Glaucoma, a leading cause of irreversible blindness globally, manifests as a gradual, stealthy progression of ocular structural changes that pose challenges for early detection. Attentive monitoring and proactive meas...
详细信息
This study explores the use of Graph Neural Networks (GNNs) to classify enzyme functions using the ENZYMES dataset, which represents proteins and their interactions as graphs. The literature review highlights the evol...
详细信息
This study explores the application of machine learning (ML) and advanced voice signal analysis to classify speech disorders, including vocal tremors, dysarthria, and stuttering. These disorders pose significant chall...
详细信息
ISBN:
(纸本)9798331532215
This study explores the application of machine learning (ML) and advanced voice signal analysis to classify speech disorders, including vocal tremors, dysarthria, and stuttering. These disorders pose significant challenges to communication and quality of life, requiring precise and reliable diagnostic tools. To address the inherent challenges of limited data availability in this domain, the study employs synthetic voice data generated using mathematical models to augment real-world recordings. This hybrid approach ensures a more comprehensive dataset, enabling robust training and evaluation of machine learning *** machine learning algorithms such as Support Vector Machines (SVMs), Random Forest, and Gradient Boosting are utilized to extract and analyze a wide range of acoustic features from speech samples. These methods are selected for their ability to handle complex, nonlinear patterns and to identify subtle distinctions between normal and disordered speech. By leveraging these techniques, the study investigates their performance in accurately classifying speech disorders, emphasizing their potential in improving diagnostic *** findings highlight the transformative potential of machine learning in the field of speech pathology. ML models demonstrated notable improvements in the precision, efficiency, and consistency of diagnosing speech disorders compared to traditional methods. This breakthrough not only enhances diagnostic reliability but also equips clinicians with objective tools that reduce subjectivity in assessments. Moreover, the integration of these technologies promotes earlier detection of disorders, enabling timely and tailored therapeutic *** facilitating more accurate and accessible diagnostic practices, this work paves the way for significant advancements in patient care. The use of ML-powered tools can bridge the gap between clinical expertise and technological innovation, empowering healthcare professionals to offer pe
This study presents a systematic evaluation of deep learning architectures for photovoltaic (PV) power forecasting, comparing nine model configurations across three architectures (MLP, LSTM, CNN) and three optimizers ...
详细信息
The proceedings contain 32 papers. The special focus in this conference is on Practical Applications of Agents and Multi-Agent Systems. The topics include: Reinforcement learning Enabled Peer-to-Peer Energy Trading fo...
ISBN:
(纸本)9783031704147
The proceedings contain 32 papers. The special focus in this conference is on Practical Applications of Agents and Multi-Agent Systems. The topics include: Reinforcement learning Enabled Peer-to-Peer Energy Trading for Dairy Farms;Benchmarking Large Language Models for Multi-agent Systems: A Comparative Analysis of AutoGen, CrewAI, and TaskWeaver;multi-agent Opinion Pooling by Voting for Bins: Simulations and Characterization;neural Cellular Automaton for Decentralized Inference in Distributed Manipulation Systems;synthetic data Generation for Machine learning Models with Cognitive Agent Simulations;a Digital Twin Approach to Building’s Dossier for Seismic Prevention;mineLlama: Llama with Retrieval-Augmented Generation as A Decision Maker in Minecraft;learning Automata Strategies for Prolonging Lifetime of Wireless Sensor Networks;options to Speed-Up Search in Lifelong Multi-Agent Pathfinding;cooperative Task Execution in Multi-agent Systems;federated Neural Machine Translation Using Multi-agent Reinforcement learning;a Decentralized Agent-Based Model for Crisis Events Using Embedded Systems;Human and BDI-Agent Interaction via KQML Messages over IMAP and SMTP;models of intelligent Tutoring Systems Based on Autonomous Agents for Virtual learning Environments: A Systematic Literature Review;dynamic Estimation of Customer Movements by Agent-Based Simulation with Particle Filter;retrieval-Augmented Generation Powered by a Multi-agent System to Assisted the Operation of Industries;EGAR: Environment Generator for Agent-Based Research;collaborating Digital Twins for Health Coaching;Overcoming Computational Complexity: A Scalable Agent-Based Model of Traffic Activity Using FLAME-GPU;Measuring Fairness in AI Explanations with LEADR: Local Explanation Amplification Disparity Ratio;adaptive learning of Centralized and Decentralized Rewards in Multi-agent Imitation learning;integrating Supervised and Reinforcement learning for Heterogeneous Traffic Simulation;dynamic Modificati
The transition towards a sustainable and low-carbon future introduces the necessity to develop efficient energy storage systems. H2, with its high energy density and environmental benignity, emerges as a pivotal eleme...
详细信息
The international Energy Agency's World Energy Outlook 2023 highlights the essential role of photovoltaic (PV) energy in the global energy transition. Despite advancements, solar energy utilization lags behind PV ...
详细信息
The international Energy Agency's World Energy Outlook 2023 highlights the essential role of photovoltaic (PV) energy in the global energy transition. Despite advancements, solar energy utilization lags behind PV production capacity. Addressing this requires active involvement from energy stakeholders and consumers, often within energy communities, to develop tools for economic and sustainable PV energy production. Accurate PV production forecasts are crucial for market positioning, grid integration, and energy exchange coordination. Current models, which rely on irradiance data, fall short in capturing complex atmospheric phenomena, limiting predictions to short-term forecasts. This proposal aims to provide PV production forecasts by integrating validated meteorological data with advanced models, targeting reliable two-week ahead forecasts. A nowcasting model, trained on historical weather and PV production data, will predict production based on weather forecasts. The approach generalizes predictions beyond the training dataset, applicable to diverse PV installations. The methodology combines global numerical models with machine learning techniques, including Long Short-Term Memory (LSTM) and Transformer Neural Networks (NN), evaluated against classical methods. Training with real data from five PV sites will optimize model performance through a weighted combination of losses. This hybrid approach aims to enhance PV production accuracy and integration, promoting effective solar energy utilization.
This paper proposes a novel intelligent human activity recognition (HAR) framework based on a new design of Federated Split learning (FSL) with Differential Privacy (DP) over edge networks. Our FSL-DP framework levera...
详细信息
intelligentdata placement in hierarchical distributed storage networks (DSNs) has become crucial due to advancements in storage devices, an increase in big data applications, and strict time constraints. Inefficient ...
详细信息
Highway service area traffic flow has an important guiding role in the reconstruction and expansion of service areas. As the time scale decreases, the inherent characteristics of traffic flow, such as uncertainty and ...
详细信息
暂无评论