A Bayesian network perspective on neonatal pneumonia in pregnant women with diabetes mellitus.

OBJECTIVE: To predict the influencing factors of neonatal pneumonia in pregnant women with diabetes mellitus using a Bayesian network model. By examining the intricate network connections between the numerous variables given by Bayesian networks (BN), this study aims to compare the prediction effect of the Bayesian network model and to analyze the influencing factors directly associated to neonatal pneumonia. METHOD: Through the structure learning algorithms of BN, Naive Bayesian (NB), Tree Augmented Naive Bayes (TAN), and k-Dependence Bayesian Classifier (KDB), complex networks connecting variables were presented and their predictive abilities were tested. The BN model and three machine learning models computed using the R bnlean package were also compared in the data set. RESULTS: In constraint-based algorithms, three algorithms had different presentation DAGs. KDB had a better prediction effect than NB and TAN, and it achieved higher AUC compared with TAN. Among three machine learning modes, Support Vector Machine showed a accuracy rate of 91.04% and 67.88% of precision, which was lower than TAN (92.70%; 72.10%). CONCLUSION: KDB was applicable, and it can detect the dependencies between variables, identify more potential associations and track changes between variables and outcome.

Local Differential Privacy Protection of High-Dimensional Perceptual Data by the Refined Bayes Network.

Although the Crowd-Sensing perception system brings great data value to people through the release and analysis of high-dimensional perception data, it causes great hidden danger to the privacy of participants in the meantime. Currently, various privacy protection methods based on differential privacy have been proposed, but most of them cannot simultaneously solve the complex attribute association problem between high-dimensional perception data and the privacy threat problems from untrustworthy servers. To address this problem, we put forward a local privacy protection based on Bayes network for high-dimensional perceptual data in this paper. This mechanism realizes the local data protection of the users at the very beginning, eliminates the possibility of other parties directly accessing the user's original data, and fundamentally protects the user's data privacy. During this process, after receiving the data of the user's local privacy protection, the perception server recognizes the dimensional correlation of the high-dimensional data based on the Bayes network, divides the high-dimensional data attribute set into multiple relatively independent low-dimensional attribute sets, and then sequentially synthesizes the new dataset. It can effectively retain the attribute dimension correlation of the original perception data, and ensure that the synthetic dataset and the original dataset have as similar statistical characteristics as possible. To verify its effectiveness, we conduct a multitude of simulation experiments. Results have shown that the synthetic data of this mechanism under the effective local privacy protection has relatively high data utility.

Reliable and Fast Localization in Ambiguous Environments Using Ambiguity Grid Map.

In real-world robotic navigation, some ambiguous environments contain symmetrical or featureless areas that may cause the perceptual aliasing of external sensors. As a result of that, the uncorrected localization errors will accumulate during the localization process, which imposes difficulties to locate a robot in such a situation. Using the ambiguity grid map (AGM), we address this problem by proposing a novel probabilistic localization method, referred to as AGM-based adaptive Monte Carlo localization. AGM has the capacity of evaluating the environmental ambiguity with average ambiguity error and estimating the possible localization error at a given pose. Benefiting from the constructed AGM, our localization method is derived from an improved Dynamic Bayes network to reason about the robot's pose as well as the accumulated localization error. Moreover, a portal motion model is presented to achieve more reliable pose prediction without time-consuming implementation, and thus the accumulated localization error can be corrected immediately when the robot moving through an ambiguous area. Simulation and real-world experiments demonstrate that the proposed method improves localization reliability while maintains efficiency in ambiguous environments.

Error Tolerance of Machine Learning Algorithms across Contemporary Biological Targets.

Machine learning continues to make strident advances in the prediction of desired properties concerning drug development. Problematically, the efficacy of machine learning in these arenas is reliant upon highly accurate and abundant data. These two limitations, high accuracy and abundance, are often taken together; however, insight into the dataset accuracy limitation of contemporary machine learning algorithms may yield insight into whether non-bench experimental sources of data may be used to generate useful machine learning models where there is a paucity of experimental data. We took highly accurate data across six kinase types, one GPCR, one polymerase, a human protease, and HIV protease, and intentionally introduced error at varying population proportions in the datasets for each target. With the generated error in the data, we explored how the retrospective accuracy of a Naïve Bayes Network, a Random Forest Model, and a Probabilistic Neural Network model decayed as a function of error. Additionally, we explored the ability of a training dataset with an error profile resembling that produced by the Free Energy Perturbation method (FEP+) to generate machine learning models with useful retrospective capabilities. The categorical error tolerance was quite high for a Naïve Bayes Network algorithm averaging 39% error in the training set required to lose predictivity on the test set. Additionally, a Random Forest tolerated a significant degree of categorical error introduced into the training set with an average error of 29% required to lose predictivity. However, we found the Probabilistic Neural Network algorithm did not tolerate as much categorical error requiring an average of 20% error to lose predictivity. Finally, we found that a Naïve Bayes Network and a Random Forest could both use datasets with an error profile resembling that of FEP+. This work demonstrates that computational methods of known error distribution like FEP+ may be useful in generating machine learning models not based on extensive and expensive in vitro-generated datasets.

