The Experts below are selected from a list of 9 Experts worldwide ranked by ideXlab platform

Jan-niklas Voigt-antons - One of the best experts on this subject based on the ideXlab platform.

  • QoMEX - Predicting personality traits from touchscreen based interactions
    2018 Tenth International Conference on Quality of Multimedia Experience (QoMEX), 2018
    Co-Authors: Ludwig Kuster, Carola Trahms, Jan-niklas Voigt-antons
    Abstract:

    Human Influence Factors can have a strong impact on how users perceive the quality of a given system. Traditional measures such as questionnaires can be a time consuming and partially invasive means to assess Human Influence Factors like personality. In this paper, we investigate whether an individual's personality traits can be classified based solely upon the characteristics of their touchscreen usage. We record the tablet input of 75 subjects using a cognitive training application. The application requires the user to spell words by tapping on letters and dragging them to their denoted position on the screen. The task is presented in two conditions: in one with normal functionality of the program, the other with the usability of the application impaired. The subject's personality is measured with the NEO-FFI questionnaire and captured in the five dimensions of the five-Factor model (Big 5). The personality scores and 68 features (touch-behavior and task-performance), as well as statistical metrics derived from them, are fed to a number of classification algorithms. Our results show that in a binary classification task with normal usability, high levels of ‘Neuroticism’ can be distinguished from low levels with a mean accuracy of 66 percent. The extent to which a personality dimension can be predicted is dependent on the usability of the test system. In a normal setting, ‘Extraversion’ can be predicted with an accuracy of 61 percent. However, with impaired usability, the prediction rises to an average of 67 percent. The experiment shows that records of touchscreen interactions allow for the prediction of personalities significantly better than random. The study of the Human Influence Factor personality and its relation to perceived quality would be facilitated by using touchscreen interaction data as a fast and easily accessible estimate of a user's personality.

Ludwig Kuster - One of the best experts on this subject based on the ideXlab platform.

  • QoMEX - Predicting personality traits from touchscreen based interactions
    2018 Tenth International Conference on Quality of Multimedia Experience (QoMEX), 2018
    Co-Authors: Ludwig Kuster, Carola Trahms, Jan-niklas Voigt-antons
    Abstract:

    Human Influence Factors can have a strong impact on how users perceive the quality of a given system. Traditional measures such as questionnaires can be a time consuming and partially invasive means to assess Human Influence Factors like personality. In this paper, we investigate whether an individual's personality traits can be classified based solely upon the characteristics of their touchscreen usage. We record the tablet input of 75 subjects using a cognitive training application. The application requires the user to spell words by tapping on letters and dragging them to their denoted position on the screen. The task is presented in two conditions: in one with normal functionality of the program, the other with the usability of the application impaired. The subject's personality is measured with the NEO-FFI questionnaire and captured in the five dimensions of the five-Factor model (Big 5). The personality scores and 68 features (touch-behavior and task-performance), as well as statistical metrics derived from them, are fed to a number of classification algorithms. Our results show that in a binary classification task with normal usability, high levels of ‘Neuroticism’ can be distinguished from low levels with a mean accuracy of 66 percent. The extent to which a personality dimension can be predicted is dependent on the usability of the test system. In a normal setting, ‘Extraversion’ can be predicted with an accuracy of 61 percent. However, with impaired usability, the prediction rises to an average of 67 percent. The experiment shows that records of touchscreen interactions allow for the prediction of personalities significantly better than random. The study of the Human Influence Factor personality and its relation to perceived quality would be facilitated by using touchscreen interaction data as a fast and easily accessible estimate of a user's personality.

Carola Trahms - One of the best experts on this subject based on the ideXlab platform.

