Boolean Rules Research Articles

Abstract C10: IT-enabled clinical cognitive support for differential diagnosis improvement, treatment planning and medical mistake mitigation

Abstract (a) This poster describes background, purpose, scope, structure and function of the Cloud Healthcare Appliance Real-Time (CHART) solution as a service; which is a conceptual suite of information technology (IT) analytics and middleware software, deployed in “the cloud” (i.e. - an Internet-accessible and professionally managed data center) and accessible by licensed healthcare provider subscriber subject matter experts via a secure portal; for the purpose of designing, developing and deploying automated use cases for cognitive support of medical practice and healthcare delivery (e.g. -- differential diagnosis and treatment planning, medical technology alarm/alert fatigue mitigation, patient course-in-treatment management) with minimal cost and complexity. (b) The procedure consists of use case automation design (including definition of required complex event monitoring, natural language-based case/evidence acquisition, Bayesian similarity and predictive analysis, Boolean decision rules, process flow including activities and staff/system actors, and key performance indicator-based process monitoring and continuous improvement enablement) using non-programming techniques such as drag-and-drop; development (including process connectivity to existing provider electronic health records a.k.a. EHRs and other Internet-accessible data sources and services using software-defined networking and HIPAA-compliant encryption/de-identification) with minimal IT professional assistance; and deployment via desktop and mobile digital data devices. The included software already is production-proven in other industries worldwide, so the typical high cost and risk associated with software development projects is avoided. The proposed poster will describe the implementation and utilization of the vendor-agnostic CHART; and how the clinical cognitive support it provides will improve accuracy and speed of oncology diagnosis, will mitigate medical mistakes, will facilitate progress from iterative to sequential treatment through integration of the clinical care and medical learning processes (re Bohner RMJ, “Designing Care …,” Harvard Business Press, Boston, 2009, pp. 128-150), and will ensure much-improved economy, efficiency and effectiveness and for healthcare providers. (c) All available data/information re CHART is available at the web site (www.chartsaas.org) or in the form of presentations (e.g. -- http://bit.ly/28St6MM) and other collateral such as grand rounds solution sheets re central line acquired blood stream infection (CLABSI) and white papers. For example, the benefit of CHART vis a vis the hand-off/sign-out problem (http://1.usa.gov/28UVuAA), is described in our recent Becker's Hospital Review article (http://bit.ly/24k0zov). (d) The urgent need for IT-enabled clinical cognitive support for differential diagnosis improvement, treatment planning and medical mistake mitigation (and most other healthcare provider challenges) can be rationalized as follows: BECAUSE .25M U.S. patients die every year from medical mistake mitigation (http://bit.ly/1rtW6Sa); AND medical mistakes happen because healthcare complexity creates cognitive overload (http://1.usa.gov/291u3mr); THEREFORE cognitive overload requires cognitive support for healthcare providers (http://1.usa.gov/1JXulDM , in particular the testimony of Tejal Gandhi, MD, MPH and Peter Pronovost, MD, PhD); AND healthcare providers need the cognitive support that only information technology (IT) can provide for information management, decision support and process improvement as provided by the CHART solution as a service. Although CHART is only a concept at this point in time, its structure and function have been realized for the most part by commercial off the shelf (COTS) cloud-based intelligent business process management suites (CiBPMS, re http://gtnr.it/28RSLE1). Note: This abstract was not presented at the conference. Citation Format: John Peter Melrose. IT-enabled clinical cognitive support for differential diagnosis improvement, treatment planning and medical mistake mitigation. [abstract]. In: Proceedings of the Ninth AACR Conference on the Science of Cancer Health Disparities in Racial/Ethnic Minorities and the Medically Underserved; 2016 Sep 25-28; Fort Lauderdale, FL. Philadelphia (PA): AACR; Cancer Epidemiol Biomarkers Prev 2017;26(2 Suppl):Abstract nr C10.

