Charles C. Tappert

Pace University · Computer Science

The purpose of this research was to determine whether active portions of the brain are influenced by the presence of Virtual Reality (VR) and whether those brain signals have the potential to be used for user authentication. For this study, Electroencephalography (EEG) signals were collected under two conditions: subjects viewed video using a VR he...

Electroencephalography (EEG) brain signals have been utilized in various pattern recognition applications such as biometrics and emotion detection. EEG signals provide the relevant information of individual differences which can be potentially used as salient features for user recognition. The majority of previous studies on the brain signal biomet...

The partially observable hidden Markov model is an extension of the hidden Markov Model in which the hidden state is conditioned on an independent Markov chain. This structure is motivated by the presence of discrete metadata, such as an event type, that may partially reveal the hidden state but itself emanates from a separate process. Such a scena...

The hidden Markov model (HMM) and its extensions have been applied in numerous scientific and engineering areas. In speech recognition, HMMs still outperform many other models. HMMs have also demonstrated significant performance in signature and gesture recognition. Nonetheless, the performance of HMM in Keystroke Biometric (KB) systems is typicall...

This paper develops algorithms and investigates various classifiers to determine the authenticity of short social network postings, an average of 20.6 words, from Facebook. This paper presents and discusses several experiments using a variety of classifiers. The goal of this research is to determine the degree to which such postings can be authenti...

This work introduces the partially observable hidden Markov model (POHMM), a generalization of the hidden Markov model (HMM) in which the underlying system state is partially observable through event metadata at each time step. Whereas in a HMM, the hidden state is inferred through the observed values, the hidden state in a POHMM is inferred throug...

There are numerous opportunities for adversaries to observe user behavior remotely on the web. Additionally, keystroke biometric algorithms have advanced to the point where user identification and soft biometric trait recognition rates are commercially viable. This presents a privacy concern because masking spatial information, such as IP address,...

Keystroke biometrics (KB) authentication systems are a less popular form of access control, although they are gaining popularity. In recent years, keystroke biometric authentication has been an active area of research due to its low cost and ease of integration with existing security systems. Various researchers have used different methods and algo...

This work provides strong empirical evidence for a two state generative model of typing behavior in which the user can be in either a passive or active state. Given key-press latencies with missing key names, the model is then used to spoof the key-press latencies of a user by exploiting the scaling behavior between inter-key distance and key-press...

Keystroke dynamics authentication is not as widely used compared to other biometric systems. In recent years, keystroke dynamic authentication systems have gained interest because of low cost and integration with existing security systems. Many different methods have been proposed for data collection, feature representation, classification, and per...

This work presents the results of the One-handed Keystroke Biometric Identification Competition (OhKBIC), an official competition of the 8th IAPR International Conference on Biometrics (ICB). A unique keystroke biometric dataset has been collected by the authors, that includes freely-typed long-text samples from 64 subjects. Samples were collected...

This article presents a standardized and repeatable process used to evaluate the performance of a speaker verification system. Through the use of a common passphrase and a subset of extracted feature vectors that outperforms other combinations, the study limits the exposure to potential experimental flaws, while measuring true biometric performance...

This paper presents and discusses several experiments in authorship authentication of short social network postings, an average of 20.6 words, from Facebook. The goal of this research is to determine the degree to which such postings can be authenticated as coming from the purported user and not from an intruder. Various sets of stylometry and ad h...

This study investigated methods of enhancing human computer interaction in applications of pattern recognition where higher accuracy is required than is currently achievable by automated systems, but where there is enough time for a limited amount of human interaction. On a flower identification task, methods were explored to improve the accuracy o...

Many applications need methods for handling missing or insufficient data. This paper applies a correlation technique to improve the fallback methods previously used to handle the paucity of keystroke data from the infrequently used keys in a keystroke biometric system. The proposed statistical fallback model uses a correlation based fallback table...

Keystroke and stylometry behavioral biometrics were investigated with the objective of developing a robust system to authenticate students taking online examinations. This work responds to the 2008 U.S. Higher Education Opportunity Act that requires institutions of higher learning undertake greater access control efforts, by adopting identification...

This study focuses on the development and evaluation of a new classification algorithm that halves the previously reported best error rate. Using keystroke data from 119 users, closed system performance was obtained as a function of the number of keystrokes per sample. The applications of interest are authenticating online student test takers and c...

The keystroke biometric classification system described in this study was evaluated on two types of short input - passwords and numeric keypad input. On the password input, the system outperforms 14 other systems evaluated in a previous study using the same raw input data. The three top performing systems in that study had equal error rates between...

Performance of supervised training of Artificial Neural Networks (ANNs) depends on several factors, including neural network architecture, number of neurons in hidden layers, the neurons' activation functions, and selection of initial network parameters (connection weights). Trial and error is commonly used to select the network parameters and the...

