shows that Tinderbook achieves almost 50% of precision of the recommendations.

Sentence-based summarization aims at extracting concise summaries of collections of textual documents. Summaries consist of a worthwhile subset of document sentences. The most effective multilingual strategies rely on Latent Semantic Analysis (LSA) and on frequent itemset mining, respectively. LSA-based summarizers pick the document sentences that cover the most important concepts. Concepts are modeled as combinations of single-document terms and are derived from a term-by-sentence matrix by exploiting Singular Value Decomposition (SVD). Itemset-based summarizers pick the sentences that contain the largest number of frequent itemsets, which represent combinations of frequently co-occurring terms. The main drawbacks of existing approaches are (i) the inability of LSA to consider the correlation between combinations of multiple-document terms and the underlying concepts, (ii) the inherent redundancy of frequent itemsets because similar itemsets may be related to the same concept, and (iii) the inability of itemset-based summarizers to correlate itemsets with the underlying document concepts. To overcome the issues of both of the abovementioned algorithms, we propose a new summarization approach that exploits frequent itemsets to describe all of the latent concepts covered by the documents under analysis and LSA to reduce the potentially redundant set of itemsets to a compact set of uncorrelated concepts. The summarizer selects the sentences that cover the latent concepts with minimal redundancy. We tested the summarization algorithm on both multilingual and English-language benchmark document collections. The proposed approach performed significantly better than both itemset- and LSA-based summarizers, and better than most of the other state-of-the-art approaches.

Clustering big data is a challenging task, because the majority of high-quality clustering algorithms do not scale well with respect to the data set cardinality. To tackle the scalability problem, we propose a general-purpose density-based preprocessing technique, called SCOUT, implemented in the Spark framework. It allows compacting the original data by means of a set of representative points, while still preserving the original data distribution and density information. This small set of representative points may become the input to almost any clustering algorithm. Thus, also complex, high-quality in-memory algorithms can be applied. A thorough experimental evaluation shows that the proposed approach is efficient and at the same time effective.

Predictive maintenance is an ever-growing area of interest, spanning different fields and approaches. In the automotive industry faulty behaviors of the oxygen sensor are a key challenge to address. This paper presents OxyClog, a data-driven framework that, given a large number of time series collected from a vehicle's ECU (engine control unit), builds a model to predict if the oxygen sensor is currently unclogged, almost clogged (since the clogging of the sensor happens gradually), or clogged. OxyClog is characterized by a tailored preprocessing, which includes a custom and interpretable feature selection algorithm, along with a summarization strategy to transform a time-dependent problem into a time-independent one. Furthermore, a semi-supervised labeling methodology has been devised to use different data sources with different characteristics to define meaningful clogging labels. OxyClog integrates state-of-the-art classification algorithms - both interpretable and non-interpretable - to process real ECU data with good prediction performance.

In the last years, we are witnessing an increasing availability of geolocated data, ranging from satellite images to user generated content (e.g., tweets). This big amount of data is exploited by several cloud-based applications to deliver effective and customized services to end users. In order to provide a good user experience, a low-latency response time is needed, both when data are retrieved and provided. To achieve this goal, current geospatial applications need to exploit efficient and scalable geospatial databases, the choice of which has a high impact on the overall performance of the deployed applications. In this paper, we compare, from a qualitative point of view, four state-of-the-art SQL and NoSQL databases with geospatial features, and then we analyze the performances of two of them, selecting the ones based on the Database-as-a-service (DBaaS) model: Azure SQL Database and Azure DocumentDB (i.e., an SQL database versus a NoSQL one). The empirical evaluation shows pros and cons of both solutions and it is performed on a real use case related to an emergency management application.

Physicians and health care organizations always collect large amounts of data during patient care. These large and high-dimensional datasets are usually characterized by an inherent sparseness. Hence, analyzing these datasets to figure out interesting and hidden knowledge is a challenging task. This article proposes a new data mining framework based on generalized association rules to discover multiple-level correlations among patient data. Specifically, correlations among prescribed examinations, drugs, and patient profiles are discovered and analyzed at different abstraction levels. The rule extraction process is driven by a taxonomy to generalize examinations and drugs into their corresponding categories. To ease the manual inspection of the result, a worthwhile subset of rules (i.e., nonredundant generalized rules) is considered. Furthermore, rules are classified according to the involved data features (medical treatments or patient profiles) and then explored in a top-down fashion: from the small subset of high-level rules, a drill-down is performed to target more specific rules. The experiments, performed on a real diabetic patient dataset, demonstrate the effectiveness of the proposed approach in discovering interesting rule groups at different abstraction levels.

