Abstract: A computer-implemented method executed using a computing device comprises digitally generating and storing a machine learning statistical topic model in computer memory, the topic model being programmed to model call transcript data representing words spoken on a call as a function of one or more topics of a set of topics, the set of topics being modeled to comprise a set of pre-seeded topics and a set of non-pre-seeded topics, and the one or more topics being modeled as a function of a probability distribution of topics; programmatically pre-seeding the topic model with a set of keyword groups, each keyword group associating a respective set of keywords with a topic of the set of pre-seeded topics; programmatically training the topic model using unlabeled training data; conjoining a classifier to the topic model to create a classifier model, the classifier defining a joint probability distribution over topic vectors and one or more observed labels; programmatically training the classifier model using labeled

Abstract: There are disclosed devices, system and methods for determining a performance score for a trained binary signal classifier (classifier) by determining test output predictions for test input data entries that are input into the classifier. The test outputs are then compared to known outputs of each of the input data entries to determine whether each test output is a true negative (TN), true positive (TP), false negative (FN) or false positive (FP). A number of correct test outputs (R) is defined as a number of the true negative outputs (TN) plus a number of the true positive outputs (TP). A number of incorrect test outputs (W) is defined as a number of the false negative outputs (FN) plus a number of the false positive outputs (FP). The performance score is then calculated using a mathematical expression that decreases as W increases, decreases as TN decreases and decreases as TP decreases.

Abstract: There are disclosed devices, system and methods for determining a performance score for a trained binary signal classifier (classifier) by determining test output predictions for test input data entries that are input into the classifier. The test outputs are then compared to known outputs of each of the input data entries to determine whether each test output is a true negative (TN), true positive (TP), false negative (FN) or false positive (FP). A number of correct test outputs (R) is defined as a number of the true negative outputs (TN) plus a number of the true positive outputs (TP). A number of incorrect test outputs (W) is defined as a number of the false negative outputs (FN) plus a number of the false positive outputs (FP). The performance score is then calculated using a mathematical expression that decreases as W increases, decreases as TN decreases and decreases as TP decreases.

Abstract: Embodiments of the invention are directed to systems, methods, and computer program products for rapid assessment of cloud frameworks to evaluate those considered for use in an enterprise context. The invention may quickly and consistently identify gaps or weaknesses of cloud frameworks or resources, assess the potential negative impact of such gaps or weaknesses, and facilitate the communication of quantifiable data to responsible parties in order to facilitate the implementation of necessary controls or actions. Embodiments of the invention are highly adaptable and dynamic in fashion such that they can be quickly and easily updated based on the changing needs of the enterprise.

Abstract: Embodiments of the invention are directed to systems, methods, and computer program products for rapid assessment of cloud frameworks to evaluate those considered for use in an enterprise context. The invention may quickly and consistently identify gaps or weaknesses of cloud frameworks or resources, assess the potential negative impact of such gaps or weaknesses, and facilitate the communication of quantifiable data to responsible parties in order to facilitate the implementation of necessary controls or actions. Embodiments of the invention are highly adaptable and dynamic in fashion such that they can be quickly and easily updated based on the changing needs of the enterprise.

Abstract: There are disclosed devices, system and methods for a machine learning binary classifier automatically tolerating training data that is incorrect by determining a correct and an incorrect likelihood ratio that each training data entry has a correctly and an incorrectly labeled output. The correct and an incorrect likelihood ratio are combined with a correct and an incorrect priori odds ratio that the set of training data entries have correctly and incorrect labeled output labels. These two combinations are a correct probability and an incorrect probability that each entry of the set of entries has a correctly and an incorrect labeled output. A logistic regression model if fit to a combination of the correct probability and the incorrect probability for each training data entry to complete the training.

Abstract: There are disclosed devices, system and methods for a machine learning binary classifier automatically tolerating training data that is incorrect by determining a correct and an incorrect likelihood ratio that each training data entry has a correctly and an incorrectly labeled output. The correct and an incorrect likelihood ratio are combined with a correct and an incorrect priori odds ratio that the set of training data entries have correctly and incorrect labeled output labels. These two combinations are a correct probability and an incorrect probability that each entry of the set of entries has a correctly and an incorrect labeled output. A logistic regression model if fit to a combination of the correct probability and the incorrect probability for each training data entry to complete the training.

Abstract: There are disclosed devices, system and methods for determining a performance score for a trained binary signal classifier (classifier) by determining test output predictions for test input data entries that are input into the classifier. The test outputs are then compared to known outputs of each of the input data entries to determine whether each test output is a true negative (TN), true positive (TP), false negative (FN) or false positive (FP). A number of correct test outputs (R) is defined as a number of the true negative outputs (TN) plus a number of the true positive outputs (TP). A number of incorrect test outputs (W) is defined as a number of the false negative outputs (FN) plus a number of the false positive outputs (FP). The performance score is then calculated using a mathematical expression that decreases as W increases, decreases as TN decreases and decreases as TP decreases.

