Abstract: An image captured at a first moment in time is received. A user is identified by comparing at least one facial feature extracted from the image with user information stored in a database. It is determined whether the user observed a visual display by determining whether the visual display was within the visual field of the user. Upon determining that the user observed the visual display, the image is processed with a sentiment analysis module to determine a sentiment of the user. Further, it is determined, based on a record stored in a transaction database, that the user purchased the first product at a second moment in time, and an engagement index is generated for the visual display based on processing the determined sentiment of the user and a period of elapsed time between the second moment in time and the first moment in time.

Abstract: An image captured at a first moment in time is received. A user is identified by comparing at least one facial feature extracted from the image with user information stored in a database. It is determined whether the user observed a visual display by determining whether the visual display was within the visual field of the user. Upon determining that the user observed the visual display, the image is processed with a sentiment analysis module to determine a sentiment of the user. Further, it is determined, based on a record stored in a transaction database, that the user purchased the first product at a second moment in time, and an engagement index is generated for the visual display based on processing the determined sentiment of the user and a period of elapsed time between the second moment in time and the first moment in time.

Abstract: Methods and systems for detecting anomalous behavior include performing a principal component analysis on a plurality of key performance indicators (KPIs) to determine a set of principal axes. The KPIs are clustered in a space defined by the set of principal axes. Local anomalies are determined in the clustered KPIs by comparing, for each individual KPI in clusters that conform to a Gaussian distribution, a distance from a respective cluster mean to a threshold. Structural anomalies are determined in the clustered KPIs. The structural and local anomalies are classified based on historical information. A management action is performed based on the classified structural and local anomalies.

Abstract: Methods and systems for detecting anomalous behavior include performing a principal component analysis on a plurality of key performance indicators (KPIs) to determine a set of principal axes. The KPIs are clustered in a space defined by the set of principal axes. Local and structural anomalies are determined in the clustered KPIs. The structural and local anomalies are classified based on historical information. A transformation is performed from a space based on the principal axes to an original space. It is determined whether each of the local and structural anomalies is a global or a local anomaly. A management action is performed based on the classified structural and local anomalies.

Abstract: Approaches for generating an alert in an absence of a radio-frequency identification (RFID) tag in proximity to a mobile device are provided herein. RFID tags are detected in proximity to the first mobile device, which has a RFID receiver. The alert is generated in response to alert conditions, including a determination that a RFID tag identifier stored in a first profile list is not among detected RFID tags and that an RFID tag stored in the first profile list is not in proximity to a second device. The alert is transmitted to the second mobile device, wherein the alert adds, responsive to the stored RFID tag not being among the detected RFID tags at the first device, the stored RFID tag to a second profile list associated with the second mobile device for storing RFID tag identifiers, wherein the second profile list is separate from the first profile list.

Abstract: A method and system for testing performance of a software product. One or more complete executions of a performance test of corresponding versions of the software product are performed. The complete executions of the performance test identifies a steady state value of each performance parameter monitored during the performance test after each performance parameter has transitioned to a steady state during the performance test. A performance profile of the software product is determined according to the complete executions of the performance test. Partial executions of the performance test of corresponding further versions of the software product are performed, each partial execution having a partial duration preceding the steady state of each performance parameter. Corresponding results of the partial executions of the performance test are estimated according to the performance profile from corresponding partial trends of each performance parameter during the partial executions of the performance test.

Abstract: A method for generating an alert on a mobile device in an absence of a radio-frequency identification (RFID) tag in proximity to the mobile device is provided herein. The method comprises defining an event. A profile list for storing RFID tag identifiers is related to the event. The method also comprises sharing the event data together with the profile list using a social media network, storing all received RFID tag identifiers at a time within the duration of the event after an event start time in the profile list if the profile list was empty before the event start time, and generating the alert under alert conditions. The alert conditions comprise a determination that the profile list was not empty before the event start time, and that one RFID tag identifier stored in the profile list is not among the received RFID tag identifiers during the event duration after the event time.

Abstract: Approaches for generating an alert in an absence of a radio-frequency identification (RFID) tag in proximity to a mobile device are provided herein. RFID tags are detected in proximity to the first mobile device, which has a RFID receiver. The alert is generated in response to alert conditions, including a determination that a RFID tag identifier stored in a first profile list is not among detected RFID tags and that an RFID tag stored in the first profile list is not in proximity to a second device. The alert is transmitted to the second mobile device, wherein the alert adds, responsive to the stored RFID tag not being among the detected RFID tags at the first device, the stored RFID tag to a second profile list associated with the second mobile device for storing RFID tag identifiers, wherein the second profile list is separate from the first profile list.

