Questa è la nostra ultima selezione di pubblicazioni e brevetti in inglese sull'ingegneria dei prompt, tra numerose riviste scientifiche online, classificate e incentrate su ingegneria dei prompt, progettazione dei prompt, contestualizzazione, variabilità dei prompt, regolazione degli iperparametri, mitigazione dei bias, apprendimento a zero colpi e apprendimento a pochi colpi.
Enhancing Simulation-Based e-Learning
Published on 2025-03-05 by Charlotte Meynhardt, Patrick Meybohm, Peter Kranke, Carlos Ramon H�lzing @MDPI
Abstract: Medical education is rapidly evolving with the integration of artificial intelligence (AI), particularly through the application of generative AI to create dynamic learning environments. This paper examines the transformative role of prompt engineering in enhancing simulation-based learning in emergency medicine. By enabling the generation of realistic, context-specific clinical case scenarios, prompt engineering fosters critical thinking and decision-making skills among medical trainees. To gui[...]
Our summary: Transformative role of prompt engineering in enhancing simulation-based learning in emergency medicine. Introduction of the PROMPT+ Framework for designing, evaluating, and refining prompts in AI-driven simulations. Importance of developing specialized AI models tailored to regional guidelines and educational contexts for relevance and alignment with current standards.
simulation-based learning, prompt engineering, AI-driven simulations, medical education
Publication
Optimization of Deep Learning Models for Enhanced Respiratory Signal Estimation Using Wearable Sensors
Published on 2025-03-04 by Jiseon Kim, Jooyong Kim @MDPI
Abstract: Measuring breathing changes during exercise is crucial for healthcare applications. This study used wearable capacitive sensors to capture abdominal motion and extract breathing patterns. Data preprocessing methods included filtering and normalization, followed by feature extraction for classification. Despite the growing interest in respiratory monitoring, research on a deep learning-based analysis of breathing data remains limited. To address this research gap, we optimized CNN and ResNet thro[...]
Our summary: Study optimized CNN and ResNet for enhanced respiratory signal estimation using wearable sensors. Data preprocessing included filtering, normalization, and feature extraction for classification. Optimized ResNet outperformed CNN in accuracy and precision, demonstrating its capability for real-time assessment in medical applications.
Deep Learning Models, Optimization, Wearable Sensors, Respiratory Signal Estimation
Publication
Disease Infection Classification in Coconut Tree Based on an Enhanced Visual Geometry Group Model
Published on 2025-02-27 by Xiaocun Huang, Mustafa Muwafak Alobaedy, Yousef Fazea, S. B. Goyal, Zilong Deng @MDPI
Abstract: The coconut is a perennial, evergreen tree in the palm family that belongs to the monocotyledonous group. The coconut plant holds significant economic value due to the diverse functions served by each of its components. Any ailment that impacts the productivity of the coconut plantation will ultimately have repercussions on the associated industries and the sustenance of the families reliant on the coconut economy. Deep learning has the potential to significantly alter the landscape of plant dis[...]
Our summary: Disease detection in coconut trees using an EVGG16 model trained through transfer learning achieves high accuracy rates, revolutionizing plant disease detection and improving productivity in coconut plantations.
Deep Learning, Convolutional Neural Networks, Enhanced Visual Geometry Group Model, Disease Infection Classification
Publication
Feature Fusion Transformer for Zero-Shot Learning
Published on 2025-02-26 by Wenjin Tao, Jiahao Xie, Zhinan An, Xianjia Meng @MDPI
Abstract: Zero-shot learning (ZSL) typically leverages semantic knowledge and textual descriptions of classes to forge connections between seen and unseen classes. ZSL can classify new categories of data unseen in the training set. Prior research has focused on aligning image features with their corresponding auxiliary information, overlooking the limitation whereby individual features may not capture the full spectrum of information inherent in the original image. Additionally, there are concerns regardi[...]
Our summary: Feature Fusion Transformer for Zero-Shot Learning leverages semantic knowledge to classify unseen data, addressing bias towards seen classes, achieving 76.8% accuracy in the CUB dataset.
Feature Fusion Transformer, Zero-Shot Learning, Semantic Knowledge, Auxiliary Information
Publication
How the Choice of LLM and Prompt Engineering Affects Chatbot Effectiveness
Published on 2025-02-24 by Lukasz Pawlik @MDPI
Abstract: Modern businesses increasingly rely on chatbots to enhance customer communication and automate routine tasks. The research aimed to determine the optimal configurations of a telecommunications chatbot on the Rasa Pro platform, including the selection of large language models (LLMs), prompt formats, and command structures. The impact of various LLMs, prompt formats, and command precision on response quality was analyzed. Smaller models, like Gemini-1.5-Flash-8B and Gemma2-9B-IT, can achieve resul[...]
Our summary: Impact of LLM and prompt engineering on chatbot effectiveness, Analysis of optimal configurations for telecommunications chatbot, Importance of prompt preparation and data format choice.
LLM, prompt engineering, chatbot, telecommunications
Publication
Few-Shot Learning with Multimodal Fusion for Efficient Cloud–Edge Collaborative Communication
Published on 2025-02-19 by Bo Gao, Xing Liu, Quan Zhou @MDPI
Abstract: As demand for high-capacity, low-latency communication rises, mmWave systems are essential for enabling ultra-high-speed transmission in fifth-generation mobile communication technology (5G) and upcoming 6G networks, especially in dynamic, data-scarce environments. However, deploying mmWave systems in dynamic environments presents significant challenges, especially in beam selection, where limited training data and environmental variability hinder optimal performance. In such scenarios, computat[...]
Our summary: Efficient cloud-edge collaboration using few-shot learning and multimodal fusion for high-speed transmission in dynamic environments. Leveraging diverse modalities within a cloud-edge architecture to optimize resource utilization and reduce latency. Experimental evaluations confirm high accuracy under limited data conditions.
Few-Shot Learning, Multimodal Fusion, Cloud-Edge Collaboration, Beam Selection Accuracy
Publication
Rendering techniques
Patent published on the 2024-11-16 in TW under Ref TW202446101 by FRAUNHOFER GES FORSCHUNG [DE] (Peters Nils [de], Silzle Andreas [de], Adami Alexander [de], Disch Sascha [de])
Abstract: There is disclosed renderer apparatus, comprising: a rendering unit configured to process an audio scene representation (402, 412) to be rendered and to receive at least one context-specific rule or parameter (441, 442), the rendering unit being configured to generate a rendered audio signal from the audio scene representation (402, 412) conditioned by the at least one context-specific rule or parameter (441, 442), a contextualization unit configured to receive and/or derive context-specific dat[...]
Our summary: Rendering unit processes audio scene representation and generates rendered audio signal based on context-specific rule, contextualization unit provides rule based on context-specific data.
Rendering techniques, renderer apparatus, audio scene representation, context-specific rule
Patent
IT 
EN 
FR 
DE 
ES