An Unobtrusive Fall Detection and Alerting System Based on Kalman Filter and Bayes Network Classifier.

Falls are one of the main health risks among the elderly. A fall detection system based on inertial sensors can automatically detect fall event and alert a caregiver for immediate assistance, so as to reduce injuries causing by falls. Nevertheless, most inertial sensor-based fall detection technologies have focused on the accuracy of detection while neglecting quantization noise caused by inertial sensor. In this paper, an activity model based on tri-axial acceleration and gyroscope is proposed, and the difference between activities of daily living (ADLs) and falls is analyzed. Meanwhile, a Kalman filter is proposed to preprocess the raw data so as to reduce noise. A sliding window and Bayes network classifier are introduced to develop a wearable fall detection system, which is composed of a wearable motion sensor and a smart phone. The experiment shows that the proposed system distinguishes simulated falls from ADLs with a high accuracy of 95.67%, while sensitivity and specificity are 99.0% and 95.0%, respectively. Furthermore, the smart phone can issue an alarm to caregivers so as to provide timely and accurate help for the elderly, as soon as the system detects a fall.

Probabilistic Evaluation of Ecological and Economic Objectives of River Basin Management Reveals a Potential Flaw in the Goal Setting of the EU Water Framework Directive.

The biological status of European lakes has not improved as expected despite up-to-date legislation and ecological standards. As a result, the realism of objectives and the attainment of related ecological standards are under doubt. This paper gets to the bottom of a river basin management plan of a eutrophic lake in Finland and presents the ecological and economic impacts of environmental and societal drivers and planned management measures. For these purposes, we performed a Monte Carlo simulation of a diffuse nutrient load, lake water quality and cost-benefit models. Simulations were integrated into a Bayesian influence diagram that revealed the basic uncertainties. It turned out that the attainment of good ecological status as qualified in the Water Framework Directive of the European Union is unlikely within given socio-economic constraints. Therefore, management objectives and ecological and economic standards need to be reassessed and reset to provide a realistic goal setting for management. More effort should be put into the evaluation of the total monetary benefits and on the monitoring of lake phosphorus balances to reduce the uncertainties, and the resulting margin of safety and costs and risks of planned management measures.

Mono-isotope Prediction for Mass Spectra Using Bayes Network.

Mass spectrometry is one of the widely utilized important methods to study protein functions and components. The challenge of mono-isotope pattern recognition from large scale protein mass spectral data needs computational algorithms and tools to speed up the analysis and improve the analytic results. We utilized naïve Bayes network as the classifier with the assumption that the selected features are independent to predict mono-isotope pattern from mass spectrometry. Mono-isotopes detected from validated theoretical spectra were used as prior information in the Bayes method. Three main features extracted from the dataset were employed as independent variables in our model. The application of the proposed algorithm to publicMo dataset demonstrates that our naïve Bayes classifier is advantageous over existing methods in both accuracy and sensitivity.

Leveraging Bayesian network to reveal the importance of water level in a shallow lake ecosystem: A study based on Paleo-diatom and fish community.

Lake ecological processes and nutrient patterns are increasingly affected by water level variation around the world. Still, the long-term effects of water level change on lake ecosystems and their implications for suitable lake level management have rarely been studied. Here, we studied the ecosystem dynamics of a mesotrophic lake located in the cold and arid region of northern China based on long-term paleo-diatom and fishery records. Utilizing a novel Copula-Bayesian Network model, possible hydrological-driven ecosystem evolution was discussed. Results show that increased nutrient concentration caused by the first water level drop in the early 1980s incurred a transition of sedimental diatoms towards pollution-resistant species, and the following water level rise in the mid-1980s brought about considerable external loading, which attributed to eutrophication and caused the miniaturization of fishery structure. In the 21st century, a continuous water level plummet further reduced the sediment diatom biomass and the fish biomass by altering nutrient concentration. However, with the implementation of the water diversion project in 2011, oligotrophic species increased, and the ecosystem developed for the better. From the perspective of water quality protection requirements and the ecological well-being of Lake Hulun, the appropriate water level should be around 542.42-544.15 m. In summary, our study highlights the coupling effect of water level and water quality on Lake Hulun ecosystem and gives shed to lake water level operation and management under future climate change and human activities.

Active Inference, Epistemic Value, and Uncertainty in Conceptual Disorganization in First-Episode Schizophrenia.

