Boolean Features Research Articles

Host genetics and COVID-19 severity: increasing the accuracy of latest severity scores by Boolean quantum features.

The impact of common and rare variants in COVID-19 host genetics has been widely studied. In particular, in Fallerini et al. (Human genetics, 2022, 141, 147-173), common and rare variants were used to define an interpretable machine learning model for predicting COVID-19 severity. First, variants were converted into sets of Boolean features, depending on the absence or the presence of variants in each gene. An ensemble of LASSO logistic regression models was used to identify the most informative Boolean features with respect to the genetic bases of severity. After that, the Boolean features, selected by these logistic models, were combined into an Integrated PolyGenic Score (IPGS), which offers a very simple description of the contribution of host genetics in COVID-19 severity.. IPGS leads to an accuracy of 55%-60% on different cohorts, and, after a logistic regression with both IPGS and age as inputs, it leads to an accuracy of 75%. The goal of this paper is to improve the previous results, using not only the most informative Boolean features with respect to the genetic bases of severity but also the information on host organs involved in the disease. In this study, we generalize the IPGS adding a statistical weight for each organ, through the transformation of Boolean features into "Boolean quantum features," inspired by quantum mechanics. The organ coefficients were set via the application of the genetic algorithm PyGAD, and, after that, we defined two new integrated polygenic scores ( and ). By applying a logistic regression with both IPGS, ( (or indifferently ) and age as inputs, we reached an accuracy of 84%-86%, thus improving the results previously shown in Fallerini et al. (Human genetics, 2022, 141, 147-173) by a factor of 10%.

Small world of the miRNA science drives its publication dynamics.

Many scientific articles became available in the digital form which allows for querying articles data, and specifically the automated metadata gathering, which includes the affiliation data. This in turn can be used in the quantitative characterization of the scientific field, such as organizations identification, and analysis of the co-authorship graph of those organizations to extract the underlying structure of science. In our work, we focus on the miRNA science field, building the organization co-authorship network to provide the higher-level analysis of scientific community evolution rather than analyzing author-level characteristics. To tackle the problem of the institution name writing variability, we proposed the k-mer/n-gram boolean feature vector sorting algorithm, KOFER in short. This approach utilizes the fact that the contents of the affiliation are rather consistent for the same organization, and to account for writing errors and other organization name variations within the affiliation metadata field, it converts the organization mention within the affiliation to the K-Mer (n-gram) Boolean presence vector. Those vectors for all affiliations in the dataset are further lexicographically sorted, forming groups of organization mentions. With that approach, we clustered the miRNA field affiliation dataset and extracted unique organization names, which allowed us to build the co-authorship graph on the organization level. Using this graph, we show that the growth of the miRNA field is governed by the small-world architecture of the scientific institution network and experiences power-law growth with exponent 2.64 ± 0.23 for organization number, in accordance with network diameter, proposing the growth model for emerging scientific fields. The first miRNA publication rate of an organization interacting with already publishing organization is estimated as 0.184 ± 0.002 year-1.

Spider Plus: A Text Classifier for Research Article Components

Uploading research articles to a database can be a complex process with multiple HTML fields. The complexity of this process makes users less efficient and productive. This study explored the use of the Multilayer Perceptron (MLP) algorithm using language-independent features (count and Boolean features) to create a multi-class text classifier that can classify 10 research article components (e.g., title, authors, abstract, etc.). The text classifier was developed to pave the way for a streamlined manual data entry process for uploading research articles to a database by implementing a single textarea in favor of using multiple HTML fields. The text samples were obtained from multiple sources using web scraping technology, consolidated, cleaned, and standardized. The 12 language-independent features were generated based on the textual formats of sample texts (e.g., count of capitalized letters, digits, punctuation, checking the existence of a URL pattern, etc.). Recursive feature elimination with cross validation (RFECV) was used to determine the optimal number of input features. The hyperparameter values of the model were determined through the grid search technique. A trial-and-error process was conducted to determine the number of hidden layers. The model achieved 95%, 94%, and 95% scores for micro, macro, and weighted average f1-scores, respectively. The model performed well in classifying research article components. However, it is sensitive to textual format (e.g., lower or upper case, punctuation used, etc.). For subsequent research in this area, this study recommends investigating the use of both language-dependent and language-independent features to address the limitations of the current model.

