Abstract: A schedule data structure includes a schedule of visits to a plurality of destinations over a plurality of weeks, the visits being associated with respective rider/vehicle identification (RVID) parameters corresponding to one of the plurality of riders/vehicles. The schedule may be optimized for multiple parameters but non-optimized for mirroring. The schedule data structure may be broken into a first part and a second part. A permutation of the first part may be determined and appended with the second part. A mirroring-improved schedule data structure may be determined in response to iterated permutation and appending.

Abstract: A method for mitigating physical risks associated with a user in an Internet of Things (IoT) environment includes monitoring multi-modal input data associated with at least one multi-modal interaction of the user with at least one IoT device, identifying a change in at least one cognitive ability of the user, estimating a cognitive ability index of the user, predicting at least one physical risk associated with a current user activity, determining at least one corrective action to avoid the at least one physical risk, and controlling at least one IoT device to notify or perform the at least one corrective action such that the at least one physical risk is mitigated.

Abstract: A system includes an input interface receiving conversation input from at least one system participant. A natural language processor operates on the conversational input. A sentiment processor operates on the pre-processed input using a sentiment classification model to predict sentiment, the sentiment processor predicting positive, neutral, and negative sentiment for the pre-processed input. An emotion processor receiving the pre-processed input from the natural language processor and a corresponding sentiment from the sentiment processor and operates to predict an emotion class and a strength of the emotion based on the corresponding sentiment. An output mechanism generates sentiment strength for the conversation input based on the emotion class and strength of the emotion.

Abstract: A system 100 for data warehouse workload transformation is disclosed. A data extraction module 110 receives job metadata from one or more extract transform load applications, extracts domain logic information from the job metadata. A canonical model generation module 120 creates one or more relational models from the domain logic information, generates a canonical model for the job metadata by merging the one or more relational models . A model optimization module 130 creates a query execution plan using an optimization technique, passes the canonical model through one or more optimization layers, and optimizes the query execution plan to execute common logic at a single point of time for removing one or more redundant operations. A code generation module 140 generates an output code corresponding to the predefined target environment from an optimized canonical model, upon mapping of the one or more entities, for the workload transformation.

Abstract: Quantum computers with a limited number of input qubits are used to perform machine learning processes having a far greater number of trainable features. A list of features of a field are divided into a plurality of feature groups. Each of the feature groups includes a respective group of some, but not all, of the features. A first machine learning process is performed to train a first instance of a quantum computer model, where the feature groups are used as inputs. Based on the first machine learning process being performed, a subset of the feature groups is selected for a second machine learning process. Thereafter, the second machine learning process is performed to train one or more second instances of the quantum computer model. The individual features of the selected subset of the feature groups are used as inputs for the second instances of the quantum computer model.

Abstract: A system for data warehouse migration is disclosed. The system 100 includes a parsing module 110 to receive one or more input constructs from a source database in a first syntactical dialect, parse the one or more input constructs received in the first syntactical dialect using an external domain specific language parser, converts the one or more input constructs upon parsing into an abstract syntax tree corresponding to the first syntactical dialect of the source database. A canonicalization module 120 transforms the abstract syntax tree into a canonical abstract syntax tree by utilizing a library of a plurality of operators and expressions corresponding to the first syntactical dialect. A tree optimization module 130 optimizes the canonical abstract syntax tree by utilizing a set of optimization rules.

Abstract: Neural network systems are provided that comprise one or more neural networks. The first neural network can comprise a convolutional neural network (CNN) long short-term memory (LSTM) architecture for receiving a primary data set comprising text messages and output a primary data structure comprising a text pattern-based feature. The second neural network can comprise a CNN architecture for receiving a secondary data sets derived from the primary data set and output a plurality of secondary data structures. The third neural network can combine the data structures to produce a combined data structure, and then process it to produce a categorized data structure comprising the text messages assigned to targets. The primary data set can comprise hate speech and the categorized data structure can comprise target categories, for example, hate targets. Methods of operating neural network systems and computer program products for performing such methods are also provided.

Abstract: Systems, methods, and computer program products are provided for determining an event parameter are provided. Event data can be matched to a grid comprising gridlines and cells defined by the gridlines. The grid can be mapped to a predetermined area. Each cell can comprise a number of events per predetermined time interval. The cells can be sorted into classes based on the number of events occurring during the predetermined time interval to produce a classified data set. Features can be extracted from the classified data set. The extracted features can be processed using a classifier to determine the event parameter for a future time interval in at least one cell of the cells, for example, crime events. The classifier can comprise a neural network. Systems can comprise one or more of a processor, a neural network, and a user interface.

Abstract: A method for determining one or more missing slots associated with a voice command for an advanced voice interaction is provided. The method includes receiving the voice command from a user. The method includes generating a textual input from the voice command received from the user. The method further includes identifying one or more intents, one or more slots and a relation between the one or more intents and the one or more slots associated with the textual input. The method also includes identifying one or more key phrases associated with the textual input and one or more domains associated with the textual input based on the one or more key phrases. The method also includes identifying one or more missing slots associated the one or more domains for the one or more intents based on fetching information associated with the one or more missing slots from a domain specific knowledge base.

