Large Rule Sets Research Articles

Are heterogeinity and conflicting preferences no longer a problem? Personality-based dynamic clustering for group recommender systems

The complexity associated with groups of tourists led to the emergence of Group Recommender Systems (GRS) for tourism. But if generating recommendations for small groups is a complex task, to provide them to large and occasional groups is even more. This complexity is especially due to the group’s heterogeinity, conflicting preferences, the information overload found on the internet and the tourists’ different ways of coping with the information, hindering the recommendation process from the users’ profile construction to the final recommendation of a list of points of interest to visit. In this work, we show how we tackled the identified issues in a GRS prototype, Grouplanner, including the cold-start problem, by predicting the tourists’ preferences based only on their personality and dividing the main group into subgroups of similar personality; by using a Multi-Agent Microservice; a novel dynamic clustering algorithm, d-means, adapted from the k-means algorithm, that does not need to know the number of clusters a priori; and association rules. Using a personality dataset of n=100k users, the proposed d-means algorithm was tested against two baselines (k-means and k-means++), showing better results in the clustering quality and scalability. We were also able to determine a large set of association rules to refine the recommendations, although further improvements are needed. To test the Grouplanner prototype, a simulation with real users (n=35) was conducted. The results showed the subgroups formed were very compact, revealing a very good clustering quality, with an average silhouette of s = 0.91. 11 of the 15 proposed tourist preferences were successfully predicted and used for the preliminary recommendation lists, being 92 % of the participants satisfied with the individual recommendations and 96 % with the group recommendations.

TupleTree: A High-Performance Packet Classification Algorithm Supporting Fast Rule-Set Updates

Packet classification plays a crucial role in various network functions such as access control and routing. In recent years, the rapid development of SDN and NFV poses new challenges for packet classification to support fast rule-set updates as introducing strong dynamics for the structure of networks. To this end, this paper proposes a novel scheme, TupleTree, to perform high-speed packet classification while providing fast rule-set update ability. TupleTree is a hybrid scheme combining decision tree and tuple space. In TupleTree, it organizes rules in a decision tree-like structure, but distributes rules in each node into child nodes through hashing rather than cutting or splitting. With the decision tree structure, for each classification, one leaf node containing a few rules can be rapidly indexed. Hence, a high classification performance can be achieved. Meanwhile, with hashing instead of cutting or splitting, it is easy to support fast rule-set updates due to having avoided the rule replication problem. Compared to state-of-the-art schemes that support fast rule-set updates, experimental results show that our proposed scheme achieves a classification performance improvement of 85% to 237% while retaining close update performance for large rule-sets.

Management of German national parks: The role of institutions and actors in defining goals and making decisions

The process of defining goals and decision-making in German national parks (NLPs) takes place in the context of a large set of rules and a diversity of actors with different interests. As a result, unique management approaches and practices are applied in each of the 16 NLPs in Germany. This study investigates, how NLP administrations make these decisions.A conservation policy analysis based on the analytical framework of actor-centred institutionalism should identify the most salient drivers of goal setting and decision-making at the meso-level. Using a mixed-methods research approach, the range of influencing factors can be gathered from several perspectives. This study analyses 50 documents, 22 interviews with NLP managers, and an online survey of 179 actors within and associated with national park administration. Both quantitative and qualitative approaches were applied to analyse the generated data.The results show that broadly applicable institutions such as laws and decrees define the main goal to “let nature be nature” but do not determine specific actions for the national parks. The most important institutions for NLP managers are those that apply only to a single NLP, such as NLP laws or management plans. In addition to the existing rules, various interests of different actors have an impact on the decision-making process. Key actors around NLP management are politicians, ministries and scientists. Most contradictory perspectives and positions on non-intervention management are formulated by land users from the agricultural and forestry sectors who fear negative effects of this management approach.In this context, negotiations are a common governance approach to implement participatory elements; different actors have varying levels of importance within these participation processes.The large variety of influencing factors illustrates that policy outcomes do not singularly depend on legislative intervention. Besides actors and institutions, individual orientations and different contexts at a local level, as well as historical circumstance also need to be considered. To maintain or expand public acceptance, it is recommended that NLP administrations act with a high level of transparency and focus on expanded sharing of information.

