Digital Commons Network^™

The Application Of Machine Learning And Deep Learning On Demand Forecasting Across Time-Critical Industries: A Systematic Review, Asmaa Seyam, Sujith Samuel Mathew, May El Barachi, Cheng Zhang, Jun Shen

All Works

The applications of machine learning and deep learning in demand forecasting have attracted increasing attention, as they offer remarkable predictive capabilities that help automate forecasting processes and achieve higher accuracy. While numerous review studies have examined solutions within specific industries, there is a lack of comprehensive literature review investigating these solutions across different sectors. Therefore, this study overviews machine learning and deep learning applications in demand forecasting across time-critical industries, including power, tourism, water, transportation, and food. A two-tier classification framework is proposed to categorize demand forecasting studies by both application industry and methodological architecture. In addition, the most popular …

Ecu-Malnett V2, Matthew G. Gaber, Mohiuddin Ahmed, Michael N. Johnstone

Research Datasets

ECU-MALNETT (ECU MALware NETwork Traffic) is a real world, reproducible dataset of labeled benign and malicious network flows built from the Peekaboo execution corpus. Peekaboo runs evasive malware with dynamic binary instrumentation and records raw host-level PCAPs while granting full Internet access, yielding noisy, real-world captures with background OS activity and concurrent processes. To derive trustworthy labels from these traces, we apply Construct, a baseline aware, zero-trust labeling framework. Construct first ingests a baseline capture to establish reference sets (DNS qnames, HTTP hosts, TLS SNIs, and socket endpoints) and grows a conservative benign IP pool only via whitelisted DNS resolutions. …

Uncovering Customer Sentiment And Brand Perception By Leveraging Large Language Models: A Case Study In The Automotive Industry, Sujith Samuel Mathew, Kadhim Hayawi, Faseela Abdullakutty, Neethu Venugopal, May El Barachi

All Works

Analyzing customer perceptions has become increasingly important in the automotive industry as it provides actionable insights into consumer satisfaction, preferences, and areas requiring improvement. This study proposes a novel perception analysis framework for automotive reviews using advanced Large Language Models (LLMs), including BERT, FLAN-XXL, and Mistral 7B, leveraging zero-shot learning to categorize reviews without task-specific training data. The framework follows a two-stage evaluation process, beginning with zero-shot perception classification and followed by a detailed topic-wise perception analysis. Model performance was evaluated using accuracy, precision, recall, and F1-score across reviews from five major automotive brands—Toyota, Kia, Honda, Nissan, and Hyundai. While …

Deployment-Oriented Evaluation Of Temporal And Spatial Forecasting Approaches For Electric Vehicle Charging Demand In Energy Systems, Maher Alaraj, Eyob Solomon Getachew

All Works

Accurate short-term electric vehicle (EV) charging demand forecasting is important for charging infrastructure operation, grid management, and energy-system planning. This study presents a deployment-oriented and reproducible evaluation of temporal, spatial, and unified spatio-temporal forecasting approaches for day-ahead EV charging demand prediction. Using publicly available charging-session data aggregated at hourly resolution across ZIP-code regions, we compare persistence and ARIMA baselines, XGBoost, Long Short-Term Memory (LSTM) networks, Graph Convolutional Networks (GCNs), and a unified GCN+LSTM architecture under a consistent preprocessing pipeline, leakage-free validation protocol, and rolling-origin evaluation framework. For the Boulder ZIP-code dataset considered in this study, temporal information provided the dominant …

Toward Equitable Energy Futures: The Influence Of Digital Government And Financial Development On Clean Energy Justice, Martin Spraggon, Muhammad Hafeez, Sana Ullah, Chanyanan Somthawinpongsai, Zurul Aisya Osman, Sidra Sohail

All Works

Fossil fuel energy is the largest source of carbon emissions and the main driver of climate change and global warming. Therefore, the world is switching towards clean and green energy sources as an alternative to fossil fuel-based energy sources. Nevertheless, the equitable distribution of clean energy resources in urban and rural areas among every segment of society has become a concern for policymakers. Thus, urban-rural clean energy justice is an investigation topic that needs our attention. In this analysis, our main focus is on investigating the influence of financial development and digital government on clean energy justice using an advanced …