Abstract: A system for planning a data warehouse migration is provided. The system includes an extraction module 40 which extracts specific data from a data warehouse in a form of files upon registering a data warehouse owner on a centralized platform via a device. The system also includes a processing module 50 which processes the files using a processing technique to identify features of the data warehouse. The system also includes a migration planning module 60 which generates clusters of objects using a clustering technique, wherein the objects within at least one of the clusters are migrated together as the corresponding objects are related to each other with a first predefined relationship and generates a migration order according to which the objects are to be migrated based on one of the clusters generated, a second predefined relationship between the clusters generated, or a combination thereof, thereby planning the data warehouse migration.

Abstract: A system for data reconciliation is provided. The data reconciliation system includes a data processing subsystem. The data processing subsystem includes a computation module, configured to generate hash values for a set of tables located in a source database by a hashing technique and also configured generate hash values for a set of tables located in a destination database by the hashing technique. The data processing subsystem also includes an analysis module, configured to analyse the hash values located in the source database and the hash values located in the destination database by a pre-determined rule. The data processing subsystem also includes a suggestion module, configured to suggest output based on the analysis result. A data memory subsystem is configured to store the generated hash values for the source database and the generated hash values for the destination database. Present invention provides safe migration or transferring of data.

Abstract: Low-performing cells, serving a telecom deployment in a given geographical area, are commonly identified by the telecom operators based on one or more Network KPIs computed for each of the cells being part of the deployment. However, most of these KPIs describe the overall state of affairs of the cell without any insight into the user usage profile of the cell. The present disclosure proposes a novel method to adjust the network KPIs based on scores of the macro cell or the small cell (101) with the user usage profile of the cell to obtain the user correlated network scores of the cells and prioritize the low-performing cells in the network in order of degree of impact on users and their usage. Another aspect of this disclosure is that it shall predict and compute a realistic user score to get predictive insights into user profiles for solutions and preventive measures.

Abstract: Techniques are disclosed relating to feature selection based on feature-ranking-based optimization models. In various embodiments, for example, the disclosed techniques include accessing a training dataset that includes a plurality of data samples that include data values for a plurality of features, and a set of labels corresponding to the plurality of data samples. In some embodiments, a computer system processes the training dataset based on an optimization model to generate weighting values for the plurality of features. In some embodiments, for example, processing the training dataset includes using quantum annealing to determine a minimization of an objective function utilized in the optimization model, where the minimization of the objective function corresponds to an output value that indicates the weighting values for the plurality of features. In some embodiments, the weighting values correspond to a relative ranking of the plurality of features.

Abstract: Techniques are disclosed relating to feature selection based on feedback-assisted optimization models. In various embodiments, for example, the disclosed techniques include accessing a training dataset that includes a plurality of data samples that include data values for a plurality of features, and a set of labels corresponding to the plurality of data samples. In some embodiments, a computer system performs feature-selection operations to select, from the plurality of features, a subset of features to include in a reduced feature set. For example, in some embodiments the feature-selection operations include processing the training dataset based on an optimization model, where an objective function utilized in the optimization model utilizes performance feedback information corresponding to machine learning models that are trained based on candidate feature sets.

Abstract: Techniques are disclosed relating to feature selection using multivariate effect optimization models. In some embodiments, for example, the disclosed techniques include accessing a training dataset that includes a plurality of data samples that include data values for a plurality of features, and a set of labels corresponding to the plurality of data samples. In various embodiments, a computer system processes the training dataset based on an optimization model to select, from the plurality of features, a subset of features to include in a reduced feature set. For example, in some embodiments processing the training dataset based on the optimization model includes selecting the subset of features that maximizes a measure of relevancy between pairs of the plurality of features and the set of labels, and selecting the subset of features that minimizes a measure of redundancy between groups of three or more features.

Abstract: Systems and methods for identifying a cell suspension with therapeutic potential for skin regeneration and related compositions are disclosed herein. In some variations, a method may include receiving a cell suspension that comprises a population of viable cells and non-viable cells, then measuring a value indicative of at least one characteristic of the cell suspension, such as but not limited to one or more of total cell count, total cell viability, cell viability percentage, and median live cell diameter. A cell suspension composition having therapeutic potential may comprise a cell suspension met certain thresholds relating to total cell count, total viable cell count, cell viability percentage, and median live cell diameter.

Abstract: Systems and methods for identifying a cell suspension with therapeutic potential for skin regeneration and related compositions are disclosed herein. In some variations, a method may include receiving a cell suspension that comprises a population of viable cells and non-viable cells, then measuring a value indicative of at least one characteristic of the cell suspension, such as but not limited to one or more of total cell count, total cell viability, cell viability percentage, and median live cell diameter. A cell suspension composition having therapeutic potential may comprise a cell suspension met certain thresholds relating to total cell count, total viable cell count, cell viability percentage, and median live cell diameter.

Abstract: A software application or module enables real-time tracking and auditing of general ledger assertions in real-time during the processing of a given event with respect to a particular contract, ensuring that all entries are reconciled and recorded as they occur. The system allows an internal audit to be performed in real-time, and can be configured to automatically block workflow in the case of a discrepancy between a contract and the general ledger as revealed by the audit.

Abstract: A digital processing system receives, in a pre-boot duration, an indication from a user to retrieve a credential required for booting the digital processing system. The digital processing system connects, in the pre-boot duration, to a user device and retrieves, in the pre-boot duration, the credential from an external server using the user device. Booting is thereafter continued. In an embodiment, a BIOS (basic input/output system) software performs the receiving, the connecting, the retrieving, and completes the booting upon initialization of the digital processing system.