arXiv subjects

Sameer Alam

Publications and source records attributed to Sameer Alam.

12 recordsLinked to original sources

arXiv2026

Beyond Semantic Accuracy: Consequence-Aware Evaluation for Safety-Critical Language Understanding

Can language models be trusted in safety- critical operations? In such settings, strong per- formance on semantic metrics does not guaran- tee operational reliability: a misread altitude, a dropped execution condition, or a confused call- sign may score well under standard F1 yet carry sharply asymmetric operational consequences. We study this problem in air traffic control (ATC), where controller-pilot communication demands near-zero error tolerance, and use consequence-aware evaluation to test whether semantic scores misstate operational reliabil- ity. The framework is instantiated in a con- trolled diagnostic ATC benchmark grounded in aviation standards and feedback from 40 air traffic controllers across three countries. Evaluating 8 models, we uncover a system- atic semantic-safety gap: conventional scores give substantially higher performance estimates than consequence-aware evaluation, even for models that appear reliable under standard met- rics. Risk-aware fine-tuning narrows but does not close this gap, showing that consequence- aware evaluation is a necessary complement to standard NLP metrics before any real safety- critical deployment claim

cs.CL↗

arXiv2026

Safety-Oriented Evaluation of Language Understanding Systems for Air Traffic Control

Air Traffic Control (ATC) is a safety-critical domain in which incorrect interpretation of instructions may lead to severe operational consequences. While large language models (LLMs) demonstrate strong general performance, their reliability in operational ATC environments remains unclear. Existing evaluation approaches, largely based on aggregate metrics such as F1 or macro accuracy, treat all errors uniformly and fail to account for the asymmetric consequences of high-risk semantic mistakes (e.g., incorrect runway identifiers or movement constraints). To address this gap, we propose a safety-oriented, consequence-aware evaluation framework tailored to ATC operations. Our results reveal that while current LLMs achieve reasonable aggregate accuracy, their operational reliability is severely limited. Evaluated on clean transcripts, the peak Risk Score reaches only 0.69, with most models scoring below 0.6 despite high macro-F1 performance. Further analysis shows that errors concentrate in high-impact entities despite relatively stable action-type classification, indicating structural grounding deficiencies. These findings highlight the necessity of consequence-aware evaluation protocols for the responsible deployment of AI-assisted ATC systems.

cs.CL↗

arXiv2026

Contrastive Regularization for Accent-Robust ASR

ASR systems based on self-supervised acoustic pretraining and CTC fine-tuning achieve strong performance on native speech but remain sensitive to accent variability. We investigate supervised contrastive learning (SupCon) as a lightweight, accent-invariant auxiliary objective for CTC fine-tuning. An utterance-level contrastive loss regularizes encoder representations without architectural modification or explicit accent supervision. Experiments on the L2-ARCTIC benchmark show consistent WER reductions across multiple pretrained encoders, with up to 25 -- 29\% relative reduction under unseen-accent evaluation. Analysis using within-transcript cosine dispersion indicates that SupCon promotes more compact and stable representation geometry under accent variability. Overall, SupCon provides an effective and model-agnostic regularization strategy for improving accent robustness.

cs.SD↗

arXiv2025

Do ATCOs Need Explanations, and Why? Towards ATCO-Centered Explainable AI for Conflict Resolution Advisories

Interest in explainable artificial intelligence (XAI) is surging. Prior research has primarily focused on systems' ability to generate explanations, often guided by researchers' intuitions rather than end-users' needs. Unfortunately, such approaches have not yielded favorable outcomes when compared to a black-box baseline (i.e., no explanation). To address this gap, this paper advocates a human-centered approach that shifts focus to air traffic controllers (ATCOs) by asking a fundamental yet overlooked question: Do ATCOs need explanations, and if so, why? Insights from air traffic management (ATM), human-computer interaction, and the social sciences were synthesized to provide a holistic understanding of XAI challenges and opportunities in ATM. Evaluating 11 ATM operational goals revealed a clear need for explanations when ATCOs aim to document decisions and rationales for future reference or report generation. Conversely, ATCOs are less likely to seek them when their conflict resolution approach align with the artificial intelligence (AI) advisory. While this is a preliminary study, the findings are expected to inspire broader and deeper inquiries into the design of ATCO-centric XAI systems, paving the way for more effective human-AI interaction in ATM.

cs.HC↗

arXiv2025

Evaluating Input Modalities for Pilot-Centered Taxiway Navigation: Insights from a Wizard-of-Oz Simulation

