Abstract: The illustrative embodiments described herein provide a computer implemented method, apparatus, and computer program product for generating furtive glance cohorts. In an illustrative embodiment, video data of a monitored population is received and processed to form digital video data. The digital video data includes metadata describing glancing patterns associated with one or more subjects from the monitored population. The digital video is analyzed to identify a set of furtive glance patterns from the glancing patterns. One or more furtive glance attributes for the set of furtive glance cohorts are selected from the set of furtive glance patterns. Thereafter, the set of furtive glance cohorts is generated. The set of furtive glance cohorts have members selected from the monitored population and have at least one furtive glance attribute in common.

Abstract: A computer implemented method, apparatus, and computer program product for generating video based cohorts. Digital video data is processed to identify a set of size and shape based attributes associated with the set of objects. The digital video data comprises metadata describing the set of objects. A size and shape attribute comprises an attribute describing a shape associated with a portion of an object or a size measurement of the portion of the object. The set of size and shape based attributes are analyzed using cohort criteria to form a result. The cohort criteria specify attributes that are associated with members of a given cohort. A set of cohorts is generated based on the result. Each cohort in the set of cohorts comprises a subset of objects from the set of objects that share at least one size and shape based attribute in common.

Abstract: The illustrative embodiments described herein provide a computer implemented method, apparatus, and computer program product for generating biometric cohorts. In one embodiment, biometric data is received which identifies a set of biometric patterns. The biometric data is received from a set of biometric sensors. The biometric data is processed to form digital biometric data that identifies attributes of the biometric data. In addition, the digital biometric data includes metadata describing the attributes of the biometric data. Thereafter, a set of biometric cohorts is generated using the digital biometric data. Each member of the set of biometric cohorts shares at least one biometric attribute in common.

Abstract: A computer implemented method, apparatus, and computer program product for generating deportment and comportment cohorts. Digital sensor data associated with an individual is received. The digital sensor data comprises event metadata describing a set of events associated with the individual. The set of events comprises at least one of body language, facial expressions, vocalizations, and social interactions of the individual. In response to determining description data for the individual is available, the description data is retrieved. The description data comprises at least one of identification information, past history information, and current status information for the individual. A set of conduct analysis models based on the event metadata and the available description data is selected. The set of conduct analysis models process the event metadata describing the set of events associated with the individual to identify and interpret the set of events.

Abstract: A computer implemented method, apparatus, and computer program product for generating receptivity cohorts. Digital sensor data associated with a set of individuals is retrieved in response to receiving an identification of a proposed future change in a current set of circumstances associated with the set of individuals. The digital sensor data comprises events metadata describing a set of events associated with the set of individuals. The set of events comprises at least one of body language, facial expressions, vocalizations, and social interactions of the set of individuals. An analysis server selects a set of receptivity analysis models based on the proposed future event and the set of events. Each analysis model in the set of receptivity analysis models analyzes the set of events to identify conduct attributes indicating receptiveness of each individual in the set of individuals to the proposed future change.

Abstract: A computer implemented method, apparatus, and computer program product for generating general risk scores for general risk cohorts. Digital sensor data associated with a general risk cohort is received from a set of multimodal sensors. The digital sensor data comprises metadata describing attributes associated with at least one member of the general risk cohort. Each member of the general risk cohort comprises data describing objects belonging to a category. A general risk score for the general risk cohort is generated based on selected risk factors and the attributes associated with the at least one member of the general risk cohort. In response to a determination that the general risk score exceeds a risk threshold, a response action is initiated.

Abstract: A computer implemented method, apparatus, and computer program product for generating video based cohorts. Digital video data is processed to identify a set of color and texture based attributes associated with the set of objects. The digital video data comprises metadata describing the set of objects. The set of color and texture based attributes are analyzed using cohort criteria to form a result. The cohort criteria specify attributes that are associated with members of a given cohort. A set of cohorts is generated based on the result. Each cohort in the set of cohorts comprises a subset of objects from the set of objects that share at least one color and texture based attribute in common.