Abstract: There are disclosed devices, system and methods for desired signal spotting in noisy, flawed environments by identifying a signal to be spotted, identifying a target confidence level, and then passing a pool of cabined arrays through a comparator to detect the identified signal, wherein the cabined arrays are derived from respective distinct environments. The arrays may include plural converted samples, each converted sample include a product of a conversion of a respective original sample, the conversion including filtering noise and transforming the original sample from a first form to a second form. Detecting may include measuring a confidence of the presence of the identified signal in each of plural converted samples using correlation of the identified signal to bodies of known matching samples. If the confidence for a given converted sample satisfies the target confidence level, the given sample is flagged.

Abstract: There are disclosed devices, system and methods for desired signal spotting in noisy, flawed environments by identifying a signal to be spotted, identifying a target confidence level, and then passing a pool of cabined arrays through a comparator to detect the identified signal, wherein the cabined arrays are derived from respective distinct environments. The arrays may include plural converted samples, each converted sample include a product of a conversion of a respective original sample, the conversion including filtering noise and transforming the original sample from a first form to a second form. Detecting may include measuring a confidence of the presence of the identified signal in each of plural converted samples using correlation of the identified signal to bodies of known matching samples. If the confidence for a given converted sample satisfies the target confidence level, the given sample is flagged.

Abstract: There are disclosed devices, system and methods for desired signal spotting in noisy, flawed environments by identifying a signal to be spotted, identifying a target confidence level, and then passing a pool of cabined arrays through a comparator to detect the identified signal, wherein the cabined arrays are derived from respective distinct environments. The arrays may include plural converted samples, each converted sample include a product of a conversion of a respective original sample, the conversion including filtering noise and transforming the original sample from a first form to a second form. Detecting may include measuring a confidence of the presence of the identified signal in each of plural converted samples using correlation of the identified signal to bodies of known matching samples. If the confidence for a given converted sample satisfies the target confidence level, the given sample is flagged.

Abstract: There are disclosed devices, system and methods for desired signal spotting in noisy, flawed environments by identifying a signal to be spotted, identifying a target confidence level, and then passing a pool of cabined arrays through a comparator to detect the identified signal, wherein the cabined arrays are derived from respective distinct environments. The arrays may include plural converted samples, each converted sample include a product of a conversion of a respective original sample, the conversion including filtering noise and transforming the original sample from a first form to a second form. Detecting may include measuring a confidence of the presence of the identified signal in each of plural converted samples using correlation of the identified signal to bodies of known matching samples. If the confidence for a given converted sample satisfies the target confidence level, the given sample is flagged.

Abstract: A system and method for depicting a coverage area of at least one camera within a graphical representation of a data center is disclosed. In one aspect, a method includes establishing, by a computer, a representation of the at least one camera within the graphical representation of the data center, determining at least one device associated with the at least one camera, determining at least two points within the graphical representation of the data center marking outer boundaries of the at least one device, and displaying the coverage area between the outer boundaries and the representation of at least one camera.

Abstract: A system and method for depicting a coverage area of at least one camera within a graphical representation of a data center is disclosed. In one aspect, a method includes establishing, by a computer, a representation of the at least one camera within the graphical representation of the data center, determining at least one device associated with the at least one camera, determining at least two points within the graphical representation of the data center marking outer boundaries of the at least one device, and displaying the coverage area between the outer boundaries and the representation of at least one camera.

Abstract: A system and method for managing at least one camera having a coverage area within a data center is disclosed. In one aspect, a method includes obtaining, by a computer, identification information for at least one data center device within the data center from a data center management system through a communications network, associating the at least one data center device with the at least one camera based on the identification information for the at least one data center device, and displaying at least one image captured by the at least one camera associated with the at least one data center device in response to the data center management system detecting an event associated with the at least one data center device.

Abstract: A method to wash and remove dissolved solids from biomass including: discharging a biomass slurry from a pretreatment vessel to a biomass slurry retention device; adding recovered wash liquid to dilute the biomass slurry in the retention device, wherein the recovered wash liquid is extracted from a drainer device upstream of the first retention device; discharging the diluted biomass slurry from the retention device to the drainer device; separating wash liquid with dissolved solids from the diluted biomass slurry in the drainer device and discharging a concentrated biomass slurry from the drainer device, and recovering the wash liquid from the diluted biomass slurry in the drainer device and transferring the recovered wash liquid to the retention device.

Abstract: A self propelled concrete saw compensates for blade cutting resistance, for example by adjusting a movable drive assembly. An actuator may be used to move the drive assembly, for example through the operation of a control switch by an operator.

Abstract: A handle support and adjustment assembly for a saw allows the handle to be adjusted in length and/or angle relative to the saw.

Abstract: A movable saw has a handle that is movable sideways relative to the saw. The handle may also be movable so as to change its vertical position.

Abstract: A self propelled concrete saw compensates for blade cutting resistance, for example by adjusting a movable drive assembly. An actuator may be used to move the drive assembly, for example through the operation of a control switch by an operator.