Algorithmic TCAMs: Implementing Packet Classification Algorithms in Hardware

The adoption of cloud computing and the deployment of new services require more and more computing and networking resources in large data centers. In particular, there is a need for faster, rich featured switches. Today, switching integrated circuits can handle more than 50 Tb/s and are expected to reach 100 Tb/s next year. This trend is likely to continue, approaching petabit capacities in a few years. At the same time, switches need to support more advanced packet classification features. This poses many challenges to the designers of switching integrated circuits, creating a need for innovations to move forward. One of those challenges is to support programmable packet classification with large rulesets at wire speed using limited silicon footprint. Unfortunately, traditional solutions like ternary content addressable memories (TCAMs) have high cost in area and power, and therefore are not a viable option for large on-chip rulesets, so new alternatives are needed. In the last two decades, researchers have extensively studied the problem of packet classification, proposing many algorithms based on standard memories, mostly targeting software implementations. These packet classification algorithms could be a solution to enable large on-chip classification rulesets using standard memories. However, porting the standard packet classification algorithms to a hardware implementation is not a trivial task, due to the different requirements and the different kinds of memory and computing resources available on application-specific integrated circuit (ASIC) switching chips. This article describes a packet classification design tailored for high-speed switching integrated circuits, which is currently used in the NVIDIA® Mellanox® Spectrum® switching ASIC product line, illustrating how to solve the mismatch between the usual software-based classification algorithms and the specific requirements of a hardware implementation.

The third AI summer: AAAI Robert S. Engelmore Memorial Lecture

The third AI summer: AAAI Robert S. Engelmore Memorial Lecture

Application of Class Based Association Rule Pruning to Generate Optimal Association Rules in Healthcare

The association rule mining approach produces uninteresting association rules. When the set of association rules become large, it becomes less interesting to the user. In order to pick interesting association rules among peak volumes of found association rules, it is critical to aid the decision-maker with an efficient post-processing phase. Theymotivate the need for association analysis performance. Practically it is an overhead to analyze the large set of association rules. In this work, association rule pruning technique called Class Based Association Rule Pruning (CBARP). This pruning techniques is proposed to prune the weak association rules of the healthcare system. The results are compared with Semantic Tree Based Association Rule Mining (STAR) technique and it demonstrate that the CBARP method outperforms other methods for the given support values.

Rewrite rule inference using equality saturation

Many compilers, synthesizers, and theorem provers rely on rewrite rules to simplify expressions or prove equivalences. Developing rewrite rules can be difficult: rules may be subtly incorrect, profitable rules are easy to miss, and rulesets must be rechecked or extended whenever semantics are tweaked. Large rulesets can also be challenging to apply: redundant rules slow down rule-based search and frustrate debugging. This paper explores how equality saturation, a promising technique that uses e-graphs to apply rewrite rules, can also be used to infer rewrite rules. E-graphs can compactly represent the exponentially large sets of enumerated terms and potential rewrite rules. We show that equality saturation efficiently shrinks both sets, leading to faster synthesis of smaller, more general rulesets. We prototyped these strategies in a tool dubbed Ruler. Compared to a similar tool built on CVC4, Ruler synthesizes 5.8× smaller rulesets 25× faster without compromising on proving power. In an end-to-end case study, we show Ruler-synthesized rules which perform as well as those crafted by domain experts, and addressed a longstanding issue in a popular open source tool.

MoMAC: Multi-objective optimization to combine multiple association rules into an interpretable classification

A crucial characteristic of machine learning models in various domains (such as medical diagnosis, financial analysis, or real-time process monitoring) is the interpretability. The interpretation supports humans in understanding the meaning behind every single prediction made by the machine, and enables the user to assess trustworthiness before acting on the predictions. This article presents our work in building an interpretable classification model based on association rule mining and multi-objective optimization. The classification model itself is a rule list, making a single prediction based on multiple rules. The rule list consists of If ... THEN statements that are understandable to humans. We choose these rules from a large set of pre-mined rules according to an interestingness measure which is formulated as a function of basic probabilities related to the rules. We learned the interestingness measure through multi-objective optimization, concentrating on two objectives: the classifier’s size in terms of number of rules and prediction accuracy. The model is called MoMAC, “Multi-Objective optimization to combine Multiple Association rules into an interpretable Classification”. The experimental results on benchmark datasets demonstrate that MoMAC outperforms other existing rule-based classification methods in terms of classification accuracy.