Dustmambanet: A Hybrid Inceptionv3–State-Space Network For Robust Solar Panel Dust Detection, Kadhim Hayawi, Sakib Shahriar

All Works

To develop a robust, scalable vision-based model for automatic detection and quantification of dust accumulation on solar photovoltaic panels, overcoming limitations of existing convolutional and attention-based methods and supporting proactive maintenance. We propose DustMambaNet, a hybrid model that consists of a pretrained InceptionV3 convolutional neural network as a feature extractor and two selective state space sequence modules. The state space modules use gated depthwise convolutions to represent long-range spatial dependencies that are of linear complexity, after rearranging spatial features to form sequences. The network provides a binary classification of dust with a severity index (DSI) and a continuous one. All …

Badlands Bombing Range 2024-2025 Surveys, Amanda E. Cheeseman

NRM Departmental Data Sets

This dataset contains terrestrial small mammal survey data collected at the Badlands Bombing Range, South Dakota, during summer 2024 and 2025. Surveys were conducted across mixed-grass prairie, sandy tableland, prairie dog colonies, and White River floodplain habitats using Sherman live traps, pitfall traps, and remotely triggered cameras. Data include trapping effort, species detections and captures, capture locations and associated capture data, and camera detections and were collected to document mammal diversity, evaluate habitat use, and support natural-resource management of the installation.

File type: csv
File size: 132 KB

Tolkien Fanzine Dataset, 1967-2017 [Bulk 1969-1979], Robinson Ensz, Gabriel Marotto, Aidan Oakey, Ivy Stanich, Ethan Thomas

Tolkien Resources

This dataset reveals the heretofore hidden contents of fan magazines (fanzines) related to the works of J.R.R. Tolkien that were created from 1969 through the publication of Tolkien’s The Silmarillion in 1977. It supplements the earlier Tolkien Fandom Review by S. Gary Hunnewell that discussed fanzines created through 1968. The dataset provides an item level index of the fanzines’ content and is intended to aid researchers in Fan Studies. It is accompanied by an inventory document that lists the fanzine titles and provides brief notes about some of them. Data was drawn from Marquette’s large holding of Tolkien fanzines, including …

The Impact Of Partner Support On Vaginismus Treatment Outcomes: A Mixed Methods Study, Anna R. Ames, Alisha H. Redelfs, Nana Mensah

ScholarsArchive Data

A mixed-methods design was used to gain a nuanced understanding of how partner support affects the experiences of people with vaginismus.

Study aim: To guide partners of people with vaginismus in understanding how they can best help their partners with their vaginismus experience. 

• Quantitative Data: cross-sectional survey to reveal correlations in the relationship between vaginismus treatment outcomes and partner support [Available]
• Qualitative Data: Individual interviews to explore specific ways that people with vaginismus receive, or want to receive, support from their partners and the significance that they place on partner support  [Not Available]

Survey Data
Survey participants were recruited in …

Dataset For Effects Of Demineralization Protocols On Hydrogen And Oxygen Isotope Ratios In Fossil Bone Collagen, Linda M. Reynard

Geosciences Research Data

This dataset accompanies a peer-reviewed publication. The effect of three commonly used preparation protocols on bone collagen d2H and d18O values was investigated, using six generally well-preserved faunal bones (cattle, bison, horse) ranging in age from the Holocene to Late Pleistocene. The treatments tested were ethylene diamine tetraacetic acid demineralization without gelatinization and hydrochloric acid demineralization with and without gelatinization. There were small d2H changes noted by method; however, given the expected water isotopic variation among labs this should be an insignificant source of inter-lab variation.

Data For Effect Of Simple Motor Repetition On Inverted Pendulum Control: Exploring Age-Related Variations, Kimia Kiani, Qiushi Fu

Research Data and Datasets

This dataset contains data from a human motor-control experiment investigating how prior motor repetition influences subsequent control and learning of a virtual inverted-pendulum task in young and older adults. Participants performed the inverted-pendulum task using a robotic interface and completed either force-based or movement-based repetition training between task blocks. The dataset includes measures of pendulum control performance, task progression, training condition, hand, and age group. These data support the study “Effect of Simple Motor Repetition on Inverted Pendulum Control: Exploring Age-Related Variations.”