A new multiple seeds based genetic algorithm for discovering a set of interesting Boolean association rules

Association rule mining algorithms mostly use a randomly generated single seed to initialize a population without paying attention to the effectiveness of that population in evolutionary learning. Recently, research has shown significant impact of the initial population on the production of good solutions over several generations of a genetic algorithm. Single seed based genetic algorithms suffer from the following major challenges (1) solutions of a genetic algorithm are varied, since different seeds generate different initial population, (2) difficulty in defining a good seed for a specific application. To avoid these problems, in this paper we propose the MSGA, a new multiple seeds based genetic algorithm which generates multiple seeds from different domains of a solution space to discover high quality rules from a large data set. This scheme introduces m-domain model and m-seeds selection process through which the whole solution space is subdivided into m- number of same size domains, selecting a seed from each domain. Use of these seeds enables this method to generate an effective initial population for evolutionary learning of the fitness value of each rule. As a result, strong searching efficiency is obtained at the beginning of the evolution, achieving fast convergence. The MSGA is tested with different mutation and crossover operators for mining interesting Boolean association rules from four real world data sets. The results are compared to different single seeds based genetic algorithms under the same conditions.

3D medical data security protection

A novel encryption protocol for 3D biomedical objects is introduced in this work. This method consists of two phases which are iteratively applied: the confusion phase and the diffusion phase. In the confusion phase the position of the voxels are permuted by means of a discretized chaotic map, whereas in the diffusion phase the value of each voxel is changed. The diffusion phase is divided into two sub phases: in the first one a memory reversible 3D cellular automata is applied using the 3D object as the initial conditions, and in the second sub phase, a discrete dynamical system with delay defined by a non-linear boolean function is applied to the output of the evolution of the cellular automaton. The protocol is shown to be secure against the most important cryptanalytic attacks.The impact and novelty of this method lies on directly ciphering the 3D objects and considering these objects as the aggregation of voxels. Moreover, this allows to design a new and efficient encryption algorithm which is the generalization of those methods to encrypt digital images that are based on the iteration of a confusion and a diffusion phase.The use of cellular automata and boolean transition rules in the diffusion phase opens new possibilities for the use of expert and intelligence systems in cryptography since cellular automata can be used and inference machines.

A New Feature Selection Method for Oral Cancer Using Data Mining Techniques

2 Abstract: The term cancer is used generically for more than 100 different diseases including malignant tumours of different sites (such as breast, cervix, prostate, stomach, colon/rectum, lung, mouth, leukaemia, sarcoma of bone, Hodgkin disease, and non-Hodgkin lymphoma). Common to all forms of the disease is the failure of the mechanisms that regulate normal cell growth, proliferation and cell death. Ultimately, there is progression of the resulting tumour from mild to severe abnormality, with invasion of neighbouring tissues and, eventually, spread to other areas of the body. The primary risk factor for developing oral cancer is tobacco use. Smoking cigarettes, cigars, and pipes all increase risk of oral cancer. Smokeless tobacco, often called dip or chew, also heighten the risk. Alcohol consumption is another habit that is strongly associated with the development of oral cancer. This research uses data mining technology such as classification, clustering and prediction to identify potential oral cancer patients.Apriori algorithm is the originality algorithm of Boolean association rules of mining frequent item sets. The datamining methods and techniques will be explored to identify the suitable methods and techniques for efficient classificationof data.The data mining techniques are effectively used to extract meaningful relationships fromthese data. Genetic algorithms were applied to association and classification techniques.

Boolean Modeling of Cellular and Molecular Pathways Involved in Influenza Infection.

Systems virology integrates host-directed approaches with molecular profiling to understand viral pathogenesis. Self-contained statistical approaches that combine expression profiles of genes with the available databases defining the genes involved in the pathways (gene-sets) have allowed characterization of predictive gene-signatures associated with outcome of the influenza virus (IV) infection. However, such enrichment techniques do not take into account interactions among pathways that are responsible for the IV infection pathogenesis. We investigate dendritic cell response to seasonal H1N1 influenza A/New Caledonia/20/1999 (NC) infection and infer the Boolean logic rules underlying the interaction network of ligand induced signaling pathways and transcription factors. The model reveals several novel regulatory modes and provides insights into mechanism of cross talk between NFκB and IRF mediated signaling. Additionally, the logic rule underlying the regulation of IL2 pathway that was predicted by the Boolean model was experimentally validated. Thus, the model developed in this paper integrates pathway analysis tools with the dynamic modeling approaches to reveal the regulation between signaling pathways and transcription factors using genome-wide transcriptional profiles measured upon influenza infection.