Runway and taxiway incursions continue to challenge aviation safety, as pilots often experience disorientation from poor visibility in adverse conditions and cognitive workload in complex airport layouts. Current tools, such as airport moving maps on portable tablets, allow manual route planning but do not dynamically adapt to air traffic controllers' (ATCOs) clearances, limiting their effectiveness in high-stress scenarios. This study investigates the impact of different input modalities - paper-based, keyboard touch, map touch, and speech-to-text - on taxiway navigation performance, using a medium-fidelity flight simulator and a Wizard-of-Oz methodology to simulate ideal automation conditions. Contrary to common assumptions, recent studies indicate that paper-based methods outperform digital counterparts in accuracy and efficiency under certain conditions, highlighting critical limitations in current automation strategies. In response, our study investigates why manual methods may excel and how future automation can be optimized for pilot-centered operations. Employing a Wizard-of-Oz approach, we replicated the full taxiing process - from receiving ATCO clearances to executing maneuvers - and differentiated between readback and execution accuracy. Findings reveal that speech-based systems suffer from low pilot trust, necessitating hybrid solutions that integrate error correction and confidence indicators. These insights contribute to the development of future pilot-centered taxiway assistance that enhance situational awareness, minimize workload, and improve overall operational safety.

cs.HC↗

arXiv2025

SaViD: Spectravista Aesthetic Vision Integration for Robust and Discerning 3D Object Detection in Challenging Environments

The fusion of LiDAR and camera sensors has demonstrated significant effectiveness in achieving accurate detection for short-range tasks in autonomous driving. However, this fusion approach could face challenges when dealing with long-range detection scenarios due to disparity between sparsity of LiDAR and high-resolution camera data. Moreover, sensor corruption introduces complexities that affect the ability to maintain robustness, despite the growing adoption of sensor fusion in this domain. We present SaViD, a novel framework comprised of a three-stage fusion alignment mechanism designed to address long-range detection challenges in the presence of natural corruption. The SaViD framework consists of three key elements: the Global Memory Attention Network (GMAN), which enhances the extraction of image features through offering a deeper understanding of global patterns; the Attentional Sparse Memory Network (ASMN), which enhances the integration of LiDAR and image features; and the KNNnectivity Graph Fusion (KGF), which enables the entire fusion of spatial information. SaViD achieves superior performance on the long-range detection Argoverse-2 (AV2) dataset with a performance improvement of 9.87% in AP value and an improvement of 2.39% in mAPH for L2 difficulties on the Waymo Open dataset (WOD). Comprehensive experiments are carried out to showcase its robustness against 14 natural sensor corruptions. SaViD exhibits a robust performance improvement of 31.43% for AV2 and 16.13% for WOD in RCE value compared to other existing fusion-based methods while considering all the corruptions for both datasets. Our code is available at \href{https://github.com/sanjay-810/SAVID}

eess.IV↗

arXiv2024

AYDIV: Adaptable Yielding 3D Object Detection via Integrated Contextual Vision Transformer

Combining LiDAR and camera data has shown potential in enhancing short-distance object detection in autonomous driving systems. Yet, the fusion encounters difficulties with extended distance detection due to the contrast between LiDAR's sparse data and the dense resolution of cameras. Besides, discrepancies in the two data representations further complicate fusion methods. We introduce AYDIV, a novel framework integrating a tri-phase alignment process specifically designed to enhance long-distance detection even amidst data discrepancies. AYDIV consists of the Global Contextual Fusion Alignment Transformer (GCFAT), which improves the extraction of camera features and provides a deeper understanding of large-scale patterns; the Sparse Fused Feature Attention (SFFA), which fine-tunes the fusion of LiDAR and camera details; and the Volumetric Grid Attention (VGA) for a comprehensive spatial data fusion. AYDIV's performance on the Waymo Open Dataset (WOD) with an improvement of 1.24% in mAPH value(L2 difficulty) and the Argoverse2 Dataset with a performance improvement of 7.40% in AP value demonstrates its efficacy in comparison to other existing fusion-based methods. Our code is publicly available at https://github.com/sanjay-810/AYDIV2

cs.CV↗

arXiv2024

Left-right Discrepancy for Adversarial Attack on Stereo Networks

Stereo matching neural networks often involve a Siamese structure to extract intermediate features from left and right images. The similarity between these intermediate left-right features significantly impacts the accuracy of disparity estimation. In this paper, we introduce a novel adversarial attack approach that generates perturbation noise specifically designed to maximize the discrepancy between left and right image features. Extensive experiments demonstrate the superior capability of our method to induce larger prediction errors in stereo neural networks, e.g. outperforming existing state-of-the-art attack methods by 219% MAE on the KITTI dataset and 85% MAE on the Scene Flow dataset. Additionally, we extend our approach to include a proxy network black-box attack method, eliminating the need for access to stereo neural network. This method leverages an arbitrary network from a different vision task as a proxy to generate adversarial noise, effectively causing the stereo network to produce erroneous predictions. Our findings highlight a notable sensitivity of stereo networks to discrepancies in shallow layer features, offering valuable insights that could guide future research in enhancing the robustness of stereo vision systems.