Replication Stata File For The Article "Charlie Kirk's Assassination And Cross-Partisan Dialogue", Andrew Scott Bledsoe, Susan Turner Haynes

Faculty Works

No abstract provided.

Droplet Clustering Signatures Of Entrainment In Clouds, Suryadev Pratap Singh, Michael Larsen, Jesse Anderson, Hamed F. Sadi, Jae Min Yeom, Will Cantrell, Raymond A. Shaw

Michigan Tech Research Data

The spatial distribution of cloud droplets is relevant for various microphysical processes, such as condensational growth, collision-coalescence, riming and aggregation, and radiative transfer. Cloud droplets and other hydrometeors exhibit clustering at dissipation scales and above due to turbulence-induced preferential concentration. Here, we investigate the role of entrainment in modulating the scale-dependent clustering of cloud droplets and explore how this mechanism differs from inertial clustering. We have performed experiments in the Pi Convection-Cloud Chamber, and imaged 2-D droplet fields in the cloud-top region where dry-air entrained through an open cylindrical flange leads to an entrainment-mixing process. Captured images are processed to …

Theological Truths That Divide Us And Engaging In Disagreement Well, David M. Westfall

Faculty Work Comprehensive List

""Only when we locate our differences within the shared context of God’s will to unite all things in his Son can we “get with the program” and start to relate in love, allowing our objective identity in him to exert continual pressure on our relationship.""

Posting about ­­­­­­­­how pursuing unity is part of Christian transformation from In All Things, an online hub that offers insight into maintaining and faithful and orthodox Reformed Christian worldview while fearlessly engaging in every aspect of contemporary life – until all is made new.

Dataset For 'Variability Of Howitzer Artillery Infrasound Recorded In Little Cottonwood Canyon, Utah', Owen A. Walsh, Jeffrey B. Johnson

Boise State University Infrasound Data Repository

These data are a supplement to the MS thesis, “Variability of Howitzer Artillery Infrasound Recorded in Little Cottonwood Canyon, Utah”, by Department of Geosciences student, Owen Walsh. Data provided are for howitzer artillery infrasound signals recorded by six infrasound microphones (infraBSU v2) from March 22 through April 5, 2023 in Little Cottonwood Canyon, Utah, USA. This dataset consists of 142, 20-second signals sampled at 100 Hz. Data provided have been filtered using a 0.5 Hz (2-second) highpass, acausal, 2-pole butterworth filter.

Custom Hydroponic Lid Design, Noah Langenfeld

Browse all Datasets

This data set contains files necessary to recreate a custom hydroponic lid for a two-gallon bucket. Additional component descriptions are available online at cea.usu.edu.

Ground To Roof Snow Load Ratio (Gr) Data Release, Brennan Bean, Cooper Nelson, Jesse Wheeler, Scout Jarman, Salam Adil Al-Rubaye, Marc Maguire

Browse all Datasets

This data release provides historical ground-to-roof snow load ratio (GR) datasets used for snow load research and model development. The release includes original referenced datasets, cleaned country specific datasets, and a master dataset that combines Canadian and United States datasets into a standardized format for research and engineering applications.

Data Repository For "The Influence Of Hydrologic And Salinity Conditions On Drought-Tolerant Great Salt Lake Wetland Plant Species" By Samantha Kurkowski And Karin Kettenring, Samantha Kurkowski

Browse all Datasets

This greenhouse experiment investigated the effects of salinity (3 levels) and hydrologic condition (5 levels),  on the cover and biomass of a single mix of 11 native drought- and salt-tolerant species.