Efficient reduction and modularization for large fault trees stored by pages

Fault Tree Analysis (FTA), an indispensable tool used in Probabilistic Risk Assessment (PRA), has been used throughout the commercial nuclear power industry for safety and reliability analyses. However, large fault tree analysis, such as those used in nuclear power plant requires significant computer resources, which makes the analysis of PRA model inefficient and time consuming. This paper describes a fault tree pre-processing method used in the reliability and probabilistic safety assessment program RiskA that is capable of generating minimal cutsets for fault trees containing more than 10,000 gates and basic events. The novel feature of this method is not only that Boolean reduction rules are used but also that a new objective of simplification is proposed. Moreover, since the method aims to find more fault tree modules by the linear-time algorithm, it can optimize fault tree modularization, which further reduces the computational time of large fault tree analysis.

Optimal percentage of inhibitory synapses in multi-task learning.

Performing more tasks in parallel is a typical feature of complex brains. These are characterized by the coexistence of excitatory and inhibitory synapses, whose percentage in mammals is measured to have a typical value of 20-30%. Here we investigate parallel learning of more Boolean rules in neuronal networks. We find that multi-task learning results from the alternation of learning and forgetting of the individual rules. Interestingly, a fraction of 30% inhibitory synapses optimizes the overall performance, carving a complex backbone supporting information transmission with a minimal shortest path length. We show that 30% inhibitory synapses is the percentage maximizing the learning performance since it guarantees, at the same time, the network excitability necessary to express the response and the variability required to confine the employment of resources.

Finding Contextual Term from Index of Documents using Apriori Algorithm

Data mining is a multidisciplinary field that has mainly introduced to process large database and discover useful information that could help in decision making. World Wide Web is a vast resource of interlinked hypertext documents which are accessed via the Internet. Web mining, an extension of data mining, employs techniques of data mining to documents on the internet. Association rule mining is a major technique in the area of data mining. Association rule mining finds frequent itemsets from a set of transactional databases. Apriori algorithm is one of the earliest algorithm of association rule mining. Apriori employs an iterative approach known as levelwise search.. The Apriori Algorithm for mining frequent itemsets for boolean association rules can be applied to the index file of a search engine to find contextually related terms i.e the terms which occur in number of documents together. Ranking, a major component of a search engine ranks the web pages based on some criteria. The ranking algorithms consider the keywords entered in the query for rank purpose. Considering contextually related terms with query term can improve the ranking system. In this paper it is shown how apriori algorithm can be applied on index of web documents to find contextually related terms. General Terms Ranking ,apriori algorithm.

Construction of robust dynamic genome-scale metabolic model structures of Saccharomyces cerevisiae through iterative re-parameterization

Dynamic flux balance analysis (dFBA) has been widely employed in metabolic engineering to predict the effect of genetic modifications and environmental conditions in the cell׳s metabolism during dynamic cultures. However, the importance of the model parameters used in these methodologies has not been properly addressed. Here, we present a novel and simple procedure to identify dFBA parameters that are relevant for model calibration. The procedure uses metaheuristic optimization and pre/post-regression diagnostics, fixing iteratively the model parameters that do not have a significant role. We evaluated this protocol in a Saccharomyces cerevisiae dFBA framework calibrated for aerobic fed-batch and anaerobic batch cultivations. The model structures achieved have only significant, sensitive and uncorrelated parameters and are able to calibrate different experimental data. We show that consumption, suboptimal growth and production rates are more useful for calibrating dynamic S. cerevisiae metabolic models than Boolean gene expression rules, biomass requirements and ATP maintenance.

Minimal metabolic pathway structure is consistent with associated biomolecular interactions.