Multi-Angle Fast Neural Tangent Kernel Classifier

Multi-kernel learning methods are essential kernel learning methods. Still, the base kernel functions in most multi-kernel learning methods only with select kernel functions with shallow structures, which are weak for large-scale uneven data. We propose two types of acceleration models from a multidimensional perspective of the data: the neural tangent kernel (NTK)-based multi-kernel learning method is proposed, where the NTK kernel regressor is shown to be equivalent to an infinitely wide neural network predictor, and the NTK with deep structure is used as the base kernel function to enhance the learning ability of multi-kernel models; and a parallel computing kernel model based on data partitioning techniques. An RBF, POLY-based multi-kernel model is also proposed. All models use historical memory-based PSO (HMPSO) for efficient search of parameters within the model. Since NTK has a multi-layer structure and thus has a significant computational complexity, the use of a Monotone Disjunctive Kernel (MDK) to store and train Boolean features in binary achieves a 15–60% training time compression of NTK models in different datasets while obtaining a 1–25% accuracy improvement.

Provable Boolean interaction recovery from tree ensemble obtained via random forests

Random Forests (RFs) are at the cutting edge of supervised machine learning in terms of prediction performance, especially in genomics. Iterative RFs (iRFs) use a tree ensemble from iteratively modified RFs to obtain predictive and stable nonlinear or Boolean interactions of features. They have shown great promise for Boolean biological interaction discovery that is central to advancing functional genomics and precision medicine. However, theoretical studies into how tree-based methods discover Boolean feature interactions are missing. Inspired by the thresholding behavior in many biological processes, we first introduce a discontinuous nonlinear regression model, called the “Locally Spiky Sparse” (LSS) model. Specifically, the LSS model assumes that the regression function is a linear combination of piecewise constant Boolean interaction terms. Given an RF tree ensemble, we define a quantity called “Depth-Weighted Prevalence” (DWP) for a set of signed features S±. Intuitively speaking, DWP(S±) measures how frequently features in S± appear together in an RF tree ensemble. We prove that, with high probability, DWP(S±) attains a universal upper bound that does not involve any model coefficients, if and only if S± corresponds to a union of Boolean interactions under the LSS model. Consequentially, we show that a theoretically tractable version of the iRF procedure, called LSSFind, yields consistent interaction discovery under the LSS model as the sample size goes to infinity. Finally, simulation results show that LSSFind recovers the interactions under the LSS model, even when some assumptions are violated.

Several lifted abstract domains for static analysis of numerical program families

Lifted ( family-based ) static analysis based on abstract interpretation is capable of analyzing all variants of a program family (or any other configurable software system), simultaneously, in a single run without generating any of the variants explicitly. The elements of the underlying lifted domain are tuples, which maintain one property per system variant. Still, explicit property enumeration in tuples, one by one for all variants, immediately yields combinatorial explosion. This is particularly apparent in the case of program families that, apart from Boolean features, contain also numerical features with large domains, thus giving rise to astronomical configuration spaces. The key for an efficient lifted analysis is a proper handling of variability-specific constructs of the language (e.g., feature-based runtime tests and #if directives). In this work, we introduce new symbolic representations of the lifted domain that can efficiently analyze program families with numerical features. This makes sharing between property elements corresponding to different variants explicitly possible. In the first approach, elements of the new lifted domain are decision trees , in which decision nodes are labeled with linear constraints defined over numerical features and the leaf nodes belong to an existing single-program analysis domain. The lifted domain is parametric in the choice of the domains for representing linear constraints and leaf nodes. Furthermore, we propose another alternative approach for efficient lifted analysis. We encode a program family with numerical features as a family with only Boolean features, and then use a BDD lifted domain to analyze the resulting program family. To illustrate the potential of our representations, we have implemented an experimental lifted static analyzer, called SPLNum 2 Analyzer , for inferring invariants of #if -annotated C programs. The tool implements all three approaches for lifted analysis based on abstract interpretation: tuple-based, decision tree-based, and BDD-based. It uses existing numerical abstract domains (e.g., intervals, octagons, polyhedra) from the APRON library as parameters. An empirical evaluation on benchmarks from SV-COMP and BusyBox yields promising results indicating that our tool can be successfully used for analyzing program families with very large configuration spaces.