Abstract: An image captured at a first moment in time is received. A user is identified by comparing at least one facial feature extracted from the image with user information stored in a database. It is determined whether the user observed a visual display by determining whether the visual display was within the visual field of the user. Upon determining that the user observed the visual display, the image is processed with a sentiment analysis module to determine a sentiment of the user. Further, it is determined, based on a record stored in a transaction database, that the user purchased the first product at a second moment in time, and an engagement index is generated for the visual display based on processing the determined sentiment of the user and a period of elapsed time between the second moment in time and the first moment in time.

Abstract: An image captured at a first moment in time is received. A user is identified by comparing at least one facial feature extracted from the image with user information stored in a database. It is determined whether the user observed a visual display by determining whether the visual display was within the visual field of the user. Upon determining that the user observed the visual display, the image is processed with a sentiment analysis module to determine a sentiment of the user. Further, it is determined, based on a record stored in a transaction database, that the user purchased the first product at a second moment in time, and an engagement index is generated for the visual display based on processing the determined sentiment of the user and a period of elapsed time between the second moment in time and the first moment in time.

Abstract: Methods and systems for detecting anomalous behavior include performing a principal component analysis on a plurality of key performance indicators (KPIs) to determine a set of principal axes. The KPIs are clustered in a space defined by the set of principal axes. Local anomalies are determined in the clustered KPIs by comparing, for each individual KPI in clusters that conform to a Gaussian distribution, a distance from a respective cluster mean to a threshold. Structural anomalies are determined in the clustered KPIs. The structural and local anomalies are classified based on historical information. A management action is performed based on the classified structural and local anomalies.

Abstract: Methods and systems for detecting anomalous behavior include performing a principal component analysis on a plurality of key performance indicators (KPIs) to determine a set of principal axes. The KPIs are clustered in a space defined by the set of principal axes. Local and structural anomalies are determined in the clustered KPIs. The structural and local anomalies are classified based on historical information. A transformation is performed from a space based on the principal axes to an original space. It is determined whether each of the local and structural anomalies is a global or a local anomaly. A management action is performed based on the classified structural and local anomalies.

Abstract: Methods and systems for detecting anomalous behavior include performing a principal component analysis on a plurality of key performance indicators (KPIs) to determine a set of principal axes. The KPIs are clustered in a space defined by the set of principal axes. Local and structural anomalies are determined in the clustered KPIs. The structural and local anomalies are classified based on historical information. A management action is performed based on the classified structural and local anomalies.

Abstract: A method and system for testing performance of a software product. One or more complete executions of a performance test of corresponding versions of the software product are performed. The complete executions of the performance test identifies a steady state value of each performance parameter monitored during the performance test after each performance parameter has transitioned to a steady state during the performance test. A performance profile of the software product is determined according to the complete executions of the performance test. Partial executions of the performance test of corresponding further versions of the software product are performed, each partial execution having a partial duration preceding the steady state of each performance parameter. Corresponding results of the partial executions of the performance test are estimated according to the performance profile from corresponding partial trends of each performance parameter during the partial executions of the performance test.

Abstract: A method for generating an alert on a mobile device in an absence of a radio-frequency identification (RFID) tag in proximity to the mobile device is provided herein. The method comprises defining an event. A profile list for storing RFID tag identifiers is related to the event. The method also comprises sharing the event data together with the profile list using a social media network, storing all received RFID tag identifiers at a time within the duration of the event after an event start time in the profile list if the profile list was empty before the event start time, and generating the alert under alert conditions. The alert conditions comprise a determination that the profile list was not empty before the event start time, and that one RFID tag identifier stored in the profile list is not among the received RFID tag identifiers during the event duration after the event time.

Abstract: Methods and systems for detecting anomalous behavior include performing a principal component analysis on a plurality of key performance indicators (KPIs) to determine a set of principal axes. The KPIs are clustered in a space defined by the set of principal axes. Local and structural anomalies are determined in the clustered KPIs. The structural and local anomalies are classified based on historical information. A management action is performed based on the classified structural and local anomalies.