Florida Polytechnic University

About: Florida Polytechnic University is a education organization based out in Lakeland, Florida, United States. It is known for research contribution in the topics: Computer science & Catalysis. The organization has 302 authors who have published 538 publications receiving 6549 citations. The organization is also known as: Florida Poly.

Distribution-Based Dimensionality Reduction Applied to Articulated Motion Recognition

Abstract: Some articulated motion representations rely on frame-wise abstractions of the statistical distribution of low-level features such as orientation, color, or relational distributions. As configuration among parts changes with articulated motion, the distribution changes, tracing a trajectory in the latent space of distributions, which we call the configuration space. These trajectories can then be used for recognition using standard techniques such as dynamic time warping. The core theory in this paper concerns embedding the frame-wise distributions, which can be looked upon as probability functions, into a low-dimensional space so that we can estimate various meaningful probabilistic distances such as the Chernoff, Bhattacharya, Matusita, Kullback-Leibler (KL) or symmetric-KL distances based on dot products between points in this space. Apart from computational advantages, this representation also affords speed-normalized matching of motion signatures. Speed normalized representations can be formed by interpolating the configuration trajectories along their arc lengths, without using any knowledge of the temporal scale variations between the sequences. We experiment with five different probabilistic distance measures and show the usefulness of the representation in three different contexts - sign recognition (with large number of possible classes), gesture recognition (with person variations), and classification of human-human interaction sequences (with segmentation problems). We find the importance of using the right distance measure for each situation. The low-dimensional embedding makes matching two to three times faster, while achieving recognition accuracies that are close to those obtained without using a low-dimensional embedding. We also empirically establish the robustness of the representation with respect to low-level parameters, embedding parameters, and temporal-scale parameters.

Elder self-neglect: a discussion of a social typology.

Abstract: This article presents a theoretical framework for the study of social and behavioral factors associated with elder self-neglect. The model presented reflects the authors' beliefs that a risk-vulnerability model offers a useful framework from which to study all forms of elder mistreatment, as well as elder self-neglect. This model has particular utility, because it can begin to define the elements of risk and vulnerability that may be addressed using preventative measures as opposed to solely addressing intervention, which is often the case when addressing elder mistreatment and self-neglect. The authors then address a method for using the Consortium for Research in Elder Self-neglect of Texas data as currently constructed and adding to that database to effectively study risks and vulnerabilities in the elder self-neglect population. These additional data would greatly expand the scope of the study. The discussant adds his perspective to the ideas proposed by the authors.

Finding recurrent patterns from continuous sign language sentences for automated extraction of signs

Abstract: We present a probabilistic framework to automatically learn models of recurring signs from multiple sign language video sequences containing the vocabulary of interest. We extract the parts of the signs that are present in most occurrences of the sign in context and are robust to the variations produced by adjacent signs. Each sentence video is first transformed into a multidimensional time series representation, capturing the motion and shape aspects of the sign. Skin color blobs are extracted from frames of color video sequences, and a probabilistic relational distribution is formed for each frame using the contour and edge pixels from the skin blobs. Each sentence is represented as a trajectory in a low dimensional space called the space of relational distributions. Given these time series trajectories, we extract signemes from multiple sentences concurrently using iterated conditional modes (ICM). We show results by learning single signs from a collection of sentences with one common pervading sign, multiple signs from a collection of sentences with more than one common sign, and single signs from a mixed collection of sentences. The extracted signemes demonstrate that our approach is robust to some extent to the variations produced within a sign due to different contexts. We also show results whereby these learned sign models are used for spotting signs in test sequences.

Illustrating a hierarchical approach for selecting personality traits in personnel decisions: an application of the 3m model

Abstract: Recent research indicates that managers are not aware of the latest developments in theory regarding the use of personality inventories in personnel selection decisions. This article presents a systematic approach to selecting traits for use in personnel selection that is based on recent developments in hierarchical personality models. Results from a study of real estate sales associates indicate that the new approach does have much to offer the area. Results are discussed along with managerial implications.

Bio-inspired graphene-based nano-systems for biomedical applications.

Abstract: The increasing demands of environmentally sustainable, affordable, and scalable materials have inspired researchers to explore greener nanosystems of unique properties which can enhance the performance of existing systems. Such nanosystems, extracted from nature, are state-of-art high-performance nanostructures due to intrinsic hierarchical micro/nanoscale architecture and generous interfacial interactions in natural resources. Among several, bio-inspired nanosystems graphene nanosystems have emerged as an essential nano-platform wherein a highly electroactive, scalable, functional, flexible, and adaptable to a living being is a key factor. Preliminary investigation project bio-inspired graphene nanosystems as a multi-functional nano-platform suitable for electronic devices, energy storage, sensors, and medical sciences application. However, a broad understanding of bio-inspired graphene nanosystems and their projection towards applied application is not well-explored yet. Considering this as a motivation, this mini-review highlights the following; the emergence of bio-inspired graphene nanosystems, over time development to make them more efficient, state-of-art technology, and potential applications, mainly biomedical including biosensors, drug delivery, imaging, and biomedical systems. The outcomes of this review will certainly serve as a guideline to motivate scholars to design and develop novel bio-inspired graphene nanosystems to develop greener, affordable, and scalable next-generation biomedical systems.