Advances in the realism of synthetic media created with generative adversarial networks (GANs), diffusion models, and face manipulation tools has created an increased demand for well-established deepfake detection systems that can detect many different types of manipulation artifacts. However, most single model deepfake detectors are not very robust because they rely on specific forensic cues and do not adapt well to shifts in how synthesis occurs. We present DeepFakeBuster as a confidence-calibrated adaptive ensemble for deepfake image detection by fusing together heterogeneous deep learning models built around detecting complementary forensic cues e.g., spatial inconsistencies, boundary artifacts, noise residuals, semantic consistency, and frequency-domain features. In contrast to traditional ensemble approaches that use static averaging of detector outputs, our proposed framework utilizes reliability aware adaptive fusion where the contribution of each detector to the fused output is adjusted dynamically through the use of reliability priors derived from validation and input-specific confidence estimates. Our experimental evaluation on a dataset comprised of 192,000 authentic and manipulated images shows that our ensemble significantly outperforms both individual constituent detectors as well as static fusion baselines, with an overall accuracy of 97.8% for the evaluated conditions. Additionally, an interpretable forensic analysis module provides visual and quantitative indicators associated with manipulation-sensitive regions. The findings suggest that confidence-aware heterogeneous ensemble learning represents a promising direction for robust deepfake detection.
Rachana Patil, R. Shinde, S. Patil et al.· Scientific Reports· 0 citations
Pollution is a growing problem with dire effects on public health; therefore, accurate prediction of Air Quality Index (AQI) is paramount for both urban development and public health strategy. Here, we present GreenAirOps, a production-ready MLOps system that ingests multithsource environmental data, automatizes preprocessing and feature extraction, and combines Random For- est and XGBoost with ensemble learning for prediction of low-latency, near real-time AQI. This production pipeline has full MLOps pipeline capabilities: Data versioning with DVC; experiment tracking and model registration with MLflow; automated retraining and deployment using GitHub Actions. The deployment infrastructure utilizes Docker containers run on an AWS environ- ment and is designed for production grade. The specific contributions of this work are: an optimized ensemble learning system for low-latency AQI prediction; an end-to-end MLOps system which guarantee reproducibility and operational capability; and a set of production grade functions for auto-retraining, model health monitoring and auto-rollback.
Sahil Goyal, Vaibhav Sharma, Vivek Hotchandani et al.· Air quality, atmosphere and...· 0 citations
Citrus crops are economically vital worldwide, yet they remain highly susceptible to a range of infectious diseases that cause considerable yield and quality losses each year. Early and accurate disease identification is fundamental to sustainable orchard management and food security. Over the past decade, deep learning has emerged as the dominant paradigm for automated plant disease detection, surpassing traditional image-processing pipelines in both accuracy and scalability. This paper presents a comprehensive review of deep learning methodologies applied to citrus disease detection, covering convolutional neural networks (CNNs), attention mechanisms, lightweight architectures, object detection frameworks, multimodal fusion, and edge-computing deployment. Recent studies are critically analyzed with respect to model architecture, dataset characteristics, performance metrics, and deployment context. The review identifies prevailing trends including the shift toward lightweight models for edge devices, the integration of attention modules for fine-grained feature capture, and the growing adoption of multimodal and transformer-based approaches. Key open challenges such as limited data diversity, computational constraints in field deployments, and the need for domain-adaptive models are also discussed, along with prospective research directions. The findings serve as a reference for researchers and practitioners seeking to develop robust, real-time citrus disease detection systems.
Aniket K. Shahade, Vishal Jain, G. Manteghi et al.· 2026 International Conferenc...· 0 citations