  • QoMEX - Predicting personality traits from touchscreen based interactions
    2018 Tenth International Conference on Quality of Multimedia Experience (QoMEX), 2018
    Co-Authors: Ludwig Kuster, Carola Trahms, Jan-niklas Voigt-antons
    Abstract:

    Human Influence Factors can have a strong impact on how users perceive the quality of a given system. Traditional measures such as questionnaires can be a time consuming and partially invasive means to assess Human Influence Factors like personality. In this paper, we investigate whether an individual's personality traits can be classified based solely upon the characteristics of their touchscreen usage. We record the tablet input of 75 subjects using a cognitive training application. The application requires the user to spell words by tapping on letters and dragging them to their denoted position on the screen. The task is presented in two conditions: in one with normal functionality of the program, the other with the usability of the application impaired. The subject's personality is measured with the NEO-FFI questionnaire and captured in the five dimensions of the five-Factor model (Big 5). The personality scores and 68 features (touch-behavior and task-performance), as well as statistical metrics derived from them, are fed to a number of classification algorithms. Our results show that in a binary classification task with normal usability, high levels of ‘Neuroticism’ can be distinguished from low levels with a mean accuracy of 66 percent. The extent to which a personality dimension can be predicted is dependent on the usability of the test system. In a normal setting, ‘Extraversion’ can be predicted with an accuracy of 61 percent. However, with impaired usability, the prediction rises to an average of 67 percent. The experiment shows that records of touchscreen interactions allow for the prediction of personalities significantly better than random. The study of the Human Influence Factor personality and its relation to perceived quality would be facilitated by using touchscreen interaction data as a fast and easily accessible estimate of a user's personality.

Emily A. Bradley - One of the best experts on this subject based on the ideXlab platform.

  • Comparison of watershed sediment delivery estimates of 60 Michigan rivers using the USACE Great Lakes regional trend line and the Syvitski and Milliman global BQART equation
    Journal of Hydrology, 2020
    Co-Authors: John H. Barkach, Carol J. Miller, James P. Selegean, Emily A. Bradley
    Abstract:

    Abstract The purpose of this research was to compare annual watershed sediment delivery estimates for 60 Michigan rivers using two fundamentally different approaches: the Great Lakes regional trend line that was developed by the U.S. Army Corps of Engineers (USACE) and the global BQART watershed sediment delivery equation that was developed by Syvitski and Milliman (2007) . In addition, for six of the 60 watersheds, the global BQART equation and the USACE Great Lakes regional trend line were compared to watershed sediment delivery estimates that were prepared by the USACE using complex, calibrated hydrodynamic and sediment delivery models. The USACE Great Lakes regional trend line is an empirical equation that was developed based on sediment delivery estimates from 48 reservoirs and 13 watersheds located throughout the Great Lakes basin and predicts watershed sediment delivery based on watershed area (R2=0.78). The Syvitski and Milliman BQART equation was developed from a database encompassing 488 global rivers whose watersheds cover 63% of the earth’s surface. The BQART equation estimates watershed sediment delivery as dependent on five variables including: a geologic and Human Influence Factor (B), the mean annual flow of the river (Q), watershed area (A), the difference between the maximum elevation of the watershed and the elevation of the receiving water (relief; R), and, mean basin temperature (T). The global BQART sediment delivery equation was validated for rivers with mean annual flows exceeding 30 meters3/sec. The watersheds for the 60 Michigan rivers evaluated in the present research cover 128,043 kilometers2, and the mean annual river flows range from 1.0 meter3/sec (Days River) to 132.5 meters3/sec (St. Joseph River), and average 22 meters3/sec. Overall, the watershed sediment delivery estimates for these 60 rivers using the global BQART equation were 19% lower than those based on the USACE Great Lakes regional trend line and were within 25% of the USACE regional trend line for 21 of the 60 rivers evaluated. With respect to the 12 Michigan rivers with mean annual flows greater than 30 meters3/sec, the global BQART sediment delivery estimates were on average 32% higher than the USACE Great Lakes regional trend line. Of the remaining 48 rivers with mean annual flows of less than 30 meters3/sec, the global BQART sediment delivery estimates were on average 31% lower than the USACE Great Lakes regional trend line. The global BQART equation provided close estimates of watershed sediment delivery for 21 of the 60 Michigan rivers evaluated in this research in comparison to the USACE Great Lakes regional trend line, especially for rivers with mean annual flows greater than 30 meters3/sec. This implies that the global and Great Lakes regional processes of soil erosion and deposition, and sediment transport to the river outlet are similar, especially for the large Michigan watersheds. Regression analysis comparing the terms of the global BQART equation to the 60 watershed sediment delivery estimates developed using the USACE (2010) Great Lakes regional trend line revealed that the most important variables affecting watershed sediment delivery are watershed area (A), mean annual river flow (Q), and relief (R).