Aqqd: Annotated Quranic Qira’At Dataset, Linda Smail, Mohammed Lataifeh, Md Sohazur Islam Sozib, Arthur Diniz De Souza

All Works

AQQD (Annotated Quranic Qira'at Dataset) is an open audio dataset of Quranic recitations annotated across canonical Qira'at styles. The dataset is designed to support research in machine learning, speech and audio processing, computational linguistics, and Quranic studies. The current release contains 24,183 WAV audio files from 309 reciters and covers 70 selected Quranic Surahs segmented into representative verses and phonetic variation points. Of these, 23,111 recordings were collected from publicly available sources, including official reciter websites, the Midad repository, MP3Quran, and verified YouTube channels, while an additional controlled subset of 1,072 recordings was obtained from a single reciter recorded as …

Impacts Of Structural Design On Oyster Survival And Predation In Restored Oyster Reefs, Jaden E. Akers, Nigel Temple, J. Marcus Drymon, Just Cebrian, J. Patrick Broussard, Ashleigh Robbins, Eric Sparks

Research Data

Restoration efforts are critical to ensure healthy oyster populations and the ecosystem services they provide. However, restoration is expensive and outcomes are mixed due, in part, to oyster predation on contemporary structures. Here we assess the effects of reef structural design elements on predator behavior and oyster survival using a paired field and laboratory mesocosm experimental approach. Experimental reefs (n=128) were constructed out of formed concrete and varied in structural features including vertical relief (short vs. tall), continuity (e.g., gapped or continuous), position in the water column (on-bottom or elevated), and slope. Each of the 8 designs was replicated eight …

Melatonin-Functionalized Silver Nanoparticles Enhance Salinity Tolerance In Brassica Juncea By Modulating Antioxidant Defence And Growth Physiology, Mohini Yadav, Manar Fawzi Bani Mfarrej, Vikash Kumar, Ankita Singh, Faheem Ahmad, Saurabh C. Saxena

All Works

Soil salinity is a major abiotic stress that severely limits plant growth and productivity by inducing osmotic stress, oxidative damage, and ionic imbalances. The present study evaluated the potential of melatonin-mediated silver nanoparticles (Mel AgNPs) to enhance salinity stress tolerance in Brassica juncea. Pot experiments were conducted using 21-day-old plants exposed to salinity stress and treated with Mel AgNPs at different concentrations (50 and 100 mg L⁻¹) through both root application and foliar spray. Morphological, physiological, and biochemical responses were assessed 48 h after nanoparticle exposure. Salinity stress markedly increased lipid peroxidation and hydrogen peroxide accumulation while suppressing antioxidant defence. …

Novel Ultrasonic Shearing For Monodisperse And Size-Controllable Nanobubble Manufacturing In Therapeutic Delivery Systems, Margaret G. Nanfria, Pedram Sotoudehbagha, Elayaraja Kolanthai, Abhijith Rangavajjula, Sun Latt, Andres Alayon Mata, Sudipta Seal, Melanie Coathup, Mehdi Razavi

Research Data and Datasets

This dataset corresponds to the original data for the manuscript titled Nanobubbles for Novel Ultrasonic Shearing for Monodisperse and Size-Controllable Nanobubble Manufacturing in Therapeutic Delivery Systems.

Students’ Perceptions At The University Of Puerto Rico Secondary School Regarding Cellphone Use In The School Environmen, Nicolás Ramos, Nydiaam Vilanova

IALS Journal

This mixed-methods study investigates students’ perceptions of cellphone use at the University of Puerto Rico Secondary School. Data were collected from 133 students through a structured electronic survey examining phone ownership, usage patterns, emotional responses, parental regulation, and opinions regarding cellphone restrictions in schools. Results indicate that most students perceive their cellphone use as appropriate, recognize both educational and social benefits, and oppose complete bans while supporting responsible use and guided autonomy. The findings suggest that schools should emphasize digital citizenship, self-regulation, and balanced technology use rather than punitive restrictions.

Infant Hippocampal And Amygdala Volume In An Observational Follow-Up From A Randomized Clinical Trial For Maternal Prenatal Depression, Catherine H. Demers, Benjamin L. Hankin, Lillybelle K. Deer, Robert J. Gallop, Mercedes Hoeflich Haase, M. Camille Hoffman, Martin A. Styner, Nancy K. Grote, Elysia Poggi Davis

Psychology: Data Sets

Prenatal maternal depression may have intergenerational effects on offspring brain development, with potential socioemotional consequences. In an observational follow-up of a randomized clinical trial of a prenatal depression intervention (the CARE Project; ClinicalTrials.gov NCT03011801), brain development and subsequent negative emotionality were examined among 109 infants born to mothers randomized during pregnancy to brief interpersonal psychotherapy or enhanced usual care. These data include MRI-derived hippocampal and amygdala volumes at approximately 6 weeks of age and a laboratory-based assessment of infant negative emotionality at 6 months.