Simple method of selecting totalistic rules for pseudorandom number generator based on nonuniform cellular automaton

This paper is devoted to selecting rules for one-dimensional (1D) totalistic cellular automaton (TCA). These rules are used for the generation of pseudorandom sequences, which could be useful in cryptography. The power of pseudorandom number generator (PRNG) based on nonuniform TCA can be improved using not only one rule but a large set of rules. For this purpose, each subset of rules should be analyzed with its assignation to cellular automaton (CA) cells should be analyzed. We examine each of the subsets of totalistic rules, consisting of rules with neighborhood radius equal to 1 and 2. The entropy of bitstreams generated by the nonuniform TCA points out the best set of rules appropriate for the TCA-based generator. The paper also presents the method of simple selection of CA rules based on a cryptographic criterion known as a balance. The proposed method selects a maximal size of the set of available CA rules for a given neighborhood radius and suitable for PRNG. The method guarantees to avoid conflicting assignments of rules resulting in the creation of unwanted stable bit sequences, and provides high-quality pseudorandom sequences. This technique is used to verify the subsets of rules selected experimentally. Verified rules are proposed for 1D TCA-based PRNG as a new subset of best nonuniform TCA rules. New picked, examined, and verified subset of rules could be used in TCA-based PRNG and provide cryptographically strong bit sequences and huge keyspace.

MAINTENANCE LAYERS FOR RAILWAY INFRASTRUCTURE IN POLAND

The railway network in Poland with over 19000 km is one of the biggest in the European Union (EU). At the same time safety indicators collected by the European Union Agency for Railways (ERA) show that it is one of the least safe in Europe. Consequently, all the actions taken in safety management of Polish Railways are particularly important for the society. In 2015, there was a change in the main infrastructure manager’s rulebook on track maintenance. A new process rule was introduced to replace a large set of long-established action rules. However, supervision reports of the Polish National Safety Authority indicate that the new rule is not used properly. Therefore, the current process of taking maintenance decisions on Polish Railways was described and a novel concept of maintenance layers and Maintenance Board meetings was proposed. The change would allow to choose the order of maintenance activities in a more objective way than it is done nowadays, without the necessity to make any major investments.

CACDA: A knowledge graph for a context-aware cognitive design assistant

The design of complex engineered systems highly relies on a laborious zigzagging between computer-aided design (CAD) software and design rules prescribed by design manuals. Despite the emergence of knowledge management techniques (ontology, expert system, text mining, etc.), companies continue to store design rules in large and unstructured documents. To facilitate the integration of design rules and CAD software, we propose a knowledge graph that structures a large set of design rules in a computable format. The knowledge graph organises entities of design rules (nodes), relationships among design rules (edges), as well as contextual information. The categorisation of entities and relationships in four sub-contexts: semantic, social, engineering, and IT – facilitates the development of the data model, especially the definition of the “design context” concept. The knowledge graph paves the way to a context-aware cognitive design assistant. Indeed, connected to or embedded in a CAD software, a context-aware cognitive design assistant will capture the design context in near real time and run reasoning operations on the knowledge graph to extend traditional CAD capabilities, such as the recommendation of design rules, the verification of design solutions, or the automation of design routines. Our validation experiment shows that the current version of the context-aware cognitive design assistant is more efficient than the traditional document-based design. On average, participants using an unstructured design rules document have a precision of 0.36 whereas participants using our demonstrator obtain a 0.61 precision score. Finally, designers supported by the design assistant spend more time designing than searching for applicable design rules compared to the traditional design approach.