Abstract: A computer implemented method, apparatus, and computer program product for generating olfactory cohorts. Olfactory data is received from a set of chemical sensors. The olfactory data describes a set of olfactory patterns for an air sample. The olfactory data is processed to identify attributes of particles in the air sample and generate digital olfactory data. The digital olfactory data comprises metadata describing the attributes of the particles in the air sample to form digital olfactory data. A set of olfactory cohorts is generated using the attributes in the digital olfactory data.

Abstract: A computer implemented method, apparatus, and computer program product for generating audio cohorts. An audio analysis engine receives audio data from a set of audio input devices. The audio data is associated with a plurality of objects. The audio data comprises a set of audio patterns. The audio data is processed to identify attributes of the audio data to form digital audio data. The digital audio data comprises metadata describing the attributes of the audio data. A set of audio cohorts is generated using the digital audio data and cohort criteria. Each audio cohort in the set of audio cohorts comprises a set of objects from the plurality of objects that share at least one audio attribute in common.

Abstract: A dynamically determined data-driven model for detecting fraudulent behavior is provided. An initial model is developed using historical data, such as demographic, psychographic, transactional, and environmental data, using data-driven discovery techniques, such as data mining, and may be validated using additional statistical techniques. The noise within the data models determine appropriate initial control points needed for the initial model. These initial control points define an ‘electronic fence,’ wherein data points within the fence represent acceptable behavior and data points outside the fence represent unacceptable behavior. Updated data is received. A fraud detection mechanism validates the updated data using data mining and statistical methods. The data model, or ‘electronic fence,’ is refined based on the newly acquired data. The process of refining and updating the data models is iterated until a set of limits is achieved.

Abstract: A method for making an inference based on cumulative data. The method utilizes video, audio, and biometric devices to observe a retail environment for the presence of a customer. Once a customer is present, the method identifies every cohort to which the customer corresponds. Next, the method observes the customer as they peruse aisles in the retail environment. When the customer selects a product, the method identifies the selected product and searches the cohorts for alternate products to offer the customer. The method offers one alternate product to the customer and records to the cohorts whether the customer thereinafter accepts the method's offer and selects the alternate product or rejects the method's offer and continues perusing the retail environment aisles. The method continues observing the customer and offering alternate product until the customer leaves the retail environment.

Abstract: A computer implemented method, apparatus, and computer program product for selectively delivering messages. In one embodiment, the process identifies a set of pervasive devices using detection data. The detection data comprises an electronic signature transmitted from the set of pervasive devices associated with a set of users in a monitored location. The process then assigns a demographic profile to each user of the set of users based on an identity of a pervasive device from the set of pervasive devices which is associated with the user. Thereafter, the process presents a set of messages to the set of users, wherein the set of messages are selected using the demographic profile assigned to each user of the set of users.

Abstract: A computer implemented method, apparatus, and computer program product for developing neuropsychiatric treatment plans. A treatment plan generator receives a set of diagnoses for a patient. The treatment plan generator automatically analyzes medical information in a set of electronic medical literature sources for potential therapies associated with treatment of each identified condition in the set of diagnoses. The treatment plan generator identifies the potential therapies associated with the treatment of each diagnosed condition. The treatment plan generator selects a set of recommended therapies from the potential therapies based on portions of the medical literature describing each therapy in the potential therapies and a medical history for the patient. The treatment plan generator generates a treatment plan. The treatment plan comprises the set of recommended therapies to treat each diagnosed condition in the set of diagnoses.

Abstract: A computer implemented method, apparatus, and computer program product for modifying neuropsychiatric treatment plans based on efficacy of treatment. A current treatment plan comprising a first set of therapies to treat a set of neuropsychiatric conditions and portions of the medical literature associated with the set of neuropsychiatric conditions is retrieved. A set of brain scans of the patient is analyzed to determine a set of changes over time associated with the set of neuropsychiatric conditions. The portions of the medical literature and the set of changes are analyzed to determine a patient rate of response to the treatment plan. If the patient rate of response falls below a threshold expected rate, a set of alternative treatments for the patient is identified. A modified treatment plan is generated using the set of alternative treatments.