Resulting Publication: Infant hippocampal and amygdala volume in an observational follow-up from a randomized clinical trial …

Data Linking And Reproducibility Are Underrepresented In Undergraduate Social-Ecological Data Science Training, Carolyn Koehn, Kelly Hopping, Trevor Caughlin, Rebecca Som Castellano, Jodi Brandt

Human Environment Systems Datasets

Environmental research is essential for solving humanity’s sustainability challenges. The era of open data has arrived, with public environmental data proliferating year after year, but the era of open data use has not. Students often lack training to harness ecological and social data, an issue exacerbated by both rising education costs and increasing time pressures on faculty that limit their ability to develop new curricula. Open educational resources for environmental data science can address these challenges. However, it is unclear which data skills are included in existing published teaching materials and whether they adequately prepare students for real-world applications. To …

"Unmuted America": Oer Assignment And Syllabi For Law/Pol 313 Racial Politics, Camara Silver

Open Educational Resources

Professor Camara Silver created an open syllabus for LAW/POL 313 Racial Politics that includes Unmuted America: Power at Full Volume, a modular political science assignment series. The syllabus and assignment were created as part of an OER course conversion initiative during Spring 2026. The series asks students to examine how power is organized, narrated, defended, and challenged in American public life. Each version uses a two-part structure: “Volume Up,” in which students examine the historical roots, institutional foundations, and present-day structure of a major political issue, and “Volume Down,” in which students analyze a specific case study, source base, …

Polymer Precipitation Influences Membrane Mechanical Properties Of Small Extracellular Vesicles (Sevs), Bianca Mercado Velez, Eduardo Barbieri, Taravat Sarvari, Erico Freitas, Paul Goetsch, Caryn Heldt

Michigan Tech Research Data

Small extracellular vesicles (sEVs) are promising biomarkers and therapeutic delivery vehicles for disease diagnosis and treatment. However, standardizing isolation and characterization techniques is essential, as different isolation methods can alter the biophysical properties of the sEVs. In this study, we compared the physicochemical properties of HEK-293-derived sEVs isolated by polymer precipitation (PP) and sucrose cushion ultracentrifugation (UC). Using atomic force microscopy (AFM) and chemical force microscopy (CFM), we measured the morphology, adhesion, Young’s modulus, and lipid membrane tethering events to understand how the choice of isolation method influences the sEV properties. AFM topographic images revealed the presence of polymeric residues …

Climate-Responsive Design For Sustainable Construction: Passive Strategies In Domestic Architecture Supporting Sustainability, Nahed Chakouf

All Works

This study explores climate-responsive design in domestic architecture, focusing on the application and effectiveness of passive strategies across various climatic regions, including the UK, hot-arid, tropical, and cold climates. A qualitative comparative case study method was used to explore different passive design strategies, integration of sustainability, procurement, the coordination of stakeholders, and compliance with regulations in residential architectural projects under varying climate conditions. Drawing from a combination of historical case studies and original architectural projects, the research evaluates how spatial configuration, material selection, solar orientation, shading, ventilation, and insulation are optimized to achieve thermal comfort and energy efficiency. In temperate …

P-Value Visualizer, Manish Rami

Software

An interactive tool demonstrating what a user set p-value indicates with regards to probability.

Effect Size & Distributional Overlap Visualizer, Manish Rami

Software

An interactive tool comparing a control group and a treatment group, both with standard scores (M = 100, SD = 15). Cohen's d is expressed in standard deviation units. The three shaded regions show what each group's distribution looks like and how much they overlap. You can either use the preset buttons for effect sizes (SLP benchmarks) or the slider to change the values of Cohen's d to examine the distributions.