A Fast, Smart Packet Classification Algorithm Based on Decomposition

Packet classification algorithms have been the focus of research for the last few years, due to the vital role they play in various services based on packet forwarding. However, as the number of rules in the rule set increases, not only the preprocessing time but also the memory consumption is increasing greatly. In this paper, we first model and analyze the above issue in depth. Then, a fast, smart packet classification algorithm based on decomposition is proposed. By boundary-based rule traversal and smart rule set partitioning, both the preprocessing time and memory consumption are reduced dramatically. Experimental results show that the preprocessing time of our method achieves 8.8-time improvement at maximum compared with the PCIU and achieves about 31.5-time improvement on average compared with CutSplit for large rule sets. Meanwhile, the memory overhead is reduced by 40% at maximum and 27.5% on average compared with the PCIU.

A Rule-Based Data Quality Assessment System for Electronic Health Record Data.

Rule-based data quality assessment in health care facilities was explored through compilation, implementation, and evaluation of 63,397 data quality rules in a single-center case study to assess the ability of rules-based data quality assessment to identify data errors of importance to physicians and system owners. We applied a design science framework to design, demonstrate, test, and evaluate a scalable framework with which data quality rules can be managed and used in health care facilities for data quality assessment and monitoring. We identified 63,397 rules partitioned into 28 logic templates. A total of 819,683 discrepancies were identified by 4.5% of the rules. Nine out of 11 participating clinical and operational leaders indicated that the rules identified data quality problems and articulated next steps that they wanted to take based on the reported information. The combined rule template and knowledge table approach makes governance and maintenance of otherwise large rule sets manageable. Identified challenges to rule-based data quality monitoring included the lack of curated and maintained knowledge sources relevant to data error detection and lack of organizational resources to support clinical and operational leaders with investigation and characterization of data errors and pursuit of corrective and preventative actions. Limitations of our study included implementation within a single center and dependence of the results on the implemented rule set. This study demonstrates a scalable framework (up to 63,397 rules) with which data quality rules can be implemented and managed in health care facilities to identify data errors. The data quality problems identified at the implementation site were important enough to prompt action requests from clinical and operational leaders.

Knowledge redundancy approach to reduce size in association rules

Association Rules Mining is one of the most studied and widely applied fields in Data Mining. However, the discovered models usually result in a very large set of rules; so the analysis capability, from the user point of view, is diminishing. Hence, it is difficult to use the found model in order to assist decision-making process. The previous handicap is heightened in presence of redundant rules in the final set. In this work a new definition of redundancy in association rules is proposed, based on user prior knowledge. A post-processing method is developed to eliminate this kind of redundancy, using association rules known by the user. Our proposal allows to find more compact models of association rules to ease its use in the decision-making process. The developed experiments have shown reduction levels that exceed 90 percent of all generated rules, using prior knowledge always below ten percent. So, our method improves the efficiency of association rules mining and the exploitation of discovered association rules.

Learning rule sets and Sugeno integrals for monotonic classification problems

In some variants of the supervised classification setting, the domains of attributes and the set of classes are totally ordered sets. The task of learning a classifier that is nondecreasing w.r.t. each attribute is called monotonic classification. Several kinds of models can be used in this task; in this paper, we focus on decision rules. We propose a method for learning a set of decision rules that optimally fits the training data while favoring short rules over long ones. We give new results on the representation of sets of if-then rules by extensions of Sugeno integrals to distinct attribute domains, where local utility functions are used to map attribute domains to a common totally ordered scale. We study whether such qualitative extensions of Sugeno integral provide compact representations of large sets of decision rules.

A COMPREHENSIVE SURVEY ON THE COMPUTATIONAL INTELLIGENCE TECHNIQUES AND ITS APPLICATIONS

The artificial intelligence that tries to imitate the human beings by gathering a vast knowledge gained using the reasoning, planning, searching and prediction fails in certain areas that necessitate a construction of large set of rules. The AI also faces challenges due to the growing demands in the learning and the search optimization. These failures of AI paved a path for the growth of the computational tools that led to the rise of the new regimen that is the computational intelligence. The paper presents the comprehensive survey of the computational intelligent techniques and its applications as they seem to be an effective alternative for the artificial intelligence overcoming the failures and the draw backs in it.