Abstract: A computer implemented method, apparatus, and computer program product of determining mechanisms of action for therapies. A first set of brain scans for each subject in a plurality of subjects generated at a first time period and a second set of brain scans for each subject generated at a second time period are received. Each subject is diagnosed with a given condition and received a given therapy. A set of changes in the set of brain scans is identified for the each subject based on a comparison of a first set of regions of interest in the first set of scans for each subject with a second set of regions of interest in the second set of scans for each subject. A set of typical changes attributable to the given therapy is identified. A mechanism of action for the given therapy is generated based on the set of typical changes.

Abstract: A computer implemented method, apparatus, and computer program product for generating neuropsychiatric diagnoses. Quantitative information describing diagnostic characteristics associated with a patient is generated based on an analysis of a set of patient scans. The quantitative information comprises a set of indictors associated with regions of interest in the set of scans for the patient. The set of indicators of potential neuropsychiatric conditions is compared with a set of diagnostic signatures. A diagnostic signature comprises a set of indicators of a known neuropsychiatric condition. Matching signatures are identified. A matching signature is a diagnostic signature that corresponds to at least one indicator in the set of indicators to form a set of signatures. A diagnosis associated with each signature in the set of signatures is identified to form a set of potential diagnoses. The set of potential diagnoses is presented with links to relevant portion of the medical literature.

Abstract: A computer implemented method, apparatus, and computer program product for determining the efficacy of neuropsychiatric therapy is provided. A neuroimage mapping manager automatically compares a first set of regions of interest in a first set of scans taken at a first time to a second set of regions of interest in a second set of scans generated at a second time and identifies a set of changes in the regions of interest occurring over time. The neuroimage mapping manager searches a set of electronic medical literature sources for medical literature relevant to the set of changes in the regions of interest and identifies portions of the relevant medical literature associated with the set of changes in the regions of interest. The neuroimage mapping manager generates results comprising the set of changes in the regions of interest and a set of links to the portions of the relevant medical literature.

Abstract: A computer implemented method, apparatus, and computer program product for analyzing neurological images. A set of brain scans for a patient is compared to a set of baseline control scans to automatically identify regions of interest in the set of patient scans. A region of interest is an area in a scan that shows an indication of a potential abnormality. A set of electronic medical literature sources is searched for medical literature relevant to the regions of interest in the set of patient scans. The relevant medical literature is correlated to the medical literature describing the regions of interest in the set of patient scans to the regions of interest in the set of patient scans. A result is generated. The result comprises the regions of interest and a set of links to the correlated portions of the relevant medical literature are outputted.

Abstract: A method for managing data. A datum regarding a first patient is received. A first set of relationships is established. The first set of relationships comprises at least one relationship of the datum to at least one additional datum existing in at least one database. A plurality of cohorts to which the first patient belongs is established based on the first set of relationships. Ones of the plurality of cohorts contain corresponding first data regarding the first patient and corresponding second data regarding a corresponding set of additional information. The corresponding set of additional information is related to the corresponding first data. The plurality of cohorts is clustered according to at least one parameter, wherein a cluster of cohorts is formed. A determination is made of which of at least two cohorts in the cluster are closest to each other. The at least two cohorts can be stored.

Abstract: A computer implemented method, apparatus, and computer program product is provided for selecting subjects for treatment study cohorts. A set of selected dimensions for optimizing selection of subjects for a treatment cohort group and a control cohort group associated with a treatment study is identified. Attribute data associated with subjects in the pool of available subjects is clustered at the atomic level to form clustered cohort data. A set of optimized subjects from a pool of available subjects is selected using the clustered cohort data and the set of selected dimensions. Subjects in the set of optimized subjects are optimized across the set of selected dimensions. Each subject in the set of optimized subjects is assigned to the treatment cohort group or the control cohort group.