The purpose of this research is to identify and implement mouse features, which can be used as part of a user biometric authentication system. This paper explores mouse features that can be obtained from different user actions in a computer, expanding the context from earlier works on Mouse Biometric that focused on fixed patterns. The mouse featur...

A novel keystroke biometric system for long-text input was developed and evaluated for user identification and authentication applications. The system consists of a Java applet to collect raw keystroke data over the Internet, a feature extractor, and pattern classifiers to make identification or authentication decisions. Experiments on more than 10...

Data windows of keyboard input are analyzed to continually authenticate computer users and verify that they are the authorized ones. Because the focus is on fast intruder detection, the authentication process operates on short bursts of roughly a minute of keystroke input, while the training process can be extensive and use hours of input. The biom...

This study focuses on intruder detection. Short bursts of keyboard input are analyzed to continually authenticate computer users and verify that they are the authorized ones. The biometric system consists of components for data capture, feature extraction, authentication classification, and ROC curve generation. Experiments were performed on three...

A recognize-then-segment recognizer of unconstrained handprinting uses a unified tablet-display to provide a paper-like computer interface. Whereas most handwriting recognition systems segment and then recognize, this one recognizes and then finds the best segmentation. It classifies strokes, generates character hypotheses, and verifies hypotheses...

The 2008 federal Higher Education Opportunity Act requires institutions of higher learning to make greater access control efforts for the purposes of assuring that students of record are those actually accessing the systems and taking exams in online courses by adopting identification technologies as they become more ubiquitous. To meet these needs...

Looking back on the first decade of the Doctor of Professional Studies in Computing---an ambitious doctoral track for people who want to do research in an industrial setting.

For the past ten years at Pace University we have been using real-world student projects in capstone computing courses. These courses have been essentially online for the last five years. Appropriate team management changes facilitated the transition from co-located to distributed teams, and peer evaluations and other remote assessment techniques m...

A Keystroke Biometric System measures the typing characteristics believed to be unique to an individual and difficult to duplicate. A Stylometry Biometric System measures the frequency of text file features such as: number of alphabetic characters/total number of characters, number of uppercase characters/number of alphabetic characters, etc. We ca...

Our mission of capstone computing courses for the past ten years has been to offer students experience with the development of real-world information technology projects. This experience has included both the hard and soft skills required for the work they could expect as industrial practitioners. Hard skills entail extending one's knowledge struct...

At Pace University we have been using real-world student projects in capstone computing courses for about 10 years. While the courses were conducted in a traditional classroom environment during the early years, the current course has been essentially online for the last five years in order to reach a greater number of geographically scattered stud...

Over the last six years Pace University has been developing a long-text-input keystroke biométrie system. The system consists of three components: a java applet that collects raw keystroke data over the Internet, a feature extractor, and a pattern classifier. This paper presents two significant system improvements. The first achieves high performan...

Deep Venous Thrombosis (DVT) is an intrinsic disease where blood clots form in a deep vein in the body. Since DVT has a high mortality rate, predicting it early is important. Decision trees are simple and practical prediction models but often suffer from excessive complexity and can even be incomprehensible. Here a genetic algorithm is used to cons...

Deep Venous Thrombosis (DVT) is an intrinsic disease where blood clots form in a deep vein in the body. Since DVT has a high mortality rate, predicting it early is important. Decision trees are simple and practical prediction models but often suffer from excessive complexity and can even be incomprehensible. Here a genetic algorithm is used to cons...

A novel keystroke biometric system for long-text input was developed and evaluated for user identification and authentication applications. The system consists of a Java applet to collect raw keystroke data over the Internet, a feature extractor, and pattern classifiers to make identification or authentication decisions. Experiments on over 100 par...

Over the last 10 years, the Internet has been the place of tremendous information security issues and vulnerabilities; in particular, the ability to patch systems very quickly has become a necessary requirement in order to provide a safe operating environment for all organizations. At the same time, the fast proliferation of systems and their respe...

The binary feature vector is one of the most common representations of patterns and measuring similarity and distance measures play a critical role in many problems such as clustering, classification, etc. Ever since Jaccard proposed a similarity measure to classify ecological species in 1901, numerous binary similarity and distance measures have b...

There are issues in assessing the contributions of individual students on geographically distributed student teams working on information technology projects. At Pace University we have been using real-world student projects in capstone computing courses for about ten years. While the courses were conducted in a classroom environment during the ear...

Tree-based classifiers are important in pattern recognition and have been well studied. Although the problem of finding an optimal decision tree has received attention, it is a hard optimization problem. Here we propose utilizing a genetic algorithm to improve on the finding of compact, near-optimal decision trees. We present a method to encode and...

