This is our latest selection of worldwide publications and patents in english on Prompt Engineering, between many scientific online journals, classified and focused on prompt engineering, prompt design, contextualization, prompt variability, hyperparameter tuning, bias mitigation, zero-shot learning and few-shot learning.
Meta-Transfer-Learning-Based Multimodal Human Pose Estimation for Lower Limbs
Published on 2025-03-06 by Guoming Du, Haiqi Zhu, Zhen Ding, Hong Huang, Xiaofeng Bie, Feng Jiang @MDPI
Abstract: Accurate and reliable human pose estimation (HPE) is essential in interactive systems, particularly for applications requiring personalized adaptation, such as controlling cooperative robots and wearable exoskeletons, especially for healthcare monitoring equipment. However, continuously maintaining diverse datasets and frequently updating models for individual adaptation are both resource intensive and time-consuming. To address these challenges, we propose a meta-transfer learning framework tha[...]
Our summary: Accurate and reliable human pose estimation is crucial for interactive systems, especially for personalized adaptation in applications like controlling robots and wearable exoskeletons for healthcare monitoring. A meta-transfer learning framework is proposed, integrating multimodal inputs to improve accuracy and stability through knowledge fusion, resolving data alignment issues and enabling seamless integration of different modalities. Additionally, a training and adaptation framework with few-shot learning is introduced for efficient updating of encoders and decoders in real-time applications, demonstrating accurate pose estimations for intra-subject adaptation.
Meta-Transfer Learning, Multimodal Inputs, Human Pose Estimation, Lower Limbs
Publication
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
A New, Robust, Adaptive, Versatile, and Scalable Abandoned Object Detection Approach Based on DeepSORT Dynamic Prompts, and Customized LLM for Smart Video Surveillance
Published on 2025-03-04 by Merve Yilmazer, Mehmet Karakose @MDPI
Abstract: Video cameras are one of the important elements in ensuring security in public areas. Videos inspected by expert personnel using traditional methods may have a high error rate and take a long time to complete. In this study, a new deep learning-based method is proposed for the detection of abandoned objects, such as bags, suitcases, and suitcases left unsupervised in public areas. Transfer learning-based keyframe detection was first performed to remove unnecessary and repetitive frames from the [...]
Our summary: A new deep learning-based approach for abandoned object detection in smart video surveillance is proposed. Transfer learning is used for keyframe detection, YOLOv8l model for human and object classes detection, DeepSORT algorithm for tracking classes, and customized LLM for analysis and explanation output. The model shows promising results with high precision, recall, and f1-score.
DeepSORT, Adaptive, Transfer learning, Customized LLM
Publication
Filament Type Recognition for Additive Manufacturing Using a Spectroscopy Sensor and Machine Learning
Published on 2025-03-02 by Gorkem Anil Al, Uriel Martinez-Hernandez @MDPI
Abstract: This study presents a novel approach for filament recognition in fused filament fabrication (FFF) processes using a multi-spectral spectroscopy sensor module combined with machine learning techniques. The sensor module measures 18 wavelengths spanning the visible to near-infrared spectra, with a custom-designed shroud to ensure systematic data collection. Filament samples include polylactic acid (PLA), thermoplastic polyurethane (TPU), thermoplastic copolyester (TPC), carbon fibre, acrylonitrile[...]
Our summary: Novel approach for filament recognition using spectroscopy sensor and machine learning techniques, measuring 18 wavelengths and testing various filament samples, achieving high accuracy of 98.95% with SVM model.
spectroscopy sensor, machine learning, filament recognition, additive manufacturing
Publication
Baby Cry Classification Using Structure-Tuned Artificial Neural Networks with Data Augmentation and MFCC Features
Published on 2025-03-01 by Tayyip Ozcan, Hafize Gungor @MDPI
Abstract: Babies express their needs, such as hunger, discomfort, or sleeplessness, by crying. However, understanding these cries correctly can be challenging for parents. This can delay the baby’s needs, increase parents’ stress levels, and negatively affect the baby’s development. In this paper, an integrated system for the classification of baby sounds is proposed. The proposed method includes data augmentation, feature extraction, hyperparameter tuning, and mo[...]
Our summary: Classification of baby sounds using structure-tuned artificial neural networks with data augmentation and MFCC features resulted in a 90% accuracy rate, offering an effective solution for understanding baby cries and addressing their needs.
Artificial Neural Networks, Data Augmentation, MFCC Features, Classification
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
FR 
EN 
DE 
ES 
IT