David Camacho
YOU?
Author Swipe
View article: LLM one-shot style transfer for Authorship Attribution and Verification
LLM one-shot style transfer for Authorship Attribution and Verification Open
Computational stylometry analyzes writing style through quantitative patterns in text, supporting applications from forensic tasks such as identity linking and plagiarism detection to literary attribution in the humanities. Supervised and …
View article: The Impact of an 8-Week Running Technique Program on Linear and Change-of-Direction Speed in Youth Football—A Pilot Study
The Impact of an 8-Week Running Technique Program on Linear and Change-of-Direction Speed in Youth Football—A Pilot Study Open
In football, linear speed and change-of-direction speed are fundamental skills for performance in the sport. The present study aims to evaluate the effect of an 8-week running technique program on the variables described in young footballe…
View article: Effects of Sport Education Model and a Ludotechnical Model hybridisation programme on motivation and intention to be physically active in Physical Education in Secondary Education
Effects of Sport Education Model and a Ludotechnical Model hybridisation programme on motivation and intention to be physically active in Physical Education in Secondary Education Open
Introduction: the aim of the present study was to analyse the effect of an intervention programme delivered through the hybridisation of the Ludotechnical Model (LTM) and the Sport Education Model (SEM) on the satisfaction of Basic Psychol…
View article: Neuroprotective effects of SIRT1 in human RGCs derived from iPSCs following oxidative stress induction at early and late stages of differentiation
Neuroprotective effects of SIRT1 in human RGCs derived from iPSCs following oxidative stress induction at early and late stages of differentiation Open
These findings support the therapeutic success of SIRT1-based gene therapy in an in vitro culture model of human RGCs and confirm those obtained in mouse models of optic neuropathies.
View article: LLM synthetic generation to enhance online content moderation generalization in hate speech scenarios
LLM synthetic generation to enhance online content moderation generalization in hate speech scenarios Open
As social media and digital platforms become more influential, the spread of hate speech has accelerated, inflicting serious harm on individuals, communities, and society as a whole. Addressing this challenge is further complicated by the …
View article: Promoting Family Science Conversations in the LaCuKnoS Project
Promoting Family Science Conversations in the LaCuKnoS Project Open
The Language, Culture, and Knowledge-building through Science (LaCuKnoS) project tests and refines a model of science teaching and learning that brings together current research on the role of language in science communication, the role of…
View article: Pushing the boundary on Natural Language Inference
Pushing the boundary on Natural Language Inference Open
Natural Language Inference (NLI) is a central task in natural language understanding with applications in fact-checking, question answering, and information retrieval. Despite its importance, current NLI systems heavily rely on supervised …
View article: Data-Driven Dynamic Graph Convolution Transformer Network Model for EEG Emotion Recognition Under IoMT Environment
Data-Driven Dynamic Graph Convolution Transformer Network Model for EEG Emotion Recognition Under IoMT Environment Open
With the rapid progress in data-driven approaches, artificial intelligence, and big data analytics technologies, utilizing electroencephalogram (EEG) signals for emotion analysis in the field of the Internet of Medical Things can effective…
View article: Deep Learning Innovations in the Detection of Lung Cancer: Advances, Trends, and Open Challenges
Deep Learning Innovations in the Detection of Lung Cancer: Advances, Trends, and Open Challenges Open
Cancer is the second leading cause of death worldwide, and within this type of disease, lung cancer is the second most diagnosed, but the leading cause of death. Early detection is crucial to increase patient survival rates. One of the pri…
View article: A Robust Framework for Speech Emotion Recognition Using Attention Based Convolutional Peephole LSTM.
A Robust Framework for Speech Emotion Recognition Using Attention Based Convolutional Peephole LSTM. Open
Speech Emotion Recognition (SER) plays an important role in emotional computing which is widely utilized in various applications related to medical, entertainment and so on. The emotional understanding improvises the user machine interacti…
View article: A Slicing Model for Transport Networks with Traffic Burst Control and QoS Compliance for Traffic Flows
A Slicing Model for Transport Networks with Traffic Burst Control and QoS Compliance for Traffic Flows Open
Network slicing has emerged as a key network technology, providing network operators with the means to offer virtual networks to vertical users over a single physical network infrastructure. Recent research has resulted mainly in technique…
View article: On the locality bias and results in the Long Range Arena
On the locality bias and results in the Long Range Arena Open
The Long Range Arena (LRA) benchmark was designed to evaluate the performance of Transformer improvements and alternatives in long-range dependency modeling tasks. The Transformer and its main variants performed poorly on this benchmark, a…
View article: Not all tokens are created equal: Perplexity Attention Weighted Networks for AI generated text detection
Not all tokens are created equal: Perplexity Attention Weighted Networks for AI generated text detection Open
The rapid advancement in large language models (LLMs) has significantly enhanced their ability to generate coherent and contextually relevant text, raising concerns about the misuse of AI-generated content and making it critical to detect …
View article: SIREN: Self-Improving Retrieval-Augmented Deepfake Detection with Explainable LLM Reasoning
SIREN: Self-Improving Retrieval-Augmented Deepfake Detection with Explainable LLM Reasoning Open
View article: A Blockchain-Based Framework for Secure Anomaly Detection and Trust Management in Iov
A Blockchain-Based Framework for Secure Anomaly Detection and Trust Management in Iov Open
View article: Neuroprotective Effects of Sirt1 in Human Rgcs Derived from Ipscs Following Oxidative Stress Induction at Early and Late Stages of Differentiation
Neuroprotective Effects of Sirt1 in Human Rgcs Derived from Ipscs Following Oxidative Stress Induction at Early and Late Stages of Differentiation Open
View article: Adapting Urban Areas to Rising Temperatures: Strategies to Reduce Heat and Vulnerability in a Warming World
Adapting Urban Areas to Rising Temperatures: Strategies to Reduce Heat and Vulnerability in a Warming World Open
View article: Impact of Intrinsic Factors on the Insertion and Permanence of Low-Income Students in Public Universities in 2024
Impact of Intrinsic Factors on the Insertion and Permanence of Low-Income Students in Public Universities in 2024 Open
The development of early childhood is influenced by a multitude of factors, including the psychological resources of caregivers and the socioeconomic conditions of the family environment. The present study sought to examine the correlation…
View article: Performance and Communication Cost of Deep Neural Networks in Federated Learning Environments: An Empirical Study.