cs.CV↗

arXiv2022

Model Generalization in Arrival Runway Occupancy Time Prediction by Feature Equivalences

General real-time runway occupancy time prediction modelling for multiple airports is a current research gap. An attempt to generalize a real-time prediction model for Arrival Runway Occupancy Time (AROT) is presented in this paper by substituting categorical features by their numerical equivalences. Three days of data, collected from Saab Sensis' Aerobahn system at three US airports, has been used for this work. Three tree-based machine learning algorithms: Decision Tree, Random Forest and Gradient Boosting are used to assess the generalizability of the model using numerical equivalent features. We have shown that the model trained on numerical equivalent features not only have performances at least on par with models trained on categorical features but also can make predictions on unseen data from other airports.

cs.LG↗

arXiv2020

A Tunnel Gaussian Process Model for Learning Interpretable Flight's Landing Parameters

Approach and landing accidents have resulted in a significant number of hull losses worldwide. Technologies (e.g., instrument landing system) and procedures (e.g., stabilized approach criteria) have been developed to reduce the risks. In this paper, we propose a data-driven method to learn and interpret flight's approach and landing parameters to facilitate comprehensible and actionable insights into flight dynamics. Specifically, we develop two variants of tunnel Gaussian process (TGP) models to elucidate aircraft's approach and landing dynamics using advanced surface movement guidance and control system (A-SMGCS) data, which then indicates the stability of flight. TGP hybridizes the strengths of sparse variational Gaussian process and polar Gaussian process to learn from a large amount of data in cylindrical coordinates. We examine TGP qualitatively and quantitatively by synthesizing three complex trajectory datasets and compared TGP against existing methods on trajectory learning. Empirically, TGP demonstrates superior modeling performance. When applied to operational A-SMGCS data, TGP provides the generative probabilistic description of landing dynamics and interpretable tunnel views of approach and landing parameters. These probabilistic tunnel models can facilitate the analysis of procedure adherence and augment existing aircrew and air traffic controllers' displays during the approach and landing procedures, enabling necessary corrective actions.

cs.LG↗

arXiv2020

Deep4Air: A Novel Deep Learning Framework for Airport Airside Surveillance

An airport runway and taxiway (airside) area is a highly dynamic and complex environment featuring interactions between different types of vehicles (speed and dimension), under varying visibility and traffic conditions. Airport ground movements are deemed safety-critical activities, and safe-separation procedures must be maintained by Air Traffic Controllers (ATCs). Large airports with complicated runway-taxiway systems use advanced ground surveillance systems. However, these systems have inherent limitations and a lack of real-time analytics. In this paper, we propose a novel computer-vision based framework, namely "Deep4Air", which can not only augment the ground surveillance systems via the automated visual monitoring of runways and taxiways for aircraft location, but also provide real-time speed and distance analytics for aircraft on runways and taxiways. The proposed framework includes an adaptive deep neural network for efficiently detecting and tracking aircraft. The experimental results show an average precision of detection and tracking of up to 99.8% on simulated data with validations on surveillance videos from the digital tower at George Bush Intercontinental Airport. The results also demonstrate that "Deep4Air" can locate aircraft positions relative to the airport runway and taxiway infrastructure with high accuracy. Furthermore, aircraft speed and separation distance are monitored in real-time, providing enhanced safety management.

cs.CV↗

arXiv2020

An Incremental Clustering Method for Anomaly Detection in Flight Data

Safety is a top priority for civil aviation. New anomaly detection methods, primarily clustering methods, have been developed to monitor pilot operations and detect any risks from such flight data. However, all existing anomaly detection methods are offlline learning - the models are trained once using historical data and used for all future predictions. In practice, new flight data are accumulated continuously and analyzed every month at airlines. Clustering such dynamically growing data is challenging for an offlline method because it is memory and time intensive to re-train the model every time new data come in. If the model is not re-trained, false alarms or missed detections may increase since the model cannot reflect changes in data patterns. To address this problem, we propose a novel incremental anomaly detection method based on Gaussian Mixture Model (GMM) to identify common patterns and detect outliers in flight operations from digital flight data. It is a probabilistic clustering model of flight operations that can incrementally update its clusters based on new data rather than to re-cluster all data from scratch. It trains an initial GMM model based on historical offlline data. Then, it continuously adapts to new incoming data points via an expectation-maximization (EM) algorithm. To track changes in flight operation patterns, only model parameters need to be saved. The proposed method was tested on three sets of simulation data and two sets of real-world flight data. Compared with the traditional offline GMM method, the proposed method can generate similar clustering results with significantly reduced processing time (57 % - 99 % time reduction in testing sets) and memory usage (91 % - 95 % memory usage reduction in testing sets). Preliminary results indicate that the incremental learning scheme is effective in dealing with dynamically growing data in flight data analytics.

cs.LG↗