Multidocument summarization addresses the selection of a compact subset of highly informative sentences, i.e., the summary, from a collection of textual documents. To perform sentence selection, two parallel strategies have been proposed: (a) apply general-purpose techniques relying on data mining or information retrieval techniques, and/or (b) perform advanced linguistic analysis relying on semantics-based models (e.g., ontologies) to capture the actual sentence meaning. Since there is an increasing need for processing documents written in different languages, the attention of the research community has recently focused on summarizers based on strategy (a). This article presents a novel multilingual summarizer, namely MWI-Sum (Multilingual Weighted Itemset-based Summarizer), that exploits an itemset-based model to summarize collections of documents ranging over the same topic. Unlike previous approaches, it extracts frequent weighted itemsets tailored to the analyzed collection and uses them to drive the sentence selection process. Weighted itemsets represent correlations among multiple highly relevant terms that are neglected by previous approaches. The proposed approach makes minimal use of language-dependent analyses. Thus, it is easily applicable to document collections written in different languages. Experiments performed on benchmark and real-life collections, English-written and not, demonstrate that the proposed approach performs better than state-of-the-art multilingual document summarizers.

Incremental tests are widely used in cardiopulmonary exercise testing, both in the clinical domain and in sport sciences. The highest workload (denoted Wpeak) reached in the test is key information for assessing the individual body response to the test and for analyzing possible cardiac failures and planning rehabilitation, and training sessions. Being physically very demanding, incremental tests can significantly increase the body stress on monitored individuals and may cause cardiopulmonary overload. This article presents a new approach to cardiopulmonary testing that addresses these drawbacks. During the test, our approach analyzes the individual body response to the exercise and predicts the Wpeakvalue that will be reached in the test and an evaluation of its accuracy. When the accuracy of the prediction becomes satisfactory, the test can be prematurely stopped, thus avoiding its entire execution. To predict Wpeak, we introduce a new index, the CardioPulmonary Efficiency Index (CPE), summarizing the cardiopulmonary response of the individual to the test. Our approach analyzes the CPE trend during the test, together with the characteristics of the individual, and predicts Wpeak. A K-nearest-neighbor-based classifier and an ANN-based classier are exploited for the prediction. The experimental evaluation showed that the Wpeakvalue can be predicted with a limited error from the first steps of the test.

A promising approach to Bayesian classification is based on exploiting frequent patterns, i.e., patterns that frequently occur in the training data set, to estimate the Bayesian probability. Pattern-based Bayesian classification focuses on building and evaluating reliable probability approximations by exploiting a subset of frequent patterns tailored to a given test case. This paper proposes a novel and effective approach to estimate the Bayesian probability. Differently from previous approaches, the Entropy-based Bayesian classifier, namely EnBay, focuses on selecting the minimal set of long and not overlapped patterns that best complies with a conditional-independence model, based on an entropy-based evaluator. Furthermore, the probability approximation is separately tailored to each class. An extensive experimental evaluation, performed on both real and synthetic data sets, shows that EnBay is significantly more accurate than most state-of-the-art classifiers, Bayesian and not.

Associative classification is characterized by accurate models and high model generation time. Most time is spent in extracting and postprocessing a large set of irrelevant rules, which are eventually pruned. We propose I-prune, an item-pruning approach that selects uninteresting items by means of an interestingness measure and prunes them as soon as they are detected. Thus, the number of extracted rules is reduced and model generation time decreases correspondingly. A wide set of experiments on real and synthetic data sets has been performed to evaluate I-prune and select the appropriate interestingness measure. The experimental results show that I-prune allows a significant reduction in model generation time, while increasing (or at worst preserving) model accuracy. Experimental evaluation also points to the chi-square measure as the most effective interestingness measure for item pruning. © 2012 Wiley Periodicals, Inc.

BioSumm is a summarization environment that supports user queries on online repositories of scientific publications by providing abstract descriptions of focused document groups. The summarization approach is driven by a grading function which evaluates the occurrences of domain dictionary terms.