Common, low-frequency, rare, and ultra-rare coding variants contribute to COVID-19 severity

The combined impact of common and rare exonic variants in COVID-19 host genetics is currently insufficiently understood. Here, common and rare variants from whole-exome sequencing data of about 4000 SARS-CoV-2-positive individuals were used to define an interpretable machine-learning model for predicting COVID-19 severity. First, variants were converted into separate sets of Boolean features, depending on the absence or the presence of variants in each gene. An ensemble of LASSO logistic regression models was used to identify the most informative Boolean features with respect to the genetic bases of severity. The Boolean features selected by these logistic models were combined into an Integrated PolyGenic Score that offers a synthetic and interpretable index for describing the contribution of host genetics in COVID-19 severity, as demonstrated through testing in several independent cohorts. Selected features belong to ultra-rare, rare, low-frequency, and common variants, including those in linkage disequilibrium with known GWAS loci. Noteworthily, around one quarter of the selected genes are sex-specific. Pathway analysis of the selected genes associated with COVID-19 severity reflected the multi-organ nature of the disease. The proposed model might provide useful information for developing diagnostics and therapeutics, while also being able to guide bedside disease management.

Adaptive Sparse Representation of Continuous Input for Tsetlin Machines Based on Stochastic Searching on the Line

This paper introduces a novel approach to representing continuous inputs in Tsetlin Machines (TMs). Instead of using one Tsetlin Automaton (TA) for every unique threshold found when Booleanizing continuous input, we employ two Stochastic Searching on the Line (SSL) automata to learn discriminative lower and upper bounds. The two resulting Boolean features are adapted to the rest of the clause by equipping each clause with its own team of SSLs, which update the bounds during the learning process. Two standard TAs finally decide whether to include the resulting features as part of the clause. In this way, only four automata altogether represent one continuous feature (instead of potentially hundreds of them). We evaluate the performance of the new scheme empirically using five datasets, along with a study of interpretability. On average, TMs with SSL feature representation use 4.3 times fewer literals than the TM with static threshold-based features. Furthermore, in terms of average memory usage and F1-Score, our approach outperforms simple Multi-Layered Artificial Neural Networks, Decision Trees, Support Vector Machines, K-Nearest Neighbor, Random Forest, Gradient Boosted Trees (XGBoost), and Explainable Boosting Machines (EBMs), as well as the standard and real-value weighted TMs. Our approach further outperforms Neural Additive Models on Fraud Detection and StructureBoost on CA-58 in terms of the Area Under Curve while performing competitively on COMPAS.

Width-Based Planning for General Video-Game Playing

IW(1) is a simple search algorithm that assumes that states can be characterized in terms of a set of boolean features or atoms. IW(1) consists of a standard breadth-first search with one variation: a newly generated state is pruned if it does not make a new atom true. Thus, while a breadth-first search runs in time that is exponential in the number of atoms, IW(1) runs in linear time. Variations of the algorithm have been shown to yield state-of-the-art results in classical planning and more recently in the Atari video games. In this paper, we use the algorithm for selecting actions in the games of the general video-game AI competition (GVG-AI) which, unlike classical planning problems and the Atari games, are stochastic. We evaluate a variation of the algorithm over 30 games under different time windows using the number of wins as the performance measure. We find that IW(1) does better than the sample MCTS and OLMCTS controllers for all time windows with the performance gap growing with the window size. The exception are the puzzle-like games where all the algorithms do poorly. For such problems, we show that much better results can be obtained with the IW(2) algorithm, which is like IW(1), except that states are pruned in the breadth-first search when they fail to make true a new pair of atoms.

Planning from Pixels in Atari with Learned Symbolic Representations

Width-based planning methods have been shown to yield state-of-the-art performance in the Atari 2600 domain using pixel input. One successful approach, RolloutIW, represents states with the B-PROST boolean feature set. An augmented version of RolloutIW, pi-IW, shows that learned features can be competitive with handcrafted ones for width-based search. In this paper, we leverage variational autoencoders (VAEs) to learn features directly from pixels in a principled manner, and without supervision. The inference model of the trained VAEs extracts boolean features from pixels, and RolloutIW plans with these features. The resulting combination outperforms the original RolloutIW and human professional play on Atari 2600 and drastically reduces the size of the feature set.

