University of Memphis Digital Commons
Not a member yet
43176 research outputs found
Sort by
“It is important to consult” a linguist: Verb-Argument Constructions in ChatGPT and human experts\u27 medical and financial advice
No full textGraduate Computer Science TA Perspectives on In-Person Pedagogical Training: An Experience Report
No full textfeedback; teaching assistant trainin
“How Am I Supposed to Act?”: Adapting Bronfenbrenner’s Ecological Systems Theory to Understand the Developmental Impacts of Multiple Forms of Violence
No full textecological systems; multiple forms of violence; neighborhoods; qualitative; yout
The Book of Common Prayer
No full texthttps://digitalcommons.memphis.edu/item-of-the-month-2025-09/1001/thumbnail.jp
Multimodal time-series classification using CNN
No full textOur goal is to develop a uniform, relatively lightweight model that can yield high accuracy on a wide variety of multimodal time-series classification problems. To that end, we propose a model that fuses multiple convolutional neural networks (CNNs), one for each modality, at the decision level using a multilayer perceptron. The model is trained on randomized (as opposed to sequential) signal windows, which enhances generalization across diverse time segments. We evaluate the model on two real-world problems: emotion recognition using physiological signals and action recognition using wearable sensor data. In both cases, our model achieves accuracy comparable to state-of-the-art approaches while being considerably smaller in size. This efficiency makes it well-suited for edge computing scenarios, where memory and compute resources are limited. The modular design also allows for seamless scaling across additional modalities or domains without requiring much architectural changes. Overall, our method provides a practical and adaptable framework for multimodal time-series classification
ENHANCING PUBLIC TRANSIT BY INTEGRATING ON-DEMAND AND FIXED ROUTE TRANSIT SERVICES: A FOCUS ON IMPLEMENTATION, ADAPTION, EQUITY, AND ACCEPTANCE
Get PDFAs cities seek to build inclusive, efficient, and sustainable transportation systems, the integration of on-demand mobility services with traditional fixed-route transit (FRT) offers a promising solution to enhance coverage and connectivity. However, challenges persist in evaluating the cost-effectiveness, accessibility, and user acceptance of such integrated systems. This dissertation presents a comprehensive, three-part framework that addresses these gaps by (1) developing a simulation-based, pre-implementation cost evaluation model, (2) assessing the accessibility and equity outcomes of integrated systems, and (3) exploring the effectiveness of behavioral nudges in influencing transit adoption. The first study introduces an agent-based simulation model to evaluate generalized system costs comprising user, agency, and external costs across fourteen multimodal integration scenarios combining FRT, Demand Response Transit (DRT), and Transportation Network Companies (TNC). Applied to synthetic (Sioux Falls) and real-world (Morristown, TN) networks, the model demonstrated that over 70% of trips could be feasibly connected to existing FRT through feeder services. The second study examines spatial equity and accessibility impacts of integrating DRT and TNC services with FRT. This research article introduces the Accessibility-Radius metric and employs the Gini index, Lorenz curve, and Transit Coverage Gap to quantify accessibility improvements. The third study applies behavioral economics and goal-framing theory to evaluate the impact of digital nudging on public transit preference and promoting mode shift from single occupant vehicles to multimodal transit modes. These studies collectively contribute to the understanding of integrated mobility systems, dynamic feeder solutions, and behavioral interventions, with the ultimate goal of fostering sustainable and efficient urban mobility
Central Police Station
No full texthttps://digitalcommons.memphis.edu/picturing-memphis-images/1013/thumbnail.jp
Residence of E.T. Bennett
No full texthttps://digitalcommons.memphis.edu/picturing-memphis-images/1045/thumbnail.jp
Linden Crest – Residence of S.T. Carnes
No full texthttps://digitalcommons.memphis.edu/picturing-memphis-images/1047/thumbnail.jp