Performance and Communication Cost of Deep Neural Networks in Federated Learning Environments: An Empirical Study. Open
Federated learning, a distributive cooperative learning approach, allows clients to train the model locally using their data and share the trained model with a central server. When developing a federated learning environment, a deep/machin…
View article: On the integration of large scale time seriesdistance matrices into deep visual analytic tools
On the integration of large scale time seriesdistance matrices into deep visual analytic tools Open
Time series are essential for modelling a lot of activities such as software behavior, heart beats per time, business processes. The analysis of the series data can prevent errors, boost profits, and improve the understanding of behaviors.…
View article: Advances in AI-Generated Images and Videos.
Advances in AI-Generated Images and Videos. Open
In recent years generative AI models and tools have experienced a significant increase, especially techniques to generate synthetic multimedia content, such as images or videos. These methodologies present a wide range of possibilities; ho…
View article: Isolating authorship from content with semantic embeddings and contrastive learning
Isolating authorship from content with semantic embeddings and contrastive learning Open
Authorship has entangled style and content inside. Authors frequently write about the same topics in the same style, so when different authors write about the exact same topic the easiest way out to distinguish them is by understanding the…
View article: TOVAC: Tele-Operated Vehicle Admission Control and Routing
TOVAC: Tele-Operated Vehicle Admission Control and Routing Open
<p>Tele-operated Driving (ToD) is a challenging use case for mobile network operators. Video captured by the built-in vehicle cameras must be streamed meeting a latency requirement of 5 ms with a 99% reliability. Although 5G offers h…
View article: Generative Design of Periodic Orbits in the Restricted Three-Body Problem
Generative Design of Periodic Orbits in the Restricted Three-Body Problem Open
This paper has been presented in the Thursday 19 September poster session at the SPAICE 2024 conference (17-19 September 2024).
View article: A CLIP-based siamese approach for meme classification
A CLIP-based siamese approach for meme classification Open
Memes are an increasingly prevalent element of online discourse in social networks, especially among young audiences. They carry ideas and messages that range from humorous to hateful, and are widely consumed. Their potentially high impact…
View article: Exploring Scalability in Large-Scale Time Series in DeepVATS framework
Exploring Scalability in Large-Scale Time Series in DeepVATS framework Open
Visual analytics is essential for studying large time series due to its ability to reveal trends, anomalies, and insights. DeepVATS is a tool that merges Deep Learning (Deep) with Visual Analytics (VA) for the analysis of large time series…
View article: Undertaking Undergraduate Research in Mechanical Engineering as a Nontraditional Student: A Personal Perspective
Undertaking Undergraduate Research in Mechanical Engineering as a Nontraditional Student: A Personal Perspective Open
This paper documents our educational experience related to on-going research in carbon fiber reinforced plastic extrusion and fused filament fabrication under the supervision of faculty from the mechanical engineering program at XXX. This …
View article: DisTrack: a new Tool for Semi-automatic Misinformation Tracking in Online Social Networks
DisTrack: a new Tool for Semi-automatic Misinformation Tracking in Online Social Networks Open
Introduction: This article introduces DisTrack, a methodology and a tool developed for tracking and analyzing misinformation within Online Social Networks (OSNs). DisTrack is designed to combat the spread of misinformation through a combin…
View article: Health indicator construction based on normal states through <scp>FFT</scp>‐graph embedding
Health indicator construction based on normal states through <span>FFT</span>‐graph embedding Open
Unexpected faults in rotating machinery can lead to cascading disruptions of the entire work process, emphasizing the importance of early detection of performance degradation and identification of the current state. To accurately assess th…
View article: Understanding writing style in social media with a supervised contrastively pre-trained transformer
Understanding writing style in social media with a supervised contrastively pre-trained transformer Open
We introduce the Style Transformer for Authorship Representations (STAR) to detect and characterize writing style in social media. The model is trained on a heterogeneous large corpus derived from public sources with 4.5⋅106 authored texts…