Real Data Points Research Articles

Privacy-Enhanced Sentiment Analysis in Mental Health: Federated Learning with Data Obfuscation and Bidirectional Encoder Representations from Transformers

This research aims to find an optimal balance between privacy and performance in forecasting mental health sentiment. This paper investigates federated learning (FL) augmented with a novel data obfuscation (DO) technique, where synthetic data is used to "mask" real data points. Bidirectional Encoder Representations from Transformer (BERT) is used for sentiment analysis, forming a new framework, FL-BERT+DO, that addresses the privacy-performance trade-off. With FL, data remains decentralized, ensuring that user-sensitive information is retained on local devices rather than being shared with the FL server. The integration of BERT gives our system an enhanced feature of context sense-making from text conduct, and our model is extremely proficient in emotion categorization tasks. The experiments were performed on combined (real and replica synthetic) datasets containing emotions and showed significant enhancements compared to baseline methods. The proposed FL-BERT+DO framework shows the following metrics: prediction accuracy, 82.74%; precision, 83.30%; recall, 82.74%; F1-score, 82.80%. Further, we assessed its performance in the adversarial setup using membership inference and linkage attacks to ensure the privacy-preserved performance did not suffer deeply. It demonstrates that, even for large datasets, providing privacy-preserving prediction is possible and can significantly improve existing methods of addressing personal issues, like mental health support. Based on the results of our work, we can propose the development of secure decentralized learning systems that are capable of providing high accuracy of sentiment analysis and meeting strict privacy constraints.

Uncertainty analysis of digital twin model of mine ventilation system

The digital twin model of mine ventilation system (DTMVS) plays an important role in intelligent safety management. However, the uncertainty of the ventilation resistance coefficient, which is the core parameter of the model, makes it challenging to accurately construct a DTMVS. In this study, Latin Hypercube Sampling (LHS) and ventilation resistance coefficient estimation models (VRCEMs) are used to analyze the uncertainty. First, the LHS method was used to explore the effect of uncertainty in the simulated airflow by continuously increasing the level of uncertainty in the ventilation resistance coefficients. Subsequently, the ventilation resistance coefficients were estimated using the VRCEMs, and the uncertainty of the ventilation resistance coefficient and the simulated airflow was analyzed. The results showed that the ventilation resistance coefficients with a 5% coefficient of variation can cause the DTMVS to lose 34% of the real airflow data points. The degree of uncertainty in the ventilation resistance coefficients estimated by the VRCEM-GA (VRCEM using genetic algorithm) and VRCEM-DE (VRCEM using differential evolution algorithm) methods was enhanced by 27.4% and 4.4%, respectively, compared with VRCEM-ES (VRCEM using evolutionary strategy algorithm). The VRCEM-ES model had the least influence on the uncertainty of the simulated airflow of DTMVS. The simulated airflow of the DTMVS constructed based on VRCEMs fluctuated normally within the confidence interval. VRCEMs had a higher sensitivity to the ventilation resistance coefficients of branches with low coefficients of variation.

Deducing neighborhoods of classes from a fitted model

In this article, a new kind of interpretable machine learning method is presented, which can help to understand the partition of the feature space into predicted classes in a classification model using quantile shifts, and this way make the underlying statistical or machine learning model more trustworthy. Basically, real data points (or specific points of interest) are used and the changes of the prediction after slightly raising or decreasing specific features are observed. By comparing the predictions before and after the shifts, under certain conditions the observed changes in the predictions can be interpreted as neighborhoods of the classes with regard to the shifted features. Chord diagrams are used to visualize the observed changes. For illustration, this quantile shift method (QSM) is applied to an artificial example with medical labels and a real data example.