Pathways are a universal paradigm for functionally describing cellular processes. Even though advances in high-throughput data generation have transformed biology, the core of our biological understanding, and hence data interpretation, is still predicated on human-defined pathways. Here, we introduce an unbiased, pathway structure for genome-scale metabolic networks defined based on principles of parsimony that do not mimic canonical human-defined textbook pathways. Instead, these minimal pathways better describe multiple independent pathway-associated biomolecular interaction datasets suggesting a functional organization for metabolism based on parsimonious use of cellular components. We use the inherent predictive capability of these pathways to experimentally discover novel transcriptional regulatory interactions in Escherichia coli metabolism for three transcription factors, effectively doubling the known regulatory roles for Nac and MntR. This study suggests an underlying and fundamental principle in the evolutionary selection of pathway structures; namely, that pathways may be minimal, independent, and segregated.

An inspection and classification method for chip solder joints using color grads and Boolean rules

In order to improve the comprehensive performance of solder joints inspection in three aspects, i.e. high recognition rate, detailed classification of defect types and fast inspection speed, a new detection and classification algorithm of the chip solder joints based on color grads and Boolean rules is developed in this paper. Firstly, the region features, evaluation features and color grads’ features are defined and extracted based on the special solder joint image, which is acquired by a particular image acquisition system composed of a 3-CCD color digital camera and a 3-color (red, green, and blue) hemispherical LED array illumination. Secondly, the models of solder joint types are built based on extracted features and statistical characteristics of solder joint types. Thirdly, the detection and classification method is designed and presented using Boolean rules, then eight common solder joint types, including the acceptable solder joint, pseudo, no solder, lacked solder, excess solder, shifted, tombstone, and miss component, can be classified and detected by the proposed algorithm. Fourthly, the proposed algorithm is optimized to improve the inspection speed based on a parallel computing method. Finally, to evaluate the performance of the proposed method, 79 pieces of PCBs with defects were inspected by the commercial AOI system developed by the authors which integrates the proposed algorithm. Experiment and result analysis illustrates that the proposed method is better than other methods in three aspects, it can detect and classify properly all the eight common types of solder joints, its detailed classification, and high correct rate, which is up to 97.7%, are more useful to the quality control in the manufacturing process, and its inspection speed is faster, thus helping us to improve the efficiency of the manufacturing process.

A Novel Web Classification Algorithm Using Fuzzy Weighted Association Rules

In associative classification method, the rules generated from association rule mining are converted into classification rules. The concept of association rule mining can be extended in web mining environment to find associations between web pages visited together by the internet users in their browsing sessions. The weighted fuzzy association rule mining techniques are capable of finding natural associations between items by considering the significance of their presence in a transaction. The significance of an item in a transaction is usually referred as the weight of an item in the transaction and finding associations between such weighted items is called fuzzy weighted association rule mining. In this paper, we are presenting a novel web classification algorithm using the principles of fuzzy association rule mining to classify the web pages into different web categories, depending on the manner in which they appear in user sessions. The results are finally represented in the form of classification rules and these rules are compared with the result generated using famous Boolean Apriori association rule mining algorithm.

Creation of Fuzzy Control Table with Data Mining

A good fuzzy control table is the key to a fuzzy control system, and the systems performance mainly depends on the quality of the table. Based on analyzing fully the principles of a typical fuzzy control systems and the procedures of building a fuzzy control table, this paper presents a new method of applying the boolean association rule data mining techniques to mining of fuzzy control table directly from the database of manual operating records.

Novel Method of Apriori Algorithm using Top Down Approach

Association Rule mining is one of the important and most popular data mining techniques. It extracts interesting correlations, frequent patterns and associations among sets of items in the transaction databases or other data repositories. Apriori algorithm is an influential algorithm for mining frequent itemsets for Boolean association rules. Firstly, the concept of association rules is introduced and the classic algorithms of association rule are analyzed. In Apriori algorithm, most time is consumed for scanning the database repeatedly. Therefore, the methods are presented about improving the Apriori algorithm efficiency, which reduces a lot of time of scanning database and shortens the computation time of the algorithm.

