Abstract: Embodiments use a hierarchy of machine learning models to predict datacenter behavior at multiple hardware levels of a datacenter without accessing operating system generated hardware utilization information. The accuracy of higher-level models in the hierarchy of models is increased by including, as input to the higher-level models, hardware utilization predictions from lower-level models. The hierarchy of models includes: server utilization models and workload/OS prediction models that produce predictions at a server device-level of a datacenter; and also top-of-rack switch models and backbone switch models that produce predictions at higher levels of the datacenter. These models receive, as input, hardware utilization information from non-OS sources. Based on datacenter-level network utilization predictions from the hierarchy of models, the datacenter automatically configures its hardware to avoid any predicted over-utilization of hardware in the datacenter.

Abstract: Techniques are described herein for estimating CPU, memory, and I/O utilization for a workload via out-of-band sensor readings using a machine learning model. The framework involves receiving sensor data associated with executing benchmark applications, obtaining ground truth utilization values for the benchmarks, preprocessing the training data to select a set of enhanced sequences, and using the enhanced sequences to train a random forest model to estimate CPU, memory, and I/O utilization given sensor monitoring data. Prior to the training phase, a machine learning model is trained using a set of predefined hyper-parameters. The trained models are used to generate estimations for CPU, memory, and I/O utilizations values. The utilization values are used with workload context information to assess the deployment and generate one or more recommendations for machine types that will best serve the workload in terms of system utilization.

Abstract: Unsorted sparse dictionary encodings are transformed into unsorted-dense or sorted-dense dictionary encodings. Sparse domain codes have large gaps between codes that are adjacent in order. Unlike spare codes, dense codes have smaller gaps between adjacent codes; consecutive codes are dense codes that have no gaps between adjacent codes. The techniques described herein are relational approaches that may be used to generate sparse composite codes and sorted codes.

Abstract: Techniques are described herein for predicting disk drive failure using a machine learning model. The framework involves receiving disk drive sensor attributes as training data, preprocessing the training data to select a set of enhanced feature sequences, and using the enhanced feature sequences to train a machine learning model to predict disk drive failures from disk drive sensor monitoring data. Prior to the training phase, the RNN LSTM model is tuned using a set of predefined hyper-parameters. The preprocessing, which is performed during the training and evaluation phase as well as later during the prediction phase, involves using predefined values for a set of parameters to generate the set of enhanced sequences from raw sensor reading. The enhanced feature sequences are generated to maintain a desired healthy/failed disk ratio, and only use samples leading up to a last-valid-time sample in order to honor a pre-specified heads-up-period alert requirement.

Abstract: Herein are techniques for analysis of data streams. In an embodiment, a computer associates each software actor with data streams. Each software actor has its own backlog queue of data to analyze. In response to receiving some stream content and based on the received stream content, data is distributed to some software actors. In response to determining that the data satisfies completeness criteria of a particular software actor, an indication of the data is appended onto the backlog queue of the particular software actor. The particular software actor is reset to an initial state by loading an execution snapshot of a previous initial execution of an embedded virtual machine. Based on the particular software actor, execution of the execution snapshot of the previous initial execution is resumed to dequeue and process the indication of the data from the backlog queue of the particular software actor to generate a result.

Abstract: Techniques are provided herein for contextual embedding of features of operational logs or network traffic for anomaly detection based on sequence prediction. In an embodiment, a computer has a predictive recurrent neural network (RNN) that detects an anomalous network flow. In an embodiment, an RNN contextually transcodes sparse feature vectors that represent log messages into dense feature vectors that may be predictive or used to generate predictive vectors. In an embodiment, graph embedding improves feature embedding of log traces. In an embodiment, a computer detects and feature-encodes independent traces from related log messages. These techniques may detect malicious activity by anomaly analysis of context-aware feature embeddings of network packet flows, log messages, and/or log traces.

Abstract: Techniques are provided herein for contextual embedding of features of operational logs or network traffic for anomaly detection based on sequence prediction. In an embodiment, a computer has a predictive recurrent neural network (RNN) that detects an anomalous network flow. In an embodiment, an RNN contextually transcodes sparse feature vectors that represent log messages into dense feature vectors that may be predictive or used to generate predictive vectors. In an embodiment, graph embedding improves feature embedding of log traces. In an embodiment, a computer detects and feature-encodes independent traces from related log messages. These techniques may detect malicious activity by anomaly analysis of context-aware feature embeddings of network packet flows, log messages, and/or log traces.

Abstract: Embodiments monitor statistics from groups of devices and generate an alarm upon detecting a utilization imbalance that is beyond a threshold. Particular balance statistics are periodically sampled, over a timeframe, for a group of devices configured to have balanced utilization. The devices are ranked at every data collection timestamp based on the gathered device statistics. The numbers of times each device appears within each rank over the timeframe are tallied. The device/rank summations are collectively used as a probability distribution representing the probability of each device being ranked at each of the rankings in the future. Based on this probability distribution, an entropy value that represents a summary of the imbalance of the group of devices over the timeframe is derived. An imbalance alert is generated when one or more entropy values for a group of devices shows an imbalanced utilization of the devices going beyond an identified imbalance threshold.

Abstract: Techniques related to code dictionary generation based on non-blocking operations are disclosed. In some embodiments, a column of tokens includes a first token and a second token that are stored in separate rows. The column of tokens is correlated with a set of row identifiers including a first row identifier and a second row identifier that is different from the first row identifier. Correlating the column of tokens with the set of row identifiers involves: storing a correlation between the first token and the first row identifier, storing a correlation between the second token and the second row identifier if the first token and the second token have different values, and storing a correlation between the second token and the first row identifier if the first token and the second token have identical values. After correlating the column of tokens with the set of row identifiers, duplicate correlations are removed.

