Abstract: A hierarchical based sequencing (HBS) machine learning model. In one example embodiment, a method of employing an HBS machine learning model to predict multiple interdependent output components of an MOD output decision may include determining an order for multiple interdependent output components of an MOD output decision. The method may also include sequentially training a classifier for each component in the selected order to predict the component based on an input and based on any previous predicted component(s).

Abstract: Respiratory insufficiency is detected by classifying preliminary breaths identified through a capnogram as being valid or artifact. Individual breaths are classified as being valid or artifact by determining values of a plurality of breathing parameters for a given breath, inferring a value for a key parameter from the determined values for the plurality of breathing parameters, and comparing the inferred value for the key parameter to a predetermined threshold.

Abstract: A computerized method for evaluating and reporting a cause of a performance change in a building management system is shown and described. The method includes receiving an indication of a fault for building equipment of the building management system and determining a root cause for the fault by traversing a causal relationship model including the building equipment and other devices of the building management system.

Abstract: An active metric learning device includes a metric application data analysis unit, a metric optimization unit, and an attribute clustering unit. The metric application data analysis unit is formed with a metric applying module for calculating the distance between data to be analyzed, a data analyzing module for analyzing the data using a predetermined function and the distances between the data to be analyzed and outputting the result of the data analysis, and an analysis result storage unit for storing the result of the data analysis. The metric optimization unit is formed with a feedback converting module for creating side information according to the command of feedback from the user and a metric learning module for generating a metric matrix optimized under a predetermined condition using the created side information. The attribute clustering unit clusters the metric matrix optimized by the metric optimization unit and structuralizes the attributes.

Abstract: A computerized method for evaluating and reporting a fault in a building management system includes receiving, at a processing circuit, multiple fault indications for different building equipment of the building management system. The method further includes displaying a single fault related to the multiple fault indications rather than reporting the multiple fault indications.

Abstract: A health and fitness management system is provided that has a health and fitness application operating, e.g., on a smart phone, that can wirelessly communicate with an activity module worn on the user which has an accelerometer. The application accepts food and weight inputs (e.g., from the smart phone) and user activity units (e.g., from the activity unit) and develops a user intrinsic metabolism. The application includes fitness arc and health quotient graphical indicators that guide the user on health and fitness activities.

Abstract: In training data, a similarity matrix is generated for each of types of data corresponding to different kernels, and graph Laplacians are formed individually from the similarity matrices. An entire graph Laplacian is defined as linear combination of the individual graph Laplacians with coupling constants. Observation variables and latent variables associated therewith are assumed to form normal distributions, and the coupling constants are assumed to form a gamma distribution. Then, on the basis of a variational Bayesian method, a variance of the observation variables and the coupling constants can be figured out with a reasonable computational cost. Once the variance of the observation variables and the coupling constants are figured out, a predictive distribution for any input data can be figured out by means of a Laplace approximation.

Abstract: A method of selecting and presenting content based on learned user preferences is provided. The method includes receiving search input from the user for identifying desired content items and receiving content selection actions from the user. The method further includes analyzing the date, day, and time of content selection actions by the user and analyzing descriptive terms associated with the selected content items to learn a periodicity of user selections of similar content items. In response to subsequent searches by the user, the method calls for selecting and ordering a collection of content items for presentation to the user based on comparing the user's search input to descriptive terms associated with content items and based on the learned periodicities of the user.

Abstract: A compositional recommender framework using modular recommendation functions is described. Each modular recommendation function can use a discrete technology, such as using clustering, a database lookup, or other means. A first recommendation function can recommend to a user items, such as books to check out, automobiles to purchase, people to date, etc. Another modular recommendation function can be daisy chained with the first to recommend items that are similar or related to the first recommended items, such as users who have also checked out the same recommended book, trailers that can be towed by the recommended automobiles, or vacations booked by people that were recommended as people to date. The modular recommendation functions can be used to build customized recommendation engines for different industries.