Percolation on Interdependent Networks with a Fraction of Antagonistic Interactions

Recently, the percolation transition has been characterized on interacting networks both in presence of interdependent and antagonistic interactions. Here we characterize the phase diagram of the percolation transition in two Poisson interdependent networks with a percentage q of antagonistic nodes. We show that this system can present a bistability of the steady state solutions, and both first, and second order phase transitions. In particular, we observe a bistability of the solutions in some regions of the phase space also for a small fraction of antagonistic interactions 0<q<0.4. Moreover, we show that a fraction q>q_c=2/3 of antagonistic interactions is necessary to strongly reduce the region in phase-space in which both networks are percolating. This last result suggests that interdependent networks are robust to the presence of antagonistic interactions. Our approach can be extended to multiple networks, and to complex boolean rules for regulating the percolation phase transition.

An Evaluation of Methods for Inferring Boolean Networks from Time-Series Data

Regulatory networks play a central role in cellular behavior and decision making. Learning these regulatory networks is a major task in biology, and devising computational methods and mathematical models for this task is a major endeavor in bioinformatics. Boolean networks have been used extensively for modeling regulatory networks. In this model, the state of each gene can be either ‘on’ or ‘off’ and that next-state of a gene is updated, synchronously or asynchronously, according to a Boolean rule that is applied to the current-state of the entire system. Inferring a Boolean network from a set of experimental data entails two main steps: first, the experimental time-series data are discretized into Boolean trajectories, and then, a Boolean network is learned from these Boolean trajectories. In this paper, we consider three methods for data discretization, including a new one we propose, and three methods for learning Boolean networks, and study the performance of all possible nine combinations on four regulatory systems of varying dynamics complexities. We find that employing the right combination of methods for data discretization and network learning results in Boolean networks that capture the dynamics well and provide predictive power. Our findings are in contrast to a recent survey that placed Boolean networks on the low end of the “faithfulness to biological reality” and “ability to model dynamics” spectra. Further, contrary to the common argument in favor of Boolean networks, we find that a relatively large number of time points in the time-series data is required to learn good Boolean networks for certain data sets. Last but not least, while methods have been proposed for inferring Boolean networks, as discussed above, missing still are publicly available implementations thereof. Here, we make our implementation of the methods available publicly in open source at http://bioinfo.cs.rice.edu/.

FARP: Mining fuzzy association rules from a probabilistic quantitative database

Current studies on association rule mining focus on finding Boolean/quantitative association rules from certain databases or Boolean association rules from probabilistic databases. However, little work on mining association rules from probabilistic quantitative databases has been mentioned because the simultaneous measurement of quantitative information and probability is difficult. By introducing a novel Shannon-like Entropy, we aggregate and measure the information contained in an item with the coexistence of fuzzy uncertainty hidden in quantitative values and random uncertainty. We then propose Support and Confidence metrics for a fuzzy–probabilistic database to quantify association rules. Finally, we design an algorithm, called FARP (mining Fuzzy Association Rules from a Probabilistic quantitative data), to discover frequent fuzzy–probabilistic itemsets and fuzzy association rules using the proposed interest measures. The experimental results show the effectiveness of our method and its practicality in real-world applications.

Boolean Algebra for Xor-Gates

Rules and laws of Boolean algebra are very essential for the simplification of a long and complex logic equation. Applying the Boolean algebra basic concept, such a kind of logic equation could be simplified in a more simple and efficient form.Mainly, the standard rules of Boolean algebra are given in operator ‘+’ and ‘x’, based on the AND and OR logic gates equations. For some logic designs, it is commonly that logic problems are writtenin terms of XOR format.This paper tries to conduct something different. It will analyze, describe, and derive Boolean algebra rules related to logic equations using exclusive-or (XOR) logic gate.

Versatile antibody-sensing Boolean logic for the simultaneous detection of multiple bacterial toxins

We present an OR gate based on monoclonal antibodies for the simultaneous detection of multiple toxins in a single tube. To further simplify the operating procedure, the Boolean rule of simplification was used to guide the selection of a marker toxin among the natural toxin profiles.

Weighted Association Rules Mining Algorithm Research

Aiming at the problem that most of weighted association rules mining algorithms have not the anti-monotonicity, this paper presents a weighted support-confidence framework which supports anti-monotonicity. On this basis, weighted boolean association rules mining algorithm and weighted fuzzy association rules mining algorithm are presented, which use pruning strategy of Apriori algorithm so that improve the efficiency of frequent itemsets generated. Experimental results show that both algorithms have good performance.