Abstract: A projector is provided, which has a plurality of operating modes, including a first operating mode in which a beam of electromagnetic waves is emitted by the projector. In addition, a detection unit is configured in such a way that in the first operating mode of the projector the presence of an object in the optical path of the beam is detected. Moreover, the projector includes a processing unit which is developed to switch from the first operating mode to a second operating mode that differs from the first operating mode when an object is detected in the optical path of the beam.

Abstract: The present invention is concerned with derivatives of 3,5-diphenyl-diazole compounds, which are effective therapeutic agents for use in treating diseases linked to protein aggregation and/or neurodegenerative diseases such as Alzheimer's disease (AD), Parkinson's disease (PD), and Transmissible spongiform encephalopathies (TSEs) such as Creutzfeldt-Jakob disease (CJD). The therapeutic effect is caused by the inhibition of the protein aggregation in the affected tissue, such as the brain. 3,5-Diphenyl-diazole derivatives have been shown to be effective in inhibiting aggregation of proteins but are also characterized by their poor solubility in aqueous solutions. The prodrugs of the invention are modified 3,5-diphenyl-diazole derivatives, which are characterized by their improved solubility in aqueous solutions, and by their increased bioavailability.

Abstract: A method and apparatus for adaptive data repartitioning and adaptive data replication is provided. A data set stored in a distributed data processing system is partitioned by a first partitioning key. A live workload comprising a plurality of data processing commands is processed. While processing the live workload, statistical properties of the live workload are maintained. Based on the statistical properties of the live workload with respect to the data set, it is determined to replicate and/or repartition the data set by a second partitioning key. The replicated and/or repartitioned data set is partitioned by the second partitioning key.

Abstract: The present invention is concerned with derivatives of 3,5-diphenyl-diazole compounds, which are effective therapeutic agents for use in treating diseases linked to protein aggregation and/or neurodegenerative diseases such as Alzheimer's disease (AD), Parkinson's disease (PD), and Transmissible spongiform encephalopathies (TSEs) such as Creutzfeldt-Jakob disease (CJD). The therapeutic effect is caused by the inhibition of the protein aggregation in the affected tissue, such as the brain. 3,5-Diphenyl-diazole derivatives have been shown to be effective in inhibiting aggregation of proteins but are also characterized by their poor solubility in aqueous solutions. The prodrugs of the invention are modified 3,5-diphenyl-diazole derivatives, which are characterized by their improved solubility in aqueous solutions, and by their increased bioavailability.

Abstract: A method and a projector for projecting an image pixel by pixel includes a control unit controlling a light diode device for emitting visible light, pixel by pixel, in accordance with the image to be projected and controlling an infrared diode device for emitting infrared radiation pixel by pixel based on the image to be projected and on a back radiation model, in such a way that a setpoint back radiation intensity measuring signal to be expected pixel by pixel for the actual back radiation intensity measuring signal has a predetermined value for predetermined pixels; and a radiation intensity detection device detecting pixel by pixel a back radiation intensity of reflected visible light and reflected infrared radiation and generating pixel by pixel an actual back radiation intensity measuring signal based on the detected back radiation intensities.

Abstract: A method for contactlessly interacting with a module, the module having a first submodule and a second submodule; in a first method step, the first submodule producing a primary beam; in a second method step, the second submodule inducing a scanning movement of the primary beam to allow image information to be projected into a projection area; in a third method step, a control command executed by an object being recognized by the module; the control command relating to contactlessly interacting with the module; in the third method step, the module detecting a geometric shape of the object.

Abstract: A method and apparatus for adaptive data repartitioning and adaptive data replication is provided. A data set stored in a distributed data processing system is partitioned by a first partitioning key. A live workload comprising a plurality of data processing commands is processed. While processing the live workload, statistical properties of the live workload are maintained. Based on the statistical properties of the live workload with respect to the data set, it is determined to replicate and/or repartition the data set by a second partitioning key. The replicated and/or repartitioned data set is partitioned by the second partitioning key.

Abstract: A computer is provided that has a plurality of insertion cards that are interconnected via a bus. One insertion card includes a local processing unit and a first intermediate memory for intermediate storage of messages intended for the local processing unit, and a second intermediate memory for intermediate storage of messages originating from the local processing unit. A third intermediate memory and a fourth intermediate memory are provided for free message locations that are intended for or originate from the local processing unit. The second and the third intermediate memories are each provided with a respective intermediate memory extension in a local memory of the local processing unit.

Abstract: A process is described for defined impregnation of honeycomb structures and a device for performing the process. The impregnating solutions are sprayed directly into the flow channels in the honeycomb structure using hollow injector needles.

Abstract: A catalyst for purifying the exhaust gases of internal combustion engines with improved light-off behavior and improved durability with reduced specific noble-metal content is disclosed which uses active aluminum oxide provided with customary promoters as carrier and platinum and/or palladium and rhodium in customary amounts as noble metals. In addition, it contains one or more base metals in amounts up to 5 times the mass of the total noble metal which are brought into the immediate vicinity of the rhodium by means of a special manufacturing technique.

Abstract: A method for the uniform coating of honeycomb bodies with finely divided solid matter from a dispersion in an amount which is below that which arises during customary immersion. To this end, the honeycomb is flooded from below with dispersion, emptied after a dwell time and blown out. Filling time, filling amount, dwell time emptying time as well as the time between emptying and blowing out are measured in such a manner that in order to increase the separated amount of solid matter, filling time, dwell time, pumping-out time and the time between emptying and blowing out are increased but the filling amount is reduced.