Constraints on the transition redshift from the calibrated gamma-ray burst Ep–Eiso correlation

ABSTRACT We constrain the deceleration–acceleration epoch, namely the transition redshift ztr, adopting model-independent techniques that utilize a calibrated Ep–Eiso correlation for gamma-ray bursts (GRBs). To do so, in addition to real data points, we employ up to 1000 simulated observational Hubble data (OHD) points. We then calibrate the Ep–Eiso correlation by means of the well-consolidate Bézier polynomial technique, interpolating OHD up to the second order. Once GRB data have been calibrated, we consider two strategies of cosmographic expansions, i.e. first we take a direct Hubble rate expansion around ztr, and second the expansion of the deceleration parameter around the same redshift, but with a different order. Employing Type Ia supernovae, baryonic acoustic oscillations and GRB data sets, from Monte Carlo analyses we infer tight constraints on ztr and the jerk parameters at z = ztr, namely jtr. Our results are extremely compatible with previous outcomes and confirm the Lambda cold dark matter predictions, being slightly different in terms of the jerk parameter. In this respect, we conjecture which extensions of the concordance paradigm are possible and we compare our findings with expectations provided by generic dark energy models.

An adaptive neuro-fuzzy inference system white-box model for real-time multiphase flowing bottom-hole pressure prediction in wellbores

The majority of published empirical correlations and mechanistic models are unable to provide accurate flowing bottom-hole pressure (FBHP) predictions when real-time field well data are used. This is because the empirical correlations and the empirical closure correlations for the mechanistic models were developed with experimental datasets. In addition, most machine learning (ML) FBHP prediction models were constructed with real-time well data points and published without any visible mathematical equation. This makes it difficult for other readers to use these ML models since the datasets used in their development are not open-source. This study presents a white-box adaptive neuro-fuzzy inference system (ANFIS) model for real-time prediction of multiphase FBHP in wellbores. 1001 real well data points and 1001 normalized well data points were used in constructing twenty-eight different Takagi–Sugeno fuzzy inference systems (FIS) structures. The dataset was divided into two sets; 80% for training and 20% for testing. Statistical performance analysis showed that a FIS with a 0.3 range of influence and trained with a normalized dataset achieved the best FBHP prediction performance. The optimal ANFIS black-box model was then translated into the ANFIS white-box model with the Gaussian input and the linear output membership functions and the extracted tuned premise and consequence parameter sets. Trend analysis revealed that the novel ANFIS model correctly simulates the anticipated effect of input parameters on FBHP. In addition, graphical and statistical error analyses revealed that the novel ANFIS model performed better than published mechanistic models, empirical correlations, and machine learning models. New training datasets covering wider input parameter ranges should be added to the original training dataset to improve the model's range of applicability and accuracy.

Conditional Loss and Deep Euler Scheme for Time Series Generation

We introduce three new generative models for time series that are based on Euler discretization of Stochastic Differential Equations (SDEs) and Wasserstein metrics. Two of these methods rely on the adaptation of generative adversarial networks (GANs) to time series. The third algorithm, called Conditional Euler Generator (CEGEN), minimizes a dedicated distance between the transition probability distributions over all time steps. In the context of Itô processes, we provide theoretical guarantees that minimizing this criterion implies accurate estimations of the drift and volatility parameters. Empirically, CEGEN outperforms state-of-the-art and GANs on both marginal and temporal dynamic metrics. Besides, correlation structures are accurately identified in high dimension. When few real data points are available, we verify the effectiveness of CEGEN when combined with transfer learning methods on model-based simulations. Finally, we illustrate the robustness of our methods on various real-world data sets.

Prediction of antimicrobial minimal inhibitory concentrations for Neisseria gonorrhoeae using machine learning models