Many real-life databases are updated by means of incoming business information. In these databases (e.g., transactional data from large retail chains, call-detail records), the content evolves through periodical insertions (or deletions) of data blocks. Since data evolve over time, algorithms have to be devised to incrementally update data mining models. This paper presents a novel index, called I-Forest, to support itemset mining on incoming data blocks, where new blocks are inserted periodically, or old blocks are discarded. The I-Forest structure provides a complete data representation and allows different kind of analyses (e.g., investigate quarterly data), besides supporting user-defined time and support constraints. The I-Forest index has been implemented into the PostgreSQL open source DBMS and exploits its physical level access methods. Experiments, run for both sparse and dense data distributions, show the effectiveness of the I-Forest-based approach to perform itemset mining with both time and support constraints. The execution time of the I-Forest-based itemset mining technique is often faster than the Prefix-Tree algorithm accessing static data on flat files. © 2010 Wiley Periodicals, Inc.

This paper presents the IMine index, a general and compact structure which provides tight integration of item set extraction in a relational DBMS. Since no constraint is enforced during the index creation phase, IMine provides a complete representation of the original database. To reduce the I/O cost, data accessed together during the same extraction phase are clustered on the same disk block. The IMine index structure can be efficiently exploited by different item set extraction algorithms. In particular, IMine data access methods currently support the FP-growth and LCM v.2 algorithms, but they can straightforwardly support the enforcement of various constraint categories. The IMine index has been integrated into the PostgreSQL DBMS and exploits its physical level access methods. Experiments, run for both sparse and dense data distributions, show the efficiency of the proposed index and its linear scalability also for large datasets. Item set mining supported by the IMine index shows performance always comparable with, and sometimes better than, state of the art algorithms accessing data on flat file.

Associative classification is a promising technique to build accurate classifiers. However, in large or correlated datasets, association rule mining may yield huge rule sets. Hence, several pruning techniques have been proposed to select a small subset of high quality rules. We argue that rule pruning should be reduced to a minimum, since the availability of a "rich" rule set may improve the accuracy of the classifier. The L^3 associative classifier is built by means of a lazy pruning technique which discards exclusively rules that only misclassify training data. Classification of unlabeled data is performed in two steps. A small subset of high quality rules is first considered. When this set is not able to classify the data, a larger rule set is exploited. This second set includes rules usually discarded by previous approaches. To cope with the need of mining large rule sets and efficiently use them for classification, a compact form is proposed to represent a complete rule set in a space-efficient way and without information loss. An extensive experimental evaluation on real and synthetic datasets shows that L^3 improves the classification accuracy with respect to previous approaches.

XML is a rather verbose representation of semistructured data, which may require huge amounts of storage space. We propose a summarized representation of XML data, based on the concept of instance pattern, which can both provide succinct information and be directly queried. The physical representation of instance patterns exploits itemsets or association rules to summarize the content of XML datasets. Instance patterns may be used for (possibly partially) answering queries, either when fast and approximate answers are required, or when the actual dataset is not available, for example, it is currently unreachable. Experiments on large XML documents show that instance patterns allow a significant reduction in storage space, while preserving almost entirely the completeness of the query result. Furthermore, they provide fast query answers and show good scalability on the size of the dataset, thus overcoming the document size limitation of most current XQuery engines.

Many efforts have been devoted to couple data mining activities with relational DBMSs, but a true integration into the relational DBMS kernel has been rarely achieved. This paper presents a novel indexing technique, which represents transactions in a succinct form, appropriate for tightly integrating frequent itemset mining in a relational DBMS. The data representation is complete, i.e., no support threshold is enforced, in order to allow reusing the index for mining itemsets with any support threshold. Furthermore, an appropriate structure of the stored information has been devised, in order to allow a selective access of the index blocks necessary for the current extraction phase. The index has been implemented into the PostgreSQL open source DBMS and exploits its physical level access methods. Experiments have been run for various datasets, characterized by different data distributions. The execution time of the frequent itemset extraction task exploiting the index is always comparable with and sometime faster than a C++ implementation of the FP-growth algorithm accessing data stored on a flat file.

Given a class model built from a dataset including labeled data, classification assigns a new data object to the appropriate class. In associative classification the class model (i.e., the classifier) is a set of association rules. Associative classification is a promising technique for the generation of highly accurate classifiers. In this article, we present a compact form which encodes without information loss the classification knowledge available in a classification rule set. This form includes the rules that are essential for classification purposes, and thus it can replace the complete rule set. The proposed form is particularly effective in dense datasets, where traditional extraction techniques may generate huge rule sets. The reduction in size of the rule set allows decreasing the complexity of both the rule generation step and the rule pruning step. Hence, classification rule extraction can be performed also with low support, in order to extract more, possibly useful, rules.