Knowledge Refinement via Rule Selection

In several different applications, including data transformation and entity resolution, rules are used to capture aspects of knowledge about the application at hand. Often, a large set of such rules is generated automatically or semi-automatically, and the challenge is to refine the encapsulated knowledge by selecting a subset of rules based on the expected operational behavior of the rules on available data. In this paper, we carry out a systematic complexity-theoretic investigation of the following rule selection problem: given a set of rules specified by Horn formulas, and a pair of an input database and an output database, find a subset of the rules that minimizes the total error, that is, the number of false positive and false negative errors arising from the selected rules. We first establish computational hardness results for the decision problems underlying this minimization problem, as well as upper and lower bounds for its approximability. We then investigate a bi-objective optimization version of the rule selection problem in which both the total error and the size of the selected rules are taken into account. We show that testing for membership in the Pareto front of this bi-objective optimization problem is DP-complete. Finally, we show that a similar DP-completeness result holds for a bi-level optimization version of the rule selection problem, where one minimizes first the total error and then the size.

An approach to enhance packet classification performance of software-defined network using deep learning

Packet classification in software-defined network has become more important with the rapid growth of Internet. Existing approaches focused on the data structure algorithms to classify the packets. But the existing algorithms lead to the problem of time budget and fails to accommodate large rule sets. Thus the key task is to design an algorithm for packet classification that inflicts process overhead, and the algorithm should handle large databases of classification rule. These challenging issues are achieved by proposing rectified linear unit deep neural network. The aim of this work is twofold. First various hyper-parameter values are analyzed in order to examine how they affect the packet classification performance of deep neural network; and their performance is compared with that of popular methods, e.g., K-nearest neighbor and support vector machines. The open-source TensorFlow deep learning framework with the support of NVidia GPU units is used to carry out this work, thus allowing a large number of rules to predict the exact flow. The result shows that the proposed method performs well, and hence, this model is more suitable for large classification rules.

Extending knowledge based redundancy in association rules with imprecise knowledge

Association Rules Mining is one of the most studied and widely applied fields in Data Mining. However, the discovery models usually result in a very large set of rules; so the analysis capability, from the user point of view, is diminishing. Hence, it is difficult to use the found model in order to assist decision-making process. The previous handicap is heightened in presence of redundant rules in the final set. In this work we study a way to eliminate redundancy in association rules with uncertainty, with imprecise user prior knowledge. A post-processing method is developed to eliminate this kind of redundancy, using association rules known by the user. Our proposal allows to find more compact models of association rules to ease its use in the decision-making process. The developed experiments have shown that the reduction using certainty factor has a slightly better behavior. The most important contribution of this paper is the definition of a mechanism to remove knowledge based redundancy using Dempster-Schaffer Theory and the Certainty Factor Model

Expert transmission assisted-healing system application based on alarms and real-time measurements

Transmission system restoration is a critical task which requires agility and safety. On the one hand, the restoration proceedings, composed of numerous documents, establish the sequence and its preconditions that must be observed before the execution of each action. On the other hand, a significant amount of information, such as alarms and protection signals, fills the operator’s HMI and causes an effect known as “alarm avalanche.” The time spent to understand all of this information impacts the result of the restoration, while any erroneous preconditions assessment can undermine the restoration process. In order to conduct an efficient restoration process for power transmission systems which improves both security and agility, an online decision support system inspired by assisted-healing approach is proposed. The system is also based on the expert systems methodology through which the inputs (alarms, state of circuit breakers, protection signals, and operation proceedings) are submitted to a large set of rules (a multilayer inference engine) to be transformed into intelligible outputs for operators. These outputs instantaneously give operators the full set of conclusions necessary for decision making with the advantage of preventing misunderstandings. This paper presents an applied research whose results and simulations performed at Cemig Generation and Transmission show that it is possible to automate the processing of all these data so that operators have better information to make decisions during these critical situations.