The lowest concentration of an antimicrobial agent that can inhibit the visible growth of a microorganism after overnight incubation is called as minimum inhibitory concentration (MIC) and the drug prescriptions are made on the basis of MIC data to ensure successful treatment outcomes. Therefore, reliable antimicrobial susceptibility data is crucial, and it will help clinicians about which drug to prescribe. Although few prediction studies based on strategies have been conducted, however, no single machine learning (ML) modelling has been carried out to predict MICs in N. gonorrhoeae. In this study, we propose a ML based approach that can predict MICs of a specific antibiotic using unitigs sequences data. We retrieved N. gonorrhoeae genomes from European Nucleotide Archive and NCBI and analysed them combined with their respective MIC data for cefixime, ciprofloxacin, and azithromycin and then we constructed unitigs by using de Brujin graphs. We built and compared 35 different ML regression models to predict MICs. Our results demonstrate that RandomForest and CATBoost models showed best performance in predicting MICs of the three antibiotics. The coefficient of determination, R2, (a statistical measure of how well the regression predictions approximate the real data points) for cefixime, ciprofloxacin, and azithromycin was 0.75787, 0.77241, and 0.79009 respectively using RandomForest. For CATBoost model, the R2 value was 0.74570, 0.77393, and 0.79317 for cefixime, ciprofloxacin, and azithromycin respectively. Lastly, using feature importance, we explore the important genomic regions identified by the models for predicting MICs. The major mutations which are responsible for resistance against these three antibiotics were chosen by ML models as a top feature in case of each antibiotics. CATBoost, DecisionTree, GradientBoosting, and RandomForest regression models chose the same unitigs which are responsible for resistance. This unitigs-based strategy for developing models for MIC prediction, clinical diagnostics, and surveillance can be applicable for other critical bacterial pathogens.

Promoting knowledge sharing performance in a knowledge management system: do knowledge workers’ behavior patterns matter?

PurposeThis paper aims to identify the impact of demographical and organizational variables such as age, gender, experiences use of knowledge management system (KMS), education and job level on knowledge sharing (KS) performance of knowledge workers in knowledge activities of a KMS. Specifically, it seeks to explore that is there any relationship between the KS behavior patterns of high KS performance knowledge workers with their performance. Furthermore, this study using its conceptual attitude model aims to show that whether knowledge workers’ behavior patterns in sharing information and knowledge throughout a KMS have any specific effect or not.Design/methodology/approachThis paper proposed a framework to mine knowledge workers’ raw data using data mining techniques such as clustering and association rules mining. Also, this research uses a case-based approach to a knowledge-intensive company in Iran that works in the field of information technology with 730 numbers of workers.FindingsFindings suggest that demographical and organizational variables such as age, education and experience use of KMS have positive effects on knowledge worker’s KS behavior in KMSs. In fact, people who have lower age, higher education degrees and more experience use of KMS, have more participation in KS in KMS. Also, results depict that the experienced use of KMS has the most impact on the intention of KS in this KMS. Findings emphasize on the importance of the influence of the behavioral, organizational environments and psychological factors such as reward system, top management support, openness and trust, on KS performance of knowledge workers in the KMS. In fact, according to data, the KMS reward system caused to increasing participation of the users in KS, also in each knowledge activity that top managers participate in, the scores were higher.Practical implicationsThis research helps top managers in designing policies and strategies to improve the participation of knowledge workers in KS and helps human resource managers to improve their membership policies. Also, assist Information Technology (IT) managers to enhance KMSs’ design to leverage with organization strategies in the field of improving KS and encourage people to participate in KMS.Originality/valueThis research has two key values. First, this paper applies a data mining framework to mining and analyzing data and this paper uses actual data of a KMS in a specialist company in Iran, with about 27,740 real data points. Second, this paper investigates the impact of demographical and organizational attributes on KS behavior, which little is empirically known about the impact of demographical variables on KS intention.

Research in market-calibrated option pricing analysis

PurposeThis paper aims to consolidate and review the literature in the field of market-calibrated option pricing analysis. By doing so, the paper brings out the gaps in the extant literature and makes suggestions for future researchers in the field.Design/methodology/approachThe methodology used in this research is inspired by the works of Ferreira et al. (2016), Jabbour (2013), Lage Junior and Godinho Filho (2010), Seuring (2013) and Sharma et al. (2018). A total of 1,500 papers written on the pricing of options globally are collated from the Web of Science ranging across 2010-2018.FindingsMost of the research papers present mathematical proposals to value options; without calibrating it with real market data points. The authors bring out five important gaps in the extant literature.Originality/valueThis is arguably the first study that consolidates the literature in the field of market calibrated option pricing analysis with a view to suggest directions for future researchers.

