Cities face pressure from urban growth and climate risk, yet deployed systems stay single-domain and reactive. This PRISMA-guided rapid review applies operationalized criteria to separate Agentic AI from conventional machine learning for SDG 11 (Sustainable Cities and Communities) and SDG 13 (Climate Action). Agentic AI is defined by four properties: task-level autonomy, goal-directed planning, tool use, and multi-agent coordination; evidencing at least two marks a system as fully agentic. A two-tier search across five databases with backward citation tracking returned 896 records (2018–2026), of which 60 met the eligibility criteria and 14 satisfied the agentic threshold. The corpus is stratified by study type with a threshold sensitivity analysis. Two contributions follow: a reference architecture specifying how an agentic layer and an urban digital twin exchange state, and a real-data feasibility study on the SEVIR archive testing whether multimodal fusion improves hazard classification. On real data the proposed model is the best-ranked of four but only marginally exceeds a no-change persistence baseline, giving the assumption weak support, not operational evidence. The review reveals a field growing sharply since 2023, clustered in a few urban and climate domains, with almost no validated cross-domain deployment.
Toqeer Ali Syed, Ali Akarma, M. Naqash et al.· Sustainability· 6 citations
The rapid growth of online digital platforms has significantly increased the need for recommender systems (RSs) that can deliver personalized content to users. Cross-domain recommender systems (CDRS) have emerged as promising solution to the limitations of single-domain models by incorporating user preferences, interaction histories, and item features from a source domain to enhance recommendations accuracy in a sparse target domain. However, effective transfer of knowledge from source domain to the target domain remains a challenging task due to differences in distributions of data, domain inconsistencies, and variations in user behavior. In this study, we propose a sparsity-aware generative adversarial networks-based cross-domain recommender system, named SPARGAN. The proposed model facilitates flexible and effective knowledge transfer by learning domain-invariant latent representations and generating realistic synthetic user-item interactions. SPARGAN incorporates adversarial learning and a domain-confusion loss to align user-item feature distributions between the source and target domains while preserving personalized user preferences. Additionally, the generator enhances the target-domain data by producing high-quality synthetic samples, thereby mitigating the impact of data sparsity problems. Extensive experiments are conducted on four real-world datasets: MovieLens, Amazon, Yelp, and Book-crossing. The experimental results demonstrate that SPARGAN consistently outperforms baseline methods in both top-N recommendation and rating prediction tasks, achieving superior performance in terms of Recall, Precision, RMSE, and F1-score under extreme sparsity conditions. Overall, this study highlights the effectiveness of adversarial learning for cross-domain knowledge transfer and provides foundation for future research on multi-source domain adaptation in cross-domain recommender systems with Gen AI models.
Matthew O. Ayemowa, Roliana Ibrahim, Noor Hidayah Zakaria et al.· Discover Computing· 0 citations
Today, the use of increasingly ubiquitous synthetic media, or ‘deepfakes’, has become a risk to online trust, information integrity and individual security and is being created by artificial intelligence (AI). The current approaches are mainly based on either spatial features of CNNs or high-level semantic representations of Vision Transformer; both have major drawbacks in effectively leveraging multi-domain forensic cues. This paper presents FAViT (Frequency-Aware Vision Transformer), a hybrid architecture capable of jointly utilizing spatial- and frequency-domain forensic information by the means of a bidirectional cross-attention fusion scheme. We use an 11-channel forensic tensor in each face image (including per-channel Fast Fourier Transform (FFT) magnitude maps, Discrete Wavelet Transform (DWT) sub-bands, channel noise residual maps, Sobel gradient magnitude and channels of Error Level Analysis (ELA)). A Frequency Branch CNN processes this multi-domain tensor and the original RGB image is encoded with a pretrained ViT-B/16 spatial branch. The two streams are combined through the bidirectional cross-attention which allows the model to localize both spatial and spectral manipulation artifacts. We also present an adversarial cleaning simulation pipeline which partitions the training process with five post-processing attack methods, namely GFPGAN neural face restoration, learned autoencoder cleaning, etc., to increase resistance to real-world forensic defenses. Tests of FaceForensics++ C23 (7926 images, consisting of four manipulation types) show that FAViT attains F1-score of 86.22, AUC-ROC of 94.26 and accuracy of 85.55 on the held-out test set. The strength analysis of 21 attack conditions shows that the max degradation in AUC is 30.3, with specific strengths in GFPGAN restoration (AUC = 98.51). Robustness is evaluated based on 21 post-processing attack cases that include JPEG compression, Gaussian blurring, down-sampling, and GFDGAN neural-based restoration; it should be noted that robustness against gradient-based adaptive attacks requires additional attention. Testing on the CIFAKE and Celeb-DF v2 datasets reveals some limitations of domain generalization.
Wasin Alkishri, Shahid Kamal, Jabar H. Yousif· Information· 0 citations
We use cookies to run the site and, with your consent, for analytics and to show ads.
See our Cookie Policy.
