Create accountLogin

Recent searches

No recent searches

Search options

Only available when logged in.
eupolicy.social is one of the many independent Mastodon servers you can use to participate in the fediverse.
This Mastodon server is a friendly and respectful discussion space for people working in areas related to EU policy. When you request to create an account, please tell us something about you.

Administered by:

Server stats:

235
active users

eupolicy.social: AboutProfiles directoryPrivacy policy

Mastodon: AboutGet the appKeyboard shortcutsView source codev4.3.6

#ai4good

0 posts0 participants0 posts today
Public
Dan Stowell

I'm pleased to share this, a preprint of our first work on predicting electrical grids using graph neural networks: "Enhanced Load Forecasting with GAT-LSTM: Leveraging Grid and Temporal Features" led by Ugochukwu Orji arxiv.org/abs/2502.08376 #ai4good #forecasting #GNN #electricalgrid

arXiv.orgEnhanced Load Forecasting with GAT-LSTM: Leveraging Grid and Temporal FeaturesAccurate power load forecasting is essential for the efficient operation and planning of electrical grids, particularly given the increased variability and complexity introduced by renewable energy sources. This paper introduces GAT-LSTM, a hybrid model that combines Graph Attention Networks (GAT) and Long Short-Term Memory (LSTM) networks. A key innovation of the model is the incorporation of edge attributes, such as line capacities and efficiencies, into the attention mechanism, enabling it to dynamically capture spatial relationships grounded in grid-specific physical and operational constraints. Additionally, by employing an early fusion of spatial graph embeddings and temporal sequence features, the model effectively learns and predicts complex interactions between spatial dependencies and temporal patterns, providing a realistic representation of the dynamics of power grids. Experimental evaluations on the Brazilian Electricity System dataset demonstrate that the GAT-LSTM model significantly outperforms state-of-the-art models, achieving reductions of 21. 8% in MAE, 15. 9% in RMSE and 20. 2% in MAPE. These results underscore the robustness and adaptability of the GAT-LSTM model, establishing it as a powerful tool for applications in grid management and energy planning.
Continued thread
Public
Joanna Bryson, blathering

I'm in another small panel, this one on Empowering Digital Citizens: Expert Agents to Protect Consumer Interests. Maybe everyone's queuing for Bill Gates? I'm not sure if I'm going to his 10 minute keynote on inequlaity –I already talk about AI at iJCAI 2001.

Amir Banifatemi (Mr. #AI4Good) is talking about experimenting with policies in 2 years. "global challenge to build trust" Amazon & Microsoft are helping. Expecting 50-100 winners. It's not trust in AI! It's real trust eg in medical advice.

Public *
Muse™ - Listen to your Muse

🌐 #business #Website #Blogs
listentoyourmuse.com/

📣 Join our #communities

🔗 #LinkedIn
linkedin.com/company/ia-muses

🔗 #LinkedInGroup
linkedin.com/groups/12627306/

📨 #newsletter
linkedin.com/newsletters/muse-

🐘 #Mastodon
mastodon.world/@AlexandreMarti

𝕏 #Twitter
twitter.com/musetm_grenoble

🦋 #Bluesky
bsky.app/profile/muse-tm.bsky.

#StrategicIntelligence on #AI #NFT #cyberdefense #Management #metavers #Web3 #AI4good #Industry40 #socialmedia #infolettre #technology

Muse™Muse™: Listen to your muse - is a synopsis of a strategic AI and Generative AI topics to get to the point quickly.Muse™ is the 1st and foremost website highlighting the various uses of AI. Muse™ is a monthly newsletter presenting a synopsis of a strategic artificial intelligence, AI4Good, Fintech, GenAI, Data Ethics and more. Muse™ offers you the opportunity to collaborate (opinions, feedback, suggestions...)
ExploreLive feeds
About