Adnan Saeed

Adnan Saeed is a deep learning researcher working on medical image analysis, with a focus on multimodal architectures, graph neural networks, and evidential deep learning for clinical imaging tasks. His peer reviewed research has appeared in journals across machine learning and biomedical signal processing. At AI Trend Blend he turns recent papers into clear, practical explainers, with an emphasis on what a method actually does and where it holds up, written for readers who want depth without the hype.

Construction Site Intelligence with Ontology-Based LLM Prompting

Unlocking Construction Site Intelligence with Ontology-Based LLM Prompting

Leave a Comment / Machine Learning /

Revolutionizing Construction Management: How Ontology-Guided LLMs Decode Site Images for Smarter Decisions In the fast-paced world of construction, real-time insights into on-site activities are crucial. Understanding what workers are doing, how equipment is being used, and whether tasks align with schedules can make or break a project’s success. Traditionally, this has relied on manual reporting […]

Unlocking Construction Site Intelligence with Ontology-Based LLM Prompting Read More »

Pixel-Level Concrete Crack Quantification: A Breakthrough in Structural Health Monitoring

Pixel-Level Concrete Crack Quantification: A Breakthrough in Structural Health Monitoring

Leave a Comment / Machine Learning /

Concrete cracks are more than just surface imperfections—they’re early warning signs of structural degradation that can compromise the safety and longevity of buildings, bridges, roads, and other critical infrastructure. Traditional inspection methods often rely on manual assessments, which are time-consuming, subjective, and prone to human error. However, recent advancements in computer vision and deep learning

Pixel-Level Concrete Crack Quantification: A Breakthrough in Structural Health Monitoring Read More »

RetiGen: Revolutionizing Retinal Diagnostics with Domain Generalization and Test-Time Adaptation

RetiGen: Revolutionizing Retinal Diagnostics with Domain Generalization and Test-Time Adaptation

Leave a Comment / Machine Learning /

Introduction: Bridging the Gap in AI-Powered Retinal Diagnostics Artificial intelligence (AI) has made remarkable strides in medical imaging, particularly in ophthalmology. Deep learning models now assist clinicians in diagnosing conditions like diabetic retinopathy (DR), age-related macular degeneration, and glaucoma using color fundus photographs. However, a persistent challenge remains: domain shift—the performance drop when models trained

RetiGen: Revolutionizing Retinal Diagnostics with Domain Generalization and Test-Time Adaptation Read More »

the Improved Pelican Optimization Algorithm (IPOA)—a novel metaheuristic approach designed specifically for stochastic OPF (S-OPF) problems under uncertainty.

An Improved Pelican Optimization Algorithm for Solving Stochastic Optimal Power Flow

27 Comments / Machine Learning /

As the world transitions toward clean and sustainable energy, power systems are increasingly integrating renewable energy resources (RERs) such as solar photovoltaic (PV) and wind power. While these sources reduce carbon emissions and operational costs, their inherent uncertainty and intermittency pose significant challenges to maintaining grid stability and efficiency. One of the most critical tools

An Improved Pelican Optimization Algorithm for Solving Stochastic Optimal Power Flow Read More »

Diagram showing modified final splits (MDFS) in a classification tree for improved subpopulation targeting in policy decisions.

Modifying Final Splits of Classification Trees (MDFS) for Subpopulation Targeting

Leave a Comment / Machine Learning /

In the rapidly evolving field of machine learning for public policy, precision and fairness in decision-making are paramount. One of the most widely used tools—classification trees—has long been a cornerstone for identifying high-risk or high-need subpopulations. However, traditional methods like CART (Classification and Regression Trees) often fall short when the goal is not just prediction,

Modifying Final Splits of Classification Trees (MDFS) for Subpopulation Targeting Read More »

Diagram of Hybrid Deep Learning Model

Building Electrical Consumption Forecasting with Hybrid Deep Learning | Smart Energy Management

Leave a Comment / Machine Learning /

As global energy demand continues to rise due to rapid urbanization and technological advancements, building electrical consumption forecasting has become a critical component of modern energy management systems. With buildings accounting for nearly 40% of total global energy use, accurate prediction of electricity demand is essential for optimizing energy efficiency, reducing operational costs, and supporting

Building Electrical Consumption Forecasting with Hybrid Deep Learning | Smart Energy Management Read More »

Diagram of Multi-Teacher Knowledge Distillation with Reinforcement Learning (MTKD-RL)

Multi-Teacher Knowledge Distillation with RL — Teaching the Agent Which Teacher to Trust

Leave a Comment / Machine Learning, Knowledge Distillation /

Analysis by the aitrendblend editorial team June 30, 2025 arXiv:2502.18510 · AAAI 2025 Knowledge Distillation Reinforcement Learning Visual Recognition Teaching the Agent Which Teacher to Trust Multi-Teacher KD · Reinforcement Learning · MTKD-RL · Visual Recognition MTKD-RL from the Institute of Computing Technology, Chinese Academy of Sciences — an RL agent arbitrates teacher weights dynamically,

Multi-Teacher Knowledge Distillation with RL — Teaching the Agent Which Teacher to Trust Read More »

Discrete Migratory Bird Optimizer with Transfer Learning Aided Multi-Retinal Disease Detection

Discrete Migratory Bird Optimizer with Deep Transfer Learning for Multi-Retinal Disease Detection

4 Comments / Machine Learning /

Retinal diseases such as diabetic retinopathy (DR), age-related macular degeneration (AMD), and glaucoma are leading causes of irreversible vision loss worldwide. Early detection is critical to preventing permanent blindness, yet manual diagnosis remains time-consuming and subjective. Recent advances in artificial intelligence have paved the way for automated, high-accuracy diagnostic systems. Among them, a groundbreaking approach—Discrete

Discrete Migratory Bird Optimizer with Deep Transfer Learning for Multi-Retinal Disease Detection Read More »

PSO-optimized fractional order CNNs revolutionize breast cancer detection with 99.35% accuracy, superior sensitivity, and robust image analysi

PSO-Optimized Fractional Order CNNs for Enhanced Breast Cancer Detection

Leave a Comment / Machine Learning /

Early Detection, Smarter AI: How PSO-Optimized Fractional Order CNNs Are Transforming Breast Cancer Diagnosis Every year, millions of women face the daunting challenge of a breast cancer diagnosis. Despite advances in medical imaging, traditional mammography still struggles with high false-positive and false-negative rates, especially in patients with dense breast tissue. These limitations can lead to

PSO-Optimized Fractional Order CNNs for Enhanced Breast Cancer Detection Read More »

Visual representation of AMGF-GNN framework for tumor grading using multi-graph fusion in histopathology.

AMGF-GNN: Adaptive Multi-Graph Fusion for Tumor Grading in Pathology Images

1 Comment / Machine Learning /

In the rapidly evolving field of computational pathology, accurate tumor grading in pathology images remains a cornerstone for effective cancer diagnosis and treatment planning. With the advent of artificial intelligence (AI), researchers are increasingly turning to advanced deep learning models to automate and enhance this critical process. Among the latest breakthroughs, the Adaptive Multi-Graph Fusion-based

AMGF-GNN: Adaptive Multi-Graph Fusion for Tumor Grading in Pathology Images Read More »