Kenrick J. Mock

An experimental framework for email categorization and management

Many problems are difficult to adequately explore until a prototype exists in order to elicit user feedback. One such problem is a system that automatically categorizes and manages email. Due to a myriad of user interface issues, a prototype is necessary to determine what techniques and technologies are effective in the email domain. This paper describes the implementation of an add-in for Microsoft Outlook 2000 TM that intends to address two problems with email: 1) help manage the inbox by automatically classifying email based on user folders, and 2) to aid in search and retrieval by providing a list of email relevant to the selected item. This add-in represents a first step in an experimental system for the study of other issues related to information management. The system has been set up to allow experimentation with other classification algorithms and the source code is available online in an effort to promote further experimentation.

Information filtering via hill climbing, WordNet and index patterns

The recent growth of the Internet has left many users awash in a sea of information. This development has spawned the need for intelligent filtering systems. This paper describes work implemented in the INFOS (Intelligent News Filtering Organizational System) project that is designed to reduce the users search burden by automatically categorizing data as relevant or irrelevant based upon user interests. These predictions are learned automatically based upon features taken from input articles and collaborative features derived from other users. The filtering is performed by a hybrid technique that combines elements of a keyword-based hill climbing method, knowledge-based conceptual representation via WordNet, and partial parsing via index patterns. The hybrid system integrating all these approaches combines the benefits of each while maintaining robustness and scalability.

Wildwood: the evolution of L-system plants for virtual environments

This paper describes the Wildwood project. In this work, a genetic algorithm was applied to a simplified L-system representation in order to generate artificial-life style plants for virtual worlds. Acting as a virtual gardener, a human selects which plants to breed, producing a unique new generation of plants. An experiment involving a simulation-style fitness function was also performed, and the virtual plants were adapted to maximize the fitness function.

Gaze-based password authentication through automatic clustering of gaze points

Researchers have proposed systems in which users utilize an eye tracker to enter passwords by merely looking at the proper symbols on the computer monitor in the appropriate order. This authentication method is immune to the practice of shoulder surfing: secretly observing the keystrokes of a legitimate user as he or she types a password on a keyboard. In this paper we describe the EyeDent system—in which users authenticate by looking at the symbols on an on-screen keyboard to enter their password. Existing eye-tracking based authentication systems require the user to dwell or press a trigger when looking at each symbol. Instead, in EyeDent, gaze points are automatically clustered to determine the users selected symbols; this approach has the benefit of allowing users to authenticate at their natural speed, rather than with a fixed dwell time. Additionally, the absence of a visible trigger does not divulge the number of symbols in the password. Results from preliminary investigations indicate that quick (3 seconds for a 4 digit PIN) authentication is possible using this scheme, but more work is needed to account for calibration error, and to dynamically adapt system parameters to the characteristics of individual users.

Real-time continuous iris recognition for authentication using an eye tracker

The majority of todays authentication systems, including password and fingerprint scanners, are based on one-time, static authentication methods. A continuous, real-time authentication system opens up the possibility for greater security, but such a system must be unobtrusive and secure. In this work we studied whether a commercial eye tracker can be used for unobtrusive, continuous, real-time user authentication via iris recognition. In a user study, all 37 participants could be authenticated with 11% equal error rate (EER). For 14 of the 37 users, iris occlusion was sufficiently small to authenticate with 9% EER. When classified using a k-nearest neighbors algorithm and only the right iris, the same data set allowed 100% accuracy for k = 3. Although these error rates are too high for standalone use, iris recognition via an eye tracker might enable real-time continuous authentication when combined with other more reliable authentication means (e.g., a password). As eye trackers become widely available their capabilities for multiple factor, continuous authentication will become compelling.

Dynamic email organization via relevance categories

Many researchers have proposed classification systems that automatically classify email in order to reduce information overload. However, none of these systems are in use today. This paper examines some of the problems with classification technologies and proposes Relevance Categories as a method to avoid some of these problems. In particular, the dynamic nature of email categories, the cognitive overhead, required training categories, and the high costs of classification errors are hurdles for many classification algorithms. Relevance Categories avoid some of these problems through their simplicity; they are merely relevance-ranked lists of email messages that are similar to a set of query messages. by displaying messages as the result of a dynamic query in lieu of fixed categories, we hypothesize that users will be less sensitive to errors using the Relevance Categories scheme than to errors using a fixed categorization scheme. To study the effectiveness of the Relevance Categories concept, we devised a performance metric for relevance ranking and used it to test an inverted index implementation on the Reuter-21578 test collection. The promising test results indicate the need for further work.

