Enhancing plant disease detection from leaf imagery remains a persistent challenge due to scarce labeled data and complex contextual factors. We introduce a transformative two-stage methodology: Mid Point Normalization (MPN) for intelligent image preprocessing, coupled with sophisticated attention mechanisms that dynamically recalibrate feature representations. Our classification pipeline, merging MPN with Squeeze-and-Excitation (SE) blocks, achieves remarkable 93% accuracy while maintaining exceptional class-wise balance. The perfect F1 score attained for our target class exemplifies attention’s power in adaptive feature refinement. For segmentation tasks, we seamlessly integrate identical attention blocks within U-Net architecture using MPN-enhanced inputs, delivering compelling performance gains with 72.44% Dice score and 58.54% IoU, substantially outperforming baseline implementations. Beyond superior accuracy metrics, our approach yields computationally efficient, lightweight architectures perfectly suited for real-world computer vision applications.

Dynamic resource allocation for machine learning workloads in cloud environments remains challenging due to competing objectives of minimizing training time and operational costs while meeting Service Level Agreement (SLA) constraints. Traditional approaches employ static resource allocation or single-objective optimization, leading to either SLA violations or resource waste. We present SLA-MORL, an adaptive multi-objective reinforcement learning framework that intelligently allocates GPU and CPU resources based on user-defined preferences (time, cost, or balanced) while ensuring SLA compliance. Our approach introduces two key innovations: (1) intelligent initialization through historical learning or efficient baseline runs that eliminates cold-start problems, reducing initial exploration overhead by 60%, and (2) dynamic weight adaptation that automatically adjusts optimization priorities based on real-time SLA violation severity, creating a self-correcting system. SLA-MORL constructs a 21-dimensional state representation capturing resource utilization, training progress, and SLA compliance, enabling an actor-critic network to make informed allocation decisions across 9 possible actions. Extensive evaluation on 13 diverse ML workloads using production HPC infrastructure demonstrates that SLA-MORL achieves 67.2% reduction in training time for deadline-critical jobs, 68.8% reduction in costs for budget-constrained workloads, and 73.4% improvement in overall SLA compliance compared to static baselines. By addressing both cold-start inefficiency and dynamic adaptation challenges, SLA-MORL provides a practical solution for cloud resource management that balances performance, cost, and reliability in modern ML training environments. Our code is open-source and available at https://github.com/big-data-lab-umbc/SLA-MORL.

Ocean eddies play a significant role both at the sea surface and beneath it, contributing to the sustainability of marine ecosystems and influencing broader oceanic and climatic behaviors. Investigating ocean eddies is essential for monitoring changes in the Earth’s oceans and their impact on climate. This study focuses on benchmarking the performance of state-of-theart YOLO (You Only Look Once) models for locating small-scale (<20km) ocean eddies using satellite remote sensing images. We leverage AWS SageMaker for this evaluation, utilizing both single and multi-GPU configurations to explore the feasibility and efficiency of deploying AI applications in cloud-based environments. This research not only assesses the effectiveness of SageMaker in handling complex Earth science data but also provides insights into deployment challenges, resource management for large-scale data, and the overall user experience. The findings highlight the strengths and limitations of using SageMaker for remote sensing applications and suggest potential future research directions. Our code is open-sourced at https://shorturl.at/hcjmq.

This study focuses on small-scale ocean eddy (<20km) detection in satellite remote images using Convolutional Neural Network (CNN) deployed on AWS cloud platforms, specifically SageMaker and EC2. Our goal is to streamline the workflow and make the services accessible in the climate change domain. In this work, we proposed a CNN-based Ocean Eddy detection model and it is deployed using Sage-Maker and EC2. Our proposed approach achieved more than 95% and 94% training and validation accuracy respectively by applying principal component analysis (PCA) on the dataset. We considered the usability, performance, and cost comparison while deploying the services. Our analysis shows that SageMaker and EC2 are highly capable of building CNN-based services, though there are some challenges in deploying services and limitations related to resources.

Atmospheric gravity waves are produced when gravity attempts to restore disturbances through stable layers in the atmosphere. They have a visible effect on many atmospheric phenomena such as global circulation and air turbulence. Despite their importance, however, little research has been conducted on how to detect gravity waves using machine learning algorithms. We faced two major challenges in our research: our raw data had a lot of noise and the labeled dataset was extremely small. In this study, we explored various methods of preprocessing and transfer learning in order to address those challenges. We pre-trained an autoencoder on unlabeled data before training it to classify labeled data. We also created a custom CNN by combining certain pre-trained layers from the InceptionV3 Model trained on ImageNet with custom layers and a custom learning rate scheduler. Experiments show that our best model outperformed the best performing baseline model by 6.36% in terms of test accuracy.

The Arctic is a region with unique climate features, motivating new AI methodologies to study it. Unfortunately, Arctic sea ice has seen a continuous decline since 1979. This not only poses a significant threat to Arctic wildlife and surrounding coastal communities but is also adversely affecting the global climate patterns. To study the potential of AI in tackling climate change, we analyze the performance of four probabilistic machine learning methods in forecasting sea-ice extent for lead times of up to 6 months, further comparing them with traditional machine learning methods. Our comparative analysis shows that Gaussian Process Regression is a good fit to predict sea-ice extent for longer lead times with lowest RMSE score.

3GPP Long-term Evolution (LTE) systems being deployed are fast gaining market shares. High data rates (approaching 100 Mbit/s in the downlink direction and 50 Mbit/s for uplink connections) and small delays are attractive features of LTE. Spectrum flexibility also makes deployment easy on various frequency bands in different parts of the world. However, as LTE offers packet switched services only, mobile broadband connectivity has become the dominant LTE application so far. This paper studies user-perceived quality of service for a mobile Voice over IP (VoIP) application in LTE. Results were achieved using the OPNET Modeler simulation environment.