AI for crisis decisions

Ethics and Information Technology, Journal Year: 2024, Volume and Issue: 26(1)

Published: Feb. 14, 2024

Abstract Increasingly, our cities are confronted with crises. Fuelled by climate change and a loss of biodiversity, increasing inequalities fragmentation, challenges range from social unrest outbursts violence to heatwaves, torrential rainfall, or epidemics. As crises require rapid interventions that overwhelm human decision-making capacity, AI has been portrayed as potential avenue support even automate decision-making. In this paper, I analyse the specific in urban crisis management an example test case for many super wicked decision problems. These problems characterised coincidence great complexity urgency. will argue combination, arise only partially covered current guidelines standards around trustworthy human-centered AI. By following decision-centric perspective, solve urgent problems, context, capacities, networks need be addressed. response needs follow dedicated design principles ensure (i) control complex networks, where humans interact AI; (ii) principled considers core such solidarity humanity; (iii) designing most vulnerable. paper is meant inspire researchers, developers practitioners space (urban) – other planners with.

Language: Английский

---

PBNet: Combining Transformer and CNN in Passport Background Texture Printing Image Classification

Electronics, Journal Year: 2024, Volume and Issue: 13(21), P. 4160 - 4160

Published: Oct. 23, 2024

Passport background texture classification has always been an important task in border checks. Current manual methods struggle to achieve satisfactory results terms of consistency and stability for weakly textured images. For this reason, study designs develops a CNN Transformer complementary network (PBNet) passport image classification. We first design two encoders by produce features the domains, respectively. Then, we cross-wisely concatenate these propose feature enhancement module (FEM) effectively blending them. In addition, introduce focal loss relieve overfitting problem caused data imbalance. Experimental show that our PBNet significantly surpasses state-of-the-art segmentation models based on CNNs, Transformers, even combined designed

Language: Английский

---

Impact of Noise in Large Real-World Datasets on Semi-Supervised Object Detection: A Case Study of Homeless Encampments Detection

2021 IEEE International Conference on Big Data (Big Data), Journal Year: 2024, Volume and Issue: unknown, P. 1434 - 1441

Published: Dec. 15, 2024

Language: Английский

---

Introduction to the special section on Computing and Communication Networks (ICCCN 2022) (VSI-icccn)

Physical Communication, Journal Year: 2023, Volume and Issue: 60, P. 102152 - 102152

Published: July 13, 2023

Language: Английский

---