Power quality prediction based on least squares method

In the current high degree of popularity of power products, power abnormalities on the production of more and more. Therefore, the prediction of power quality is of great significance. The method of prediction is generally to find the fitting function, the least squares fitting is the commonly used method to find the fitting function. In this paper, the least square method is used to fit the data of power grid. The factors influencing power quality were analyzed from four aspects, and the conclusions were obtained by fitting with real data points. In order to further improve the power quality prediction.

Robust Non-Rigid Point Set Registration Using Spatially Constrained Gaussian Fields.

Estimating transformations from degraded point sets is necessary for many computer vision and pattern recognition applications. In this paper, we propose a robust non-rigid point set registration method based on spatially constrained context-aware Gaussian fields. We first construct a context-aware representation (e.g., shape context) for assignment initialization. Then, we use a graph Laplacian regularized Gaussian fields to estimate the underlying transformation from the likely correspondences. On the one hand, the intrinsic manifold is considered and used to preserve the geometrical structure, and a priori knowledge of the point set is extracted. On the other hand, by using the deterministic annealing, the presented method is extended to a projected high-dimensional feature space, i.e., reproducing kernel Hilbert space through a kernel trick to solve the transformation, in which the local structure is propagated by the coarse-to-fine scaling strategy. In this way, the proposed method gradually recovers much more correct correspondences, and then estimates the transformation parameters accurately and robustly when facing degradations. Experimental results on 2D and 3D synthetic and real data (point sets) demonstrate that the proposed method reaches better performance than the state-of-the-art algorithms.

Archetypal analysis for data‐driven prototype identification

Prototypes, as Rosch (1973) defined the term in the cognitive sciences field, are ideal exemplars that summarize and represent groups of objects (or categories) and that are “typical" according to their internal resemblance and external dissimilarity vis‐à‐vis other groups or categories. In line with the cognitive approach, we propose a data‐driven procedure for identifying prototypes that is based on archetypal analysis and compositional data analysis. The procedure presented here exploits the properties of archetypes, both in terms of their external dissimilarity in relation to other points in the data set and in terms of their ability to represent the data through compositions in a simplex in which it is possible to cluster all of the observations. The proposed procedure is useful not only for the usual real data points; it may also be used for interval‐valued data, functional data, and relational data, and it provides well‐separated and clearly profiled prototypes. © 2016 Wiley Periodicals, Inc. Statistical Analysis and Data Mining: The ASA Data Science Journal, 2016

Novel $\varepsilon$ -Approximation to Data Streams in Sensor Networks

We are gradually moving into a realm where sensors, processors, memory and wireless transceivers would be seamlessly integrated together in the physical world and form a wireless sensor network. Such networks pose new challenges in data processing and transmission due to the characteristic of limited communication bandwidth and other resource constraints of sensor networks. To reduce the cost of storage, transmission and processing of time series data generated by sensor nodes, the need for more compact representations of time series data is compelling. Although a large number of data compression algorithms have been proposed to reduce data volume, their offline characteristic or super-linear time complexity prevents them from being applied directly on time series data generated by sensor nodes. Motivated by these observations, we propose an optimal online algorithm GDPLA for constructing a disconnected piecewise linear approximation of a time series which guarantees that the vertical distance between each real data point and the corresponding fit line is less than or equal to $\varepsilon$ . GDPLA not only generates the minimum number of segments to approximate a time series with precision guarantee, but also only requires linear time $O(n)$ bounded by a constant coefficient $6$ , where unit $1$ denotes the time complexity of comparing the slopes of two lines. The low cost characteristic of our method makes it a proper choice for resource-constrained WSNs. Extensive experiments on two real data sets have been conducted to demonstrate the superior compression performance of our method.

