In medicinal chemistry programs it is key to design and make compounds that are efficacious safe. This a long, complex, difficult multiparameter optimization process, often including several properties with orthogonal trends. New methods for the automated of against profiles multiple thus great value. Here we present fragment-based reinforcement learning approach based on an actor-critic model, generation novel molecules optimal properties. The actor critic both modeled bidirectional long...

Every year worldwide more than one million people die and a further 50 are injured in traffic accidents. Therefore, the development of car safety features that actively support driver preventing accidents, is utmost importance to reduce number injuries fatalities. However, establish this it necessary advanced assistance system (ADAS) understands drivers intended behavior advance. The growing variety sensors available for vehicles together with improved computer vision techniques, hence led...

In medicinal chemistry programs it is key to design and make compounds that are efficacious safe. This a long, complex difficult multi-parameter optimization process, often including several properties with orthogonal trends. New methods for the automated of against profiles multiple thus great value. Here we present fragment-based reinforcement learning approach based on an actor-critic model, generation novel molecules optimal properties. The actor critic both modelled bidirectional long...

We present a flexible deep convolutional neural network method for the analysis of arbitrary sized graph structures representing molecules. This method, which makes use Lipinski RDKit module, an open-source cheminformatics software, enables incorporation any global molecular (such as charge and weight) local atom hybridization bond orders) information. In this paper, we show that significantly outperforms another recently proposed based on networks several datasets are studied. Several best...

Ensemble classifiers are known to generally perform better than each individual classifier of which they consist. One approach fusion is apply Shaferpsilas theory evidence. While most approaches have adopted Dempsterpsilas rule combination, a multitude combination rules been proposed. A number as well two voting compared when used in conjunction with specific kind ensemble classifier, random forests, w.r.t. accuracy, area under ROC curve and Brier score on 27 datasets. The empirical...

Since second-order probability distributions assign probabilities to there is uncertainty on two levels. Although different types of have been distinguished before and corresponding measures suggested, the distinction made here between first- levels has not considered before. In this paper previously existing are from perspective new introduced. We conclude that concepts informativeness needs be qualified if used in a context suggest certain point view information can minimized, just shifted...

We extend the State-Based Anomaly Detection approach by introducing precise and imprecise anomaly detectors using Bayesian credal combination operators, where evidences over time are combined into a joint evidence. use imprecision in order to represent sensitivity of classification regarding an object being normal or anomalous. evaluate on real-world maritime dataset containing recorded AIS data show that outperform previously proposed based Gaussian mixture models kernel density estimators....

The development of high-throughput biomolecular technologies has resulted in generation vast omics data at an unprecedented rate. This is transforming biomedical research into a big discipline, where the main challenges relate to analysis and interpretation new biological knowledge. aim this study was develop framework for analytics, apply it analyzing transcriptomics time series from early differentiation human pluripotent stem cells towards mesoderm cardiac lineages. To end, transcriptome...

Bayesian networks are often proposed as a method for high-level information fusion. However, network relies on strong assumptions about the underlying probabilities. In many cases it is not realistic to require such precise probability assessments. We show that there exists significant set of problems where credal outperform networks, thus enabling more dependable decision making this type problems. A graphical probabilistic utilizes sets distributions, e.g., interval probabilities,...

Abstract To ensure reliable network performance, anomaly detection is an important part of the telecommunication operators’ work. This includes that operators need to timely intervene with network, should they encounter indications performance degradation. In this paper, we describe results initial experiment for regard using topic modeling on base station run-time variable data collected from live Radio Access Networks (RANs). The show clusters semantically related in same way as human...

For an operator of wireless telecommunication networks to make timely interventions in the network before minor faults escalate into issues that can lead substandard system performance, good situation awareness is high importance. Due increasing complexity such networks, as well explosion traffic load, it has become necessary aid human operators reach a level through use exploratory data analysis and information fusion techniques. However, understand results techniques often cognitively...

In medicinal chemistry programs it is key to design and make compounds that are efficacious safe. This a long, complex difficult multi-parameter optimization process, often including several properties with orthogonal trends. New methods for the automated of against profiles multiple thus great value. Here we present fragment-based reinforcement learning approach based on an actor-critic model, generation novel molecules optimal properties. The actor critic both modelled bidirectional long...