A binary decision diagram lifted domain for analyzing program families

Many software systems today are highly configurable. They can produce a potentially large variety of related programs (variants) by selecting suitable configuration options (features) at compile time. Recently, specialized variability-aware (lifted, family-based) static analyses based on abstract interpretation have been developed. They allow analyzing all variants of a program family (or, any other configurable software system), simultaneously, in a single run without generating any of the variants explicitly. In effect, they produce precise analysis results for all individual variants. The elements of the underlying lifted analysis domain represent tuples (i.e. disjunction of properties), which maintain one property from an existing single-program analysis domain per variant. Nevertheless, explicit property enumeration in tuples, one by one for all variants, immediately yields to combinatorial explosion given that the number of variants can grow exponentially with the number of features. Therefore, such lifted analyses may be too costly or even infeasible for program families with a large number of variants. In this work, we propose a more efficient lifted static analysis of program families with Boolean features, where sharing is explicitly possible between analysis elements corresponding to different variants. This is achieved by giving a symbolic representation of the lifted analysis domain, which can efficiently handle disjunctive properties in program families. The elements of the new lifted domain are binary decision diagrams, where decision nodes are labeled with Boolean features and leaf nodes belong to an existing single-program analysis domain. The lifted domain is parametric in the choice of the abstract (property) domain for leaf nodes. To illustrate the potential of this representation, we have implemented a lifted static analyzer that uses a combination of forward and backward analyses for inferring numerical invariants and necessary preconditions of C program families. It uses APRON and BDDAPRON libraries for implementing the new lifted analysis domain. The APRON library, used for the leaves, is a widely accepted API for numerical abstract domains (e.g. polyhedra, octagons, intervals), while the BDDAPRON is an extension of APRON which adds the power domain of Boolean formulae and any APRON domain. An empirical evaluation on C benchmarks taken from SV-COMP and BusyBox indicates that our binary decision diagram-based approach is effective and outperforms the baseline tuple-based approach.

A statistical method for detecting spatiotemporal co-occurrence patterns

ABSTRACTSpatiotemporal co-occurrence patterns (STCOPs) are subsets of Boolean features whose instances frequently co-occur in both space and time. The detection of STCOPs is crucial to the investigation of the spatiotemporal interactions among different features. However, prevalent STCOPs reported by available methods do not necessarily indicate the statistically significant dependence among different features, which is likely to result in highly erroneous assessments in practice. To improve the reliability of results, this paper develops a statistical method to detect STCOPs and discern their statistical significance. The proposed method detects STCOPs against the null hypothesis that the spatiotemporal distributions of different features are independent of each other. To construct the null hypothesis, suitable spatiotemporal point-process models considering spatiotemporal autocorrelation are employed to model the distributions of different features. The performance of the proposed statistical method is assessed by synthetic experiments and a case study aimed at identifying crime patterns among multiple crime types in Portland City. The experimental results demonstrate that the proposed method is more effective for detecting meaningful STCOPs than the available alternative methods.

Oddness-based classification: A new way of exploiting neighbors

The classification of a new item may be viewed as a matter of associating it with the class where it is the least at odds w.r.t. the elements already in the class. An oddness measure of an item with respect to a multiset, applicable to Boolean features as well as to numerical ones, has been recently proposed. It has been shown that cumulating this measure over pairs or triples (rather than larger subsets) of elements in a class could provide an accurate estimate of the global oddness of an item with respect to a class. This idea is confirmed and refined in the present paper. Rather than considering all the pairs in a class, one can only deal with the pairs whose an element is one of the nearest neighbors of the item, in the target class. The oddness evaluation computed on this basis still leads to good results in terms of accuracy. One can take a step further and choose the second element in the pair also as another nearest neighbor in the class. Although the method relies on the notion of neighbors, the resulting algorithm is far from being a variant of the classical k?nearest neighbors approach. The oddness with respect to a class computed only on the basis of pairs made of two nearest neighbors leads to a low complexity algorithm. Experiments on a set of UCI benchmarks show that the classifier obtained can compete with other well?known approaches.

Structural properties of algebras of S-probabilities

Abstract Let S be a set of states of a physical system. The probabilities p(s) of the occurrence of an event when the system is in different states s ∈ S define a function from S to [0, 1] called a numerical event or, more precisely, an S-probability. A set of S-probabilities comprising the constant functions 0 and 1 which is structured by means of the addition and order of real functions in such a way that an orthomodular partially ordered set arises is called an algebra of S-probabilities, a structure significant as a quantum-logic with a full set of states. The main goal of this paper is to describe algebraic properties of algebras of S-probabilities through operations with real functions. In particular, we describe lattice characteristics and characterize Boolean features. Moreover, representations by sets are considered and pertinent examples provided.