John H. Barkach - One of the best experts on this subject based on the ideXlab platform.

  • Comparison of watershed sediment delivery estimates of 60 Michigan rivers using the USACE Great Lakes regional trend line and the Syvitski and Milliman global BQART equation
    Journal of Hydrology, 2020
    Co-Authors: John H. Barkach, Carol J. Miller, James P. Selegean, Emily A. Bradley
    Abstract:

    Abstract The purpose of this research was to compare annual watershed sediment delivery estimates for 60 Michigan rivers using two fundamentally different approaches: the Great Lakes regional trend line that was developed by the U.S. Army Corps of Engineers (USACE) and the global BQART watershed sediment delivery equation that was developed by Syvitski and Milliman (2007) . In addition, for six of the 60 watersheds, the global BQART equation and the USACE Great Lakes regional trend line were compared to watershed sediment delivery estimates that were prepared by the USACE using complex, calibrated hydrodynamic and sediment delivery models. The USACE Great Lakes regional trend line is an empirical equation that was developed based on sediment delivery estimates from 48 reservoirs and 13 watersheds located throughout the Great Lakes basin and predicts watershed sediment delivery based on watershed area (R2=0.78). The Syvitski and Milliman BQART equation was developed from a database encompassing 488 global rivers whose watersheds cover 63% of the earth’s surface. The BQART equation estimates watershed sediment delivery as dependent on five variables including: a geologic and Human Influence Factor (B), the mean annual flow of the river (Q), watershed area (A), the difference between the maximum elevation of the watershed and the elevation of the receiving water (relief; R), and, mean basin temperature (T). The global BQART sediment delivery equation was validated for rivers with mean annual flows exceeding 30 meters3/sec. The watersheds for the 60 Michigan rivers evaluated in the present research cover 128,043 kilometers2, and the mean annual river flows range from 1.0 meter3/sec (Days River) to 132.5 meters3/sec (St. Joseph River), and average 22 meters3/sec. Overall, the watershed sediment delivery estimates for these 60 rivers using the global BQART equation were 19% lower than those based on the USACE Great Lakes regional trend line and were within 25% of the USACE regional trend line for 21 of the 60 rivers evaluated. With respect to the 12 Michigan rivers with mean annual flows greater than 30 meters3/sec, the global BQART sediment delivery estimates were on average 32% higher than the USACE Great Lakes regional trend line. Of the remaining 48 rivers with mean annual flows of less than 30 meters3/sec, the global BQART sediment delivery estimates were on average 31% lower than the USACE Great Lakes regional trend line. The global BQART equation provided close estimates of watershed sediment delivery for 21 of the 60 Michigan rivers evaluated in this research in comparison to the USACE Great Lakes regional trend line, especially for rivers with mean annual flows greater than 30 meters3/sec. This implies that the global and Great Lakes regional processes of soil erosion and deposition, and sediment transport to the river outlet are similar, especially for the large Michigan watersheds. Regression analysis comparing the terms of the global BQART equation to the 60 watershed sediment delivery estimates developed using the USACE (2010) Great Lakes regional trend line revealed that the most important variables affecting watershed sediment delivery are watershed area (A), mean annual river flow (Q), and relief (R).