Abstract: Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for graph-based semi-supervised learning of structured tagging models. In one aspect, a method includes creating a graph having a plurality of unique vertices in which vertices in a first set of vertices represent n-grams that are each associated with a respective part-of-speech and that were derived from labeled source domain text, and in which vertices in a different second set of vertices represent n-grams that are not associated with a part-of-speech and that were derived from unlabeled target domain text. A respective measure of similarity is calculated between the vertices in each of the pairs based at least partially on a distance between the respective features of the pair used to weight a graph edge between the pair.

Abstract: In a machine condition monitoring technique, a sensor reading is filtered using a switching Kalman filter. Kalman filters are created to describe separate modes of the signal, including a steady mode and a non-steady mode. For each new observation of the signal, a new mode is estimated based on the previous mode and state, and a new state is then estimated based on the new mode and the previous mode and state. In the steady mode, evolution covariances of both the observed signal and the rate of change of that signal are low. In the non-steady mode, the evolution covariance of the observed signal is set to a higher value, permitting the observed signal to vary widely, while the evolution covariance of the rate of change of the signal is maintained at a low level.

Abstract: Non-mechanistic, differential-equation-free approaches for predicting a particular response of a system to a given input are provided in the form of systems, methods, and devices. These approaches are generally directed to a non-compartmental method of predicting a time-dependent response of a component of a system to an input into the system. The systems, methods, and devices provide the ability to (i) reduce the cost of research and development by offering an accurate modeling of heterogeneous and complex physical systems; (ii) reduce the cost of creating such systems and methods by simplifying the modeling process; (iii) accurately capture and model inherent nonlinearities in cases where sufficient knowledge does not exist to a priori build a model and its parameters; and, (iv) provide one-to-one relationships between model parameters and model outputs, addressing the problem of the ambiguities inherent in the current, state-of-the-art systems and methods.

Abstract: Methods and systems for performing computer based education are described herein. According to various aspects, a user is presented with computer-based education regarding completion of an objective within an interactive computing environment. When the user is ready to perform (or attempt to perform) the objective in a real-world or “live” situation, the software may place the user in a training session where other users are actually computer-controlled participants, or bots, having a prescribed level of artificial intelligence. If the user successfully completes the objective, the software may increment the level of AI until the user completes the objective while interacting with bots having a required level of AI. The user may thereafter be allowed to participate in dynamic sessions with other human users. During training sessions the user may be affirmatively led to believe that other participants are human, rather than bots.

Abstract: A truth maintenance method and system. The method includes receiving by a computer processor, health event data associated with heath care records for patients. The computer processor associates portions of the health event data with associated patients and related records in a truth maintenance system database. The computer processor derives first health related assumption data and retrieves previous health related assumption data derived from and associated with previous portions of previous health event data. The computer processor executes non monotonic logic with respect to the first health related assumption data and the previous health related assumption data. In response, the computer processor generates and stores updated first updated health related assumption data associated with the first health related assumption data and the previous health related assumption data.

Abstract: The present disclosure relates to methods of rapidly and efficiently searching biologically-related data space to identify a population set maximally diverse and optimized for sets of desired properties. More specifically, the disclosure provides methods of identifying a diverse, evolutionary separated bio-molecules with desired properties from complex bio-molecule libraries. The disclosure additionally provides digital systems and software for performing these methods.

Abstract: A truth maintenance method and system. The method includes receiving by a computer processor from RFID tags embedded in sensors, event data associated with events detected by said sensors. The computer processor associates portions of the event data with associated RFID tags and derives assumption data associated with each portion of the portions. The computer processor retrieves previous assumption data derived from and associated with previous portions of previous event data retrieved from the RFID tags and executes non monotonic logic with respect to the assumption data and the previous assumption data. In response, the computer processor generates and stores updated assumption data associated with the assumption data and the previous assumption data.

Abstract: The invention discloses a method for building adaptive soft sensor. The method comprises the following steps. The input and schedule vectors are constructed, and a novel learning algorithm that uses online subtractive clustering is used to recursively update the structure and parameters of a local model network. Three rules are proposed for updating centers and local model coefficients of existing clusters, for generating new clusters and new models as well as for merging existing clusters and their corresponding models. Once verified, the online inferential model can be created to generate the predicted value of process. Thus, it does not need much memory space to process the method and can be easily applied to any other machine.