Tracking Companiess Real Time Sustainability Trends: Cognitive Computing's Identification of Short-Term Materiality Indicators

The article argues that what as known as big data analytics using cognitive computing can be applied to sustainability (environmental, social and corporate governance) analysis. This can supplement what is now almost entirely done by human analysis, but this new technology is scalable and can create multiple real time data points (trends). Proprietary sustainability data analytics has been developed by a technology start up, TruValue Labs, Inc.. Using early data for a six month period, we have found statistically significant short term volatility variations correlated against what is called (and defined as) compounded TruValue (cTV), a sustainability indicator. This has been especially true in the E and S, and to a lesser degree, G areas. We argue that such short-term movement, previously undetected, and therefore not measured, has potential materiality (hence value) implications. The article sets the stage for these conclusions with a review of sustainability ratings and measurement systems currently in use, a brief review of cognitive computing, a discussion of materiality and sustainability as well as how TruValue data is generated.

Improving activated sludge classification based on imbalanced data

A fast and accurate classification method for sewage sludge biological activity classification is of great significance for wastewater treatment. However, the data are often imbalanced and the accuracy of traditional classification algorithms applied to imbalanced small classes of data is very low. Such small classes are crucial application data. Therefore, based on the analysis of eight microorganisms, a novel method is proposed in this paper for the classification of activated sludge known as balanced support-vector-based back-propagation (SV-BP) neural network. It first splits the multiclass classification problem into a plurality of pairwise classification problems and uses a support vector machine (SVM) to achieve equalization. Second, the new dataset is produced, following which back-propagation neural network (BPNN) is used for training and classification. To examine the efficiency of the model, 1731 real data points are collected from a wastewater treatment factory and divide the data into four classes with the help of wastewater experts. Based on the new model, data redundancy and noise are greatly reduced. With area under the curve (AUC) measurements, we find that the AUC of SV-BP is 6.9% higher than classical BPNN. In addition, the small-class recognition rate of SV-BP is far better than that by classical BPNN and SVM algorithms.

Block bootstrap methods for the estimation of the intensity of a spatial point process with confidence bounds

This paper deals with the estimation of the intensity of a planar point process on the basis of a single point pattern, observed in a rectangular window. If the model assumptions of stationarity and isotropy hold, the method of block bootstrapping can be used to estimate the intensity of the process with confidence bounds. The results of two variants of block bootstrapping are compared with a parametric approximation based on the assumption of a Gaussian distribution of the numbers of points in deterministic subwindows of the original pattern. The studies were performed on patterns obtained by simulation of well-known point process models (Poisson process, two Matérn cluster processes, Matérn hardcore process, Strauss hardcore process). They were also performed on real histopathological data (point patterns of capillary profiles of 12 cases of prostatic cancer). The methods are presented as worked examples on two cases, where we illustrate their use as a check on stationarity (homogeneity) of a point process with respect to different fields of vision. The paper concludes with various methodological discussions and suggests possible extensions of the block bootstrap approach to other fields of spatial statistics.

Discovery of Marinopyrrole A (Maritoclax) as a Selective Mcl-1 Antagonist that Overcomes ABT-737 Resistance by Binding to and Targeting Mcl-1 for Proteasomal Degradation

The anti-apoptotic Bcl-2 family of proteins, including Bcl-2, Bcl-X(L) and Mcl-1, are well-validated drug targets for cancer treatment. Several small molecules have been designed to interfere with Bcl-2 and its fellow pro-survival family members. While ABT-737 and its orally active analog ABT-263 are the most potent and specific inhibitors to date that bind Bcl-2 and Bcl-X(L) with high affinity but have a much lower affinity for Mcl-1, they are not very effective as single agents in certain cancer types because of elevated levels of Mcl-1. Accordingly, compounds that specifically target Mcl-1 may overcome this resistance. In this study, we identified and characterized the natural product marinopyrrole A as a novel Mcl-1-specific inhibitor and named it maritoclax. We found that maritoclax binds to Mcl-1, but not Bcl-X(L), and is able to disrupt the interaction between Bim and Mcl-1. Moreover, maritoclax induces Mcl-1 degradation via the proteasome system, which is associated with the pro-apoptotic activity of maritoclax. Importantly, maritoclax selectively kills Mcl-1-dependent, but not Bcl-2- or Bcl-X(L)-dependent, leukemia cells and markedly enhances the efficacy of ABT-737 against hematologic malignancies, including K562, Raji, and multidrug-resistant HL60/VCR, by ∼60- to 2000-fold at 1-2 μM. Taken together, these results suggest that maritoclax represents a new class of Mcl-1 inhibitors, which antagonizes Mcl-1 and overcomes ABT-737 resistance by targeting Mcl-1 for degradation.