A keystroke biometric system for long-text input was developed and evaluated for identification and authentication applications. The system consists of a Java applet to collect raw keystroke data over the Internet, a feature extractor, and pattern classifiers to make identification or authentication decisions. Experiments on over 100 subjects inves...

This paper presents a method of creating Receiver Operating Characteristic (ROC) curves from the non- parametric, k-nearest-neighbor classification procedure and illustrates the method on keystroke biometric authentication data. The long-text-input keystroke biometric system developed at Pace University has the ability to identify with a high degre...

The binary feature vector is one of the most common representations of patterns and measuring similarity and distance measures play an important role in many statistical problems such as clustering, classification, etc. Numerous binary similarity and distance measures have been proposed in various fields. Some measures have been identified as the s...

In work directed toward Automatic Recognition of Continuous Speech (ARCS), there are several approaches which may be taken. The selection among these depends heavily on the purposes and, to some extent, the inclinations of the experimentalist/developer.

Decision trees have been well studied and widely used in knowledge discovery and decision support systems. Although the problem of finding an optimal decision tree has received attention, it is a hard optimization problem. Here we propose utilizing a genetic algorithm to improve on the finding of ap-propriate decision trees. We present a method to...

Accurate object identification and classification remains a hard problem in the field of computer vision. Many different approaches to the problem have been and continue to be explored. This paper presents a preliminary investigation into the applicability of using semantic (i.e. human recognizable) features of an object for both identification and...

This chapter discusses English language handwritings recognition interfaces as a method of entering text into a computer. It reveals that handwriting has been an excellent means of communication and documentation for thousands of years. Handwriting is a learned skill, but because it has a long history and is learned in early school years, many cons...

The development of pen-centric chatroom shorthand handwriting recognition interfaces can provide the critical infrastructure for natural pen-centric interactions and enhance many pen-centric learning applications.

A long-text-input keystroke biometric system was developed for applications such as identifying perpetrators of inappropriate e-mail or fraudulent Internet activity. A Java applet collected raw keystroke data over the Internet, appropriate long-text-input features were extracted, and a pattern classifier made identification decisions. Experiments w...

While most previous keystroke biometric studies dealt with short input like passwords, we focused on long-text input for applications such as identifying perpetrators of inappropriate e-mail or fraudulent Internet activity. A Java applet collected raw keystroke data over the Internet, appropriate long-text-input features were extracted, and a patte...

Similarity and dissimilarity measures play an important role in pattern classification and clustering. For a century, researchers have searched for a good measure. Here, we review, categorize, and evaluate various binary vector similarity/dissimilarity measures. One of the most contentious disputes in the similarity measure selection problem is whe...

This paper concerns the generalizability of biometric identification results from small-sized closed systems to larger open systems. Many re- searchers have claimed high identification accuracies on closed system consist- ing of a few hundred or thousand members. Here, we consider what happens to these closed identification systems as they are open...

The distinctive aspect of the CAVIAR technology is a visible, parameterized geometrical model that serves as the human-computer communication channel. Evaluation of CAVIAR flower and face recognition systems shows that their accuracy is much higher than that of the machine alone; their recognition time is much lower than that of the human alone; th...

Handwriting originates from a particular copybook style such as Palmer or Zaner-Bloser that one learns in childhood. Since questioned document examination plays an important investigative and forensic role in many types of crime, it is important to develop a system that helps objectively identify a questioned document"s handwriting style. Here, we...

For describing and analyzing digital images of paintings we propose a model to serve as the basis for an interactive image retrieval system. The model defines two types of features: palette and canvas features. Palette features are those related to the set of colors in a painting while canvas features relate to the frequency and spatial distributio...

Handwriting originates from a particular copybook style such as Palmer or Zaner-Bloser that one learns in childhood. Since questioned document examination plays an important investigative and forensic role in many types of crime, it is important to develop a system that helps objectively identify a questioned document's handwriting style. We propos...

Similarity and dissimilarity measures play an important role in pattern classification and clustering. For a century, researchers have searched for a good measure. Here, we review, categorize, and evaluate various binary vector similarity/dissimilarity measures for character recognition. One of the most contentious disputes in the similarity measur...

This paper concerns the generalizability of biometric iden- tification in open systems. Many researchers have claimed high identification accuracies on closed system consisting of a few hundred or thousand members. Here, we consider what happens to these closed identification systems as they are opened to non-members. We claim that these systems do...

We consider quantitatively establishing the discriminative power of iris biometric data. It is difficult, however, to establish that any biometric modality is capable of distinguishing every person because the classification task has an extremely large and unspecified number of classes. Here, we propose a methodology to establish a measure of discr...