Adaptive User Models for Intelligent Information Filtering

As networked systems grow in size, the amount of data available to users has increased dramatically. The result is an information overload for the user. In this project, an intelligent information filtering system reduced the users search burden by automatically eliminating incoming data predicted to be irrelevant. These predictions are learned by adapting an internal user model which is based upon user interactions. This report describes the information filtering problem and examines three techniques for filtering information: global hill climbing, genetic algorithms, and preliminary work with neural networks using radial basis functions. 1 The Information Overload Problem With the advent of networked systems, computer users are inundated with information that they cannot efficiently utilize. Tools are urgently needed to assist the user with information filtering devices in order to reduce the users search burden. This project examined the Usenet News system as a testbed for the filtering algorithm. In the Usenet system, users throughout the world intermittently post articles to a common bulletin board. The number of articles posted may be very large; e.g., newsgroups may receive hundreds of articles daily. The goal is to predict whether new articles are likely to be of interest, or not of interest, based upon the prior behavior of the user. This is an extremely fuzzy and difficult problem to define because users are notorious for their inconsistency in their behavior patterns and changing interests. One of the difficult constraints imposed by this type of problem is the necessity for incrementality. Many learning algorithms, such as those based on neural networks, require repeated training epochs over a fixed data set. In the Usenet News problem, the data set is constantly changing as incoming messages are posted. To ensure consistency, the method would need to store all messages that were ever posted. When new messages arrive, the system would need to retain the old as well as the new messages. This is clearly undesirable due to the time requirements for training and the space required to store all messages. Many approaches to the information filtering problem bypass this problem by typically forcing the user to explicitly define what should be filtered, e.g. via a keyword-based database language [1].

Software defined multi-spectral imaging for Arctic sensor networks

Availability of off-the-shelf infrared sensors combined with high definition visible cameras has made possible the construction of a Software Defined Multi-Spectral Imager (SDMSI) combining long-wave, near-infrared and visible imaging. The SDMSI requires a real-time embedded processor to fuse images and to create real-time depth maps for opportunistic uplink in sensor networks. Researchers at Embry Riddle Aeronautical University working with University of Alaska Anchorage at the Arctic Domain Awareness Center and the University of Colorado Boulder have built several versions of a low-cost drop-in-place SDMSI to test alternatives for power efficient image fusion. The SDMSI is intended for use in field applications including marine security, search and rescue operations and environmental surveys in the Arctic region. Based on Arctic marine sensor network mission goals, the team has designed the SDMSI to include features to rank images based on saliency and to provide on camera fusion and depth mapping. A major challenge has been the design of the camera computing system to operate within a 10 to 20 Watt power budget. This paper presents a power analysis of three options: 1) multi-core, 2) field programmable gate array with multi-core, and 3) graphics processing units with multi-core. For each test, power consumed for common fusion workloads has been measured at a range of frame rates and resolutions. Detailed analyses from our power efficiency comparison for workloads specific to stereo depth mapping and sensor fusion are summarized. Preliminary mission feasibility results from testing with off-the-shelf long-wave infrared and visible cameras in Alaska and Arizona are also summarized to demonstrate the value of the SDMSI for applications such as ice tracking, ocean color, soil moisture, animal and marine vessel detection and tracking. The goal is to select the most power efficient solution for the SDMSI for use on UAVs (Unoccupied Aerial Vehicles) and other drop-in-place installations in the Arctic. The prototype selected will be field tested in Alaska in the summer of 2016.

Why do people disagree with a statement they do not understand? Relations between comprehension and evaluation of a simple assertion

This article presents the results of a quasi-experimental study that examined the relation between the metacomprehension (i.e., understand/do not understand) and evaluative (i.e., agree/disagree) response to a simple one-sentence statement to compare the relative timing in which these two responses are generated in the course of sentence processing. In the study, participants were asked to provide metacomprehension and evaluative judgements to simple one-sentence assertions, and their response times were measured. Two of the main findings are: first, the response time for the evaluative judgement is faster than the response time for the metacomprehension judgement and, second, the faster response time of the evaluative judgement relative to the metacomprehension judgement is more pronounced either when they are not sure about whether they understand a statement or when they feel they do not understand a statement. The findings are analysed in relation to a multiple constraint satisfaction model of sentence comprehension to generate a possible processing model of a simple one-sentence assertion underlying the generation of metacomprehension and evaluative responses.

Machine-extracted eye gaze features: how well do they correlate to sight-reading abilities of piano players?

Skilled piano players are able to decipher and play a musical piece they had never seen before (a skill known as sight-reading). For a sample of 23 piano players of various abilities we consider the correlation between machine-extracted gaze path features and the overall human rating. We find that correlation values (between machine-extracted gaze features and overall human ratings) are statistically similar to correlation values between human-extracted task-related ratings (e.g., note accuracy, error rate) and overall human ratings. These high correlation values suggest that an eye tracking-enabled computer could help students assess their sight-reading abilities, and could possibly advise students on how to improve. The approach could be extended to any musical instrument. For keyboard players, a MIDI keyboard with the appropriate software to provide information about note accuracy and timing could complement feedback from an eye tracker to enable more detailed analysis and advice.