BACKGROUND AND HYPOTHESIS: Active inference has become an influential concept in psychopathology. We apply active inference to investigate conceptual disorganization in first-episode schizophrenia. We conceptualize speech production as a decision-making process affected by the latent "conceptual organization"-as a special case of uncertainty about the causes of sensory information. Uncertainty is both minimized via speech production-in which function words index conceptual organization in terms of analytic thinking-and tracked by a domain-general salience network. We hypothesize that analytic thinking depends on conceptual organization. Therefore, conceptual disorganization in schizophrenia would be both indexed by low conceptual organization and reflected in the effective connectivity within the salience network. STUDY DESIGN: With 1-minute speech samples from a picture description task and resting state fMRI from 30 patients and 30 healthy subjects, we employed dynamic causal and probabilistic graphical models to investigate if the effective connectivity of the salience network underwrites conceptual organization. STUDY RESULTS: Low analytic thinking scores index low conceptual organization which affects diagnostic status. The influence of the anterior insula on the anterior cingulate cortex and the self-inhibition within the anterior cingulate cortex are elevated given low conceptual organization (ie, conceptual disorganization). CONCLUSIONS: Conceptual organization, a construct that explains formal thought disorder, can be modeled in an active inference framework and studied in relation to putative neural substrates of disrupted language in schizophrenia. This provides a critical advance to move away from rating-scale scores to deeper constructs in the pursuit of the pathophysiology of formal thought disorder.

Recognition of the Effect of Vocal Exercises by Fuzzy Triangular Naive Bayes, a Machine Learning Classifier: A Preliminary Analysis.

OBJECTIVES: Machine learning (ML) methods allow the development of expert systems for pattern recognition and predictive analysis of intervention outcomes. It has been used in Voice Sciences, mainly to discriminate between healthy and dysphonic voices. Parameter patterns of vocal acoustic analysis and vocal perceptual assessment can be evaluated by ML classifiers, such as the Fuzzy Triangular Naive Bayes (FTriangNB), after using techniques that improve the vocal quality of individuals with healthy or dysphonic voices. Thus, the goal of this study was to analyze the performance of the FTriangNB to detect patterns in the acoustic parameters and the auditory-perceptual assessment of 12 women with dysphonia and 12 vocally healthy women, after performing three vocal exercises (tongue trills, semi-occluded vocal tract exercise with a high-resistance straw - SOVTE, and over-articulation). METHODS: The FTriangNB classifier contained in the Fuzzy Class package was implemented in the data analysis software R Studio version 1.4.1106 for Macintosh. The confusion matrix was extracted, as well as the accuracy, the Kappa coefficient, and the class statistics. The final result was compared with those generated by FTriangNB with the same variables from the preapplication database of the exercises. RESULTS: The FTriangNB presented good accuracy (87.5%) and Kappa coefficient (81.3%), and showed almost perfect agreement after application of the exercises, while the results before the application of the exercises demonstrated accuracy without acceptable discrimination capacity (33.3%) and Kappa coefficient with a poor agreement (-6.67%). The Semioccluded Vocal Tract Exercises (SOVTE) with high strength straw presented with a sensitivity and Negative Predictive Value (NPV) of value 1 (one), and the over-articulation's specificity and Positive Predictive Value (PPV) also showed a value of 1 (one). CONCLUSIONS: The FTriangNB showed great accuracy in recognizing the effect of vocal exercises. Exploratory studies with larger samples using FTriangNB, as well as other Machine Learning classifiers should be further carried out for this purpose in the Voice Science to enable inferences.

A comprehensive evaluation of machine learning techniques for cancer class prediction based on microarray data.

Prostate cancer is among the most common cancer in males and its heterogeneity is well known. The genomic level changes can be detected in gene expression data and those changes may serve as standard model for any random cancer data for class prediction. Various techniques were implied on prostate cancer data set in order to accurately predict cancer class including machine learning techniques. Large number of attributes but few numbers of samples in microarray data leads to poor training; therefore, the most challenging part is attribute reduction or non-significant gene reduction. In this work, a combination of interquartile range and t-test is used for attribute reduction. Further, a comprehensive evaluation of ten state-of-the-art machine learning techniques for their accuracy in class prediction of prostate cancer is done. Out of these techniques, Bayes Network outperformed with an accuracy of 94.11% followed by Naïve Bayes with an accuracy of 91.17%.

Activities of daily living and lesion position among multiple sclerosis patients by Bayes network.

Magnetic resonance imaging is a highly sensitive approach for diagnosis of multiple sclerosis, and T2-weighted images can reveal lesions in the cerebral white matter, gray matter, and spinal cord. However, the lesions have a poor correlation with measurable clinical disability. In this study, we performed a large-scale epidemiological survey of 238 patients with multiple sclerosis in eleven districts by network member hospitals in Shanghai, China within 1 year. The involved patients were scanned for position and size of lesions by MRI. Results showed that lesions in the cerebrum, spinal cord, or supratentorial position had an impact on the activities of daily living in multiple sclerosis patients, as assessed by the Bayes network. On the other hand, brainstem lesions were very unlikely to influence the activities of daily living, and were not associated with the position of lesion, patient's gender, and patient's living place.