Muhammad Moazam Fraz

Beyond Pixel Similarity: Task-Aware Evaluation of GAN-Based Synthetic Sonar Data for Robotic Perception

Hannan Ejaz Keen, Muhammad Moazam Fraz, Karsten Berns

Synthetic data can reduce the cost of collecting and annotating training data for robotic perception, but generating sensor observations that preserve the characteristics relevant to downstream perception remains challenging, particularly for sonar imagery. In this work, we investigate whether conventional image-fidelity metrics …

Unsupervised Domain Adaptation with Temporal Prompts for Robust Crop Classification in Satellite Imagery

Mammona Qudsia, Muhammad Naseer Bajwa, Zuhair Zafar, Muhammad Moazam Fraz

pk (code pays fourni par la source)

Multi-city analysis of climate trends, cooling demand, and residential electricity use in Pakistan

Muhammad Naseer Bajwa, Muhammad Ahmad Jamil, Haseeb Yaqoob, Muhammad Wakil Shahzad et autres

Space cooling has become one of the fastest-growing sources of residential electricity demand across low- and middle-income countries, and Pakistan represents a critical case. With approximately 646 billion person-Cooling Degree Days (CDDs) annually, it ranks among the highest cooling-demand nations globally, yet …

pk, gb (code pays fourni par la source)

Early Real-World Clinical Evaluation of an AI-Enabled Decision Support System for Referral Triage in LMIC Primary Care

Hira Masood, Muhammad Naseer Bajwa, Saima Shafait, Muhammad Moazam Fraz et autres

pk, gb (code pays fourni par la source)

XMedFusion: A Knowledge-Guided Multimodal Perception and Reasoning Framework for Autonomous Medical Systems

Hamza Riaz, Arham Haroon, Maha Baig, Muhammad Dawood Rizwan et autres

Autonomous medical and robotic systems increasingly rely on intelligent perception and reasoning capabilities to interpret visual data and support clinical decision making. Radiology report generation represents a critical component of such automated diagnostic workflows, yet existing end-to-end multimodal models often suffer from …

XMedFusion: A Knowledge-Guided Multimodal Perception and Reasoning Framework for Autonomous Medical Systems

Hamza Riaz, Arham Haroon, Maha Baig, Muhammad Dawood Rizwan et autres

Autonomous medical and robotic systems increasingly rely on intelligent perception and reasoning capabilities to interpret visual data and support clinical decision making. Radiology report generation represents a critical component of such automated diagnostic workflows, yet existing end-to-end multimodal models often suffer from …

pk (code pays fourni par la source)

From Segmentation to Structured Reports: Auditable Continual Learning for Automation in Medical Imaging Diagnostics

Farhan Kashif, Ahmed Sultan, Muhammad Dawood Rizwan, Muhammad Naseer Bajwa et autres

Autonomous medical systems such as surgical robots, AI-guided treatment planners, and telemedicine platforms require diagnostic modules that are adaptive, interpretable, and structured. We present a modular, continually learning perception-to-report pipeline for automated brain tumor diagnosis, designed for integration into clinical robotic ecosystems. …

pk, gb (code pays fourni par la source)

MedLingo: Resource-Efficient Hierarchical Multi-Agent Intelligence for Autonomous Clinical and Robotic Diagnostics

Sarmad Sultan, Muhammad Sami Ullah, Ahmad Jan, Muhammad Dawood Rizwan et autres

Reliable multimodal intelligence is essential for autonomous clinical and robotic diagnostic systems, yet existing large-scale models remain difficult to deploy in real-world environments due to high computational cost, latency, and the risk of cross-modal hallucinations. This paper presents MedLingo, a hierarchical multi-agent …

pk (code pays fourni par la source)

Analyzing UAV-Based Multispectral Data for Genotypic-Aware Crop Performance Assessment

Muhammad Tayyab Iftikhar, Abdullah Imran, Muhammad Hissan Umar, Usama Athar et autres

High-throughput and accurate trait characterization is critical for accelerating crop improvement, yet conventional field methods often fail to capture genotype-specific, stage-level temporal dynamics relevant to yield. In this study, UAV-based multispectral imagery across $\mathbf{1 6}$ growth-stage timestamps revealed key phenological and physiological …

pk (code pays fourni par la source)

HunarmandAI: A Bilingual Intelligent Diagnostic Interface for Smart Vehicles and Industrial Mechatronic Systems

Muhammad Nabeel, Abubakar Khan, Muhammad Dawood Rizwan, Mehtab Malik et autres

Modern smart vehicles and industrial mechatronic systems generate complex sensor telemetry and alphanumeric fault codes that require accurate interpretation to ensure reliable and safe operation. In multilingual industrial environments, diagnostic documentation is predominantly available in English, while technicians rely on code-mixed vernacular …

pk (code pays fourni par la source)

A Hybrid Multimodal Architecture for Named Entity Recognition on Social Media Using Domain-Specific Language Modelling and Token-Level Gated Visual Fusion

Ayesha Shehzadi, Muhammad Moazam Fraz, Syed Imran Ali, Hafiz Syed Muhammad Bilal et autres

Named entity recognition on social media is a markedly harder problem than its counterpart on formal text, owing to the informal vocabulary, creative abbreviations, and context-dependent entity references that characterise platforms such as Twitter. Although attaching an image to a tweet often …

pk (code pays fourni par la source)

Boundary-Consistent Ordinal Regression for wheat yield prediction using UAV-based multispectral time-series data

Muhammad Salman Akhtar, Zuhair Zafar, Zahid Mahmood, Muhammad Kashif Naeem et autres

pk, kz, gb (code pays fourni par la source)