Associative classification is a promising technique for the generation of highly precise classifiers. Previous works propose several clever techniques to prune the huge set of generated rules, with the twofold aim of selecting a small set of high quality rules, and reducing the chance of overfitting. In this paper, we argue that pruning should be reduced to a minimum and that the availability of a large rule base may improve the precision of the classifier without affecting its performance. In L/sup 3/ (Live and Let Live), a new algorithm for associative classification, a lazy pruning technique iteratively discards all rules that only yield wrong case classifications. Classification is performed in two steps. Initially, rules which have already correctly classified at least one training case, sorted by confidence, are considered If the case is still unclassified, the remaining rules (unused during the training phase) are considered, again sorted by confidence. Extensive experiments on 26 databases from the UCI machine learning database repository show that L/sup 3/ improves the classification precision with respect to previous approaches.

Rules in active database systems can be very difficult to program due to the unstructured and unpredictable nature of rule processing. We provide static analysis techniques for predicting whether a given rule set is guaranteed to terminate and whether rule execution is confluent (guaranteed to have a unique final state). Our methods are based on previous techniques for analyzing rules in active database systems. We improve considerably on the previous techniques by providing analysis criteria that are much less conservative: our methods often determine that a rule set will terminate or is confluent when previous methods could not make this determination. Our improved analysis is based on a “propagation” algorithm, which uses an extended relational algebra to accurately determine when the action of one rule can affect the condition of another, and determine when rule actions commute. We consider both conditon-action rules and event-condition-action-rules, making our approach widely applicable to relational active database rule languages and to the trigger language in the SQL:1999 standard.

Active rules may interact in complex and sometimes unpredictable ways, thus possibly yielding infinite rule executions by triggering each other indefinitely. This paper presents analysis techniques focused on detecting termination of rule execution. We describe an approach which combines static analysis of a rule set at compile-time and detection of endless loops during rule processing at runtime. The compile-time analysis technique is based on the distinction between mutual triggering and mutual activation of rules. This distinction motivates the introduction of two graphs defining rule interaction, called Triggering and Activation Graphs, respectively. This analysis technique allows us to identify reactive behaviors which are guaranteed to terminate and reactive behaviors which may lead to infinite rule processing. When termination cannot be guaranteed at compile-time, it is crucial to detect infinite rule executions at runtime. We propose a technique for identifying loops which is based on recognizing that a given situation has already occurred in the past and, therefore, will occur an infinite number of times in the future. This technique is potentially very expensive, therefore, we explain how it can be implemented in practice with limited computational effort. A particular use of this technique allows us to develop cycle monitors, which check that critical rule sequences, detected at compile time, do not repeat forever We bridge compile-time analysis to runtime monitoring by showing techniques, based on the result of rule analysis, for the identification of rule sets that can be independently monitored and for the optimal selection of cycle monitors.

Different rule execution semantics may be available in the same active database system. We perform several simulation experiments to evaluate the performance trade-offs yielded by different execution semantics in various operating conditions. In particular, we evaluate the effect of executing transaction and rule statements that affect a varying number of data instances, and applications with different rule triggering breadth and depth. Since references to data changed by the database operation triggering the rules are commonly used in active rule programming, we also analyze the impact of its management on overall performance.

Active database systems can be used to establish and enforce data management policies. A large amount of the semantics that normally needs to be coded in application programs can be abstracted and assigned to active rules. This trend is sometimes called “knowledge independence” a nice consequence of achieving full knowledge independence is that data management policies can then effectively evolve just by modifying rules instead of application programs. Active rules, however, may be quite complex to understand and manage: rules react to arbitrary event sequences, they trigger each other, and sometimes the outcome of rule processing may depend on the order in which events occur or rules are scheduled. Although reasoning on a large collection of rules is very difficult, the task becomes more manageable when the rules are few. Therefore, we are convinced that modularization, similar to what happens in any software development process, is the key principle for designing active rules; however, this important notion has not been addressed so far. This article introduces a modularization technique for active rules called stratification; it presents a theory of stratification and indicates how stratification can be practically applied. The emphasis of this article is on providing a solution to a very concrete and practical problem; therefore, our approach is illustrated by several examples.