COMPARING MULTIPLE ChIP-SEQUENCING EXPERIMENTS

New high-throughput sequencing technologies can generate millions of short sequences in a single experiment. As the size of the data increases, comparison of multiple experiments on different cell lines under different experimental conditions becomes a big challenge. In this paper, we investigate ways to compare multiple ChIP-sequencing experiments. We specifically studied epigenetic regulation of breast cancer and the effect of estrogen using 50 ChIP-sequencing data from Illumina Genome Analyzer II. First, we evaluate the correlation among different experiments focusing on the total number of reads in transcribed and promoter regions of the genome. Then, we adopt the method that is used to identify the most stable genes in RT-PCR experiments to understand background signal across all of the experiments and to identify the most variable transcribed and promoter regions of the genome. We observed that the most variable genes for transcribed regions and promoter regions are very distinct. Gene ontology and function enrichment analysis on these most variable genes demonstrate the biological relevance of the results. In this study, we present a method that can effectively select differential regions of the genome based on protein-binding profiles over multiple experiments using real data points without any normalization among the samples.

AGGREGATION VERSUS DISAGGREGATION IN INPUT–OUTPUT ANALYSIS OF THE ENVIRONMENT

Analysts carrying out input–output analyses of environmental issues are often plagued by environmental and input–output data existing in different classifications, with environmentally sensitive sectors sometimes being aggregated in the economic input–output database. In principle there are two alternatives for dealing with such misalignment: either environmental data have to be aggregated into the input–output classification, which entails an undesirable loss of information, or input–output data have to be disaggregated based on fragmentary information. In this article, I show that disaggregation of input–output data, even if based on few real data points, is superior to aggregating environmental data in determining input–output multipliers. This is especially true if the disaggregated sectors are heterogeneous with respect to their economic and environmental characteristics. The results of this work may help analysts in understanding that disaggregation based on even a small amount of proxy information can improve the accuracy of input–output multipliers significantly. Perhaps, these results will also provide encouragement for preferring model disaggregation to aggregation in future work.

Simultaneous Nonrigid Registration of Multiple Point Sets and Atlas Construction

Groupwise registration of a set of shapes represented by unlabeled point sets is a challenging problem since, usually, this involves solving for point correspondence in a nonrigid motion setting. In this paper, we propose a novel and robust algorithm that is capable of simultaneously computing the mean shape, represented by a probability density function, from multiple unlabeled point sets(represented by finite-mixture models), and registering them nonrigidly to this emerging mean shape. This algorithm avoids the correspondence problem by minimizing the Jensen-Shannon (JS) divergence between the point sets represented as finite mixtures of Gaussian densities. We motivate the use of the JS divergence by pointing out its close relationship to hypothesis testing. Essentially,minimizing the JS divergence is asymptotically equivalent to maximizing the likelihood ratio formed from a probability density of the pooled point sets and the product of the probability densities of the individual point sets. We derive the analytic gradient of the cost function, namely, the JS-divergence, in order to efficiently achieve the optimal solution. The cost function is fully symmetric, with no bias toward any of the given shapes to be registered and whose mean is being sought. A by-product of the registration process is a probabilistic atlas, which is defined as the convex combination of the probability densities of the input point sets being aligned. Our algorithm can be especially useful for creating atlases of various shapes present in images and for simultaneously (rigidly or nonrigidly)registering 3D range data sets (in vision and graphics applications), without having to establish any correspondence. We present experimental results on nonrigidly registering 2D and 3D real and synthetic data (point sets).