Automatically generating features for learning program analysis heuristics for C-like languages

We present a technique for automatically generating features for data-driven program analyses. Recently data-driven approaches for building a program analysis have been developed, which mine existing codebases and automatically learn heuristics for finding a cost-effective abstraction for a given analysis task. Such approaches reduce the burden of the analysis designers, but they do not remove it completely; they still leave the nontrivial task of designing so called features to the hands of the designers. Our technique aims at automating this feature design process. The idea is to use programs as features after reducing and abstracting them. Our technique goes through selected program-query pairs in codebases, and it reduces and abstracts the program in each pair to a few lines of code, while ensuring that the analysis behaves similarly for the original and the new programs with respect to the query. Each reduced program serves as a boolean feature for program-query pairs. This feature evaluates to true for a given program-query pair when (as a program) it is included in the program part of the pair. We have implemented our approach for three real-world static analyses. The experimental results show that these analyses with automatically-generated features are cost-effective and consistently perform well on a wide range of programs.

Latent Network Features and Overlapping Community Discovery via Boolean Intersection Representations.

We propose a new latent Boolean feature model for complex networks that captures different types of node interactions and network communities. The model is based on a new concept in graph theory, termed the Boolean intersection representation of a graph, which generalizes the notion of an intersection representation. We mostly focus on one form of Boolean intersection, termed cointersection, and describe how to use this representation to deduce node feature sets and their communities. We derive several general bounds on the minimum number of features used in cointersection representations and discuss graph families for which exact cointersection characterizations are possible. Our results also include algorithms for finding optimal and approximate cointersection representations of a graph.

Design Intent for CAD Modeling Features Using Boolean Operations

The objective of this paper is to add one more enhancement to design intent by adding a rule to find the intersection edges created between Boolean features. Design Intent is a core module in CAD software which is used for smart design of referencing elements to create required features. In general, the particular design intent will form a particular rule which can be utilized for specified purpose. In this paper, a design intent rule for Edge Blend feature is designed. The rule is also implemented and integrated with CAD software. The major contributions of this paper is to create a new intent design rule which picks the edges of the feature Present design intent rule is intended to pick the intersection edges of the feature, in doing so; the intent will avoid referencing to topology over referencing to hierarchy objects for greater reliability

Saliency Detection Based on Color and Gradient Boolean Features

Saliency Detection Based on Color and Gradient Boolean Features

Reasoning about product-line evolution using complex feature model differences

Features define common and variable parts of the members of a (software) product line. Feature models are used to specify the set of all valid feature combinations. Feature models not only enjoy an intuitive tree-like graphical syntax, but also a precise formal semantics, which can be denoted as propositional formulae over Boolean feature variables. A product line usually constitutes a long-term investment and, therefore, has to undergo continuous evolution to meet ever-changing requirements. First of all, product-line evolution leads to changes of the feature model due to its central role in the product-line paradigm. As a result, product-line engineers are often faced with the problems that (1) feature models are changed in an ad-hoc manner without proper documentation, and (2) the semantic impact of feature diagram changes is unclear. In this article, we propose a comprehensive approach to tackle both challenges. For (1), our approach compares the old and new version of the diagram representation of a feature model and specifies the changes using complex edit operations on feature diagrams. In this way, feature model changes are automatically detected and formally documented. For (2), we propose an approach for reasoning about the semantic impact of diagram changes. We present a set of edit operations on feature diagrams, where complex operations are primarily derived from evolution scenarios observed in a real-world case study, i.e., a product line from the automation engineering domain. We evaluated our approach to demonstrate its applicability with respect to the case study, as well as its scalability concerning experimental data sets.

Novel class detection in data streams using local patterns and neighborhood graph

Data stream classification is one of the most challenging areas in the machine learning. In this paper, we focus on three major challenges namely infinite length, concept-drift and concept-evolution. Infinite length causes the inability to store all instances. Concept-drift is the change in the underlying concept and occurs in almost every data stream. Concept-evolution, in fact, is the arrival of novel classes and is an undeniable phenomenon in most real world data streams. There are lots of researches about data stream classification, but most of them focus on the first two challenges and ignore the last one. In this paper, we propose new method based on ensembles whose classifiers use local patterns to enhance the accuracy. Local pattern is a group of Boolean features which have local influence on ordinal and categorical features. Also, in order to enhance the accuracy of novel class detection we construct a neighborhood graph among novel class candidates and analyze connected components of the constructed graph. Experiments on both real and synthetic benchmark data sets show the superiority of the proposed method over the related state-of-the-art techniques.