Novel Dynamic Batch-Sensitive Adam Optimiser for Vehicular Accident Injury Severity Prediction

• URL: http://arxiv.org/abs/2605.15083v1
• Date: Thu, 14 May 2026 17:06:43 GMT
• Title: Novel Dynamic Batch-Sensitive Adam Optimiser for Vehicular Accident Injury Severity Prediction
• Abstract summary: We propose Dynamic Batch-Sensitive Adam (DBS-Adam) as an optimiser for learning from imbalanced datasets.<n>DBS-Adam dynamically scales the learning rate using a batch difficulty score derived from exponential moving averages of gradient norms and batch loss.<n>It achieves 95.22% test accuracy, 96.11% precision, 95.28% recall, 95.39% F1-score, and a test loss of 0.0086.
• Score: 0.0
• License: http://arxiv.org/licenses/nonexclusive-distrib/1.0/
• Abstract: The choice of optimiser is important in deep learning, as it strongly influences model efficiency and speed of convergence. However, many commonly used optimisers encounter difficulties when applied to imbalanced and sequential datasets, limiting their ability to capture patterns of minority classes. In this study, we propose Dynamic Batch-Sensitive Adam (DBS-Adam), an optimiser that dynamically scales the learning rate using a batch difficulty score derived from exponential moving averages of gradient norms and batch loss. DBS-Adam improves training stability and accelerates convergence by increasing updates for difficult batches and reducing them for easier ones. We evaluate DBS-Adam by integrating it with Bi-Directional LSTM networks for accident injury severity prediction, addressing class imbalance through SMOTE-ENN resampling and Focal Loss. Four experimental configurations compare baseline Bi-LSTM models and alternative architectures to assess optimiser impact. Rigorous comparison against state-of-the-art optimisers (AMSGrad, AdamW, AdaBound) across five random seeds demonstrated DBS-Adam's competitive performance with statistically significant precision improvements (p=0.020). Results indicate that DBS-Adam outperforms standard optimisation approaches, achieving 95.22% test accuracy, 96.11% precision, 95.28% recall, 95.39% F1-score, and a test loss of 0.0086. The proposed framework enables effective real-time accident severity classification for targeted emergency response and road safety interventions, demonstrating the value of DBS-Adam for learning from imbalanced sequential data.

Related papers

• Towards reliable multimodal disaster severity assessment through preference optimization and explainable vision-language reasoning [2.5428307120715634]
  This study proposes a two-stage training framework that integratesSupervised Fine-Tuning (SFT) and Direct Preference Optimization (DPO)<n>It evaluates both classification performance and explanation quality using automatic metrics, model-based scoring, and human ranking.<n> Experimental results show that SFT improves accuracy from 73.64% to 78.29% and increases Macro-F1 by 29% compared to the baseline.
  arXiv  Detail & Related papers  (2026-09-01T08:11:09Z)
• Boundary-Seeking GAN-Augmented TabTransformer for Adversarially Robust Intrusion Detection [0.0]
  This study proposes a TabTransformer framework augmented by the Boundary-Seeking Generative Adrial Network (BGAN) for flow-based intrusion detection.<n>BGAN serves a dual purpose by generating synthetic minority-class samples to mitigate data imbalance and produce adversarial samples to evaluate modelversa.<n> Experimental results demonstrate that BGAN augmentation improves TabTransformer's Macro-F1 score from 82.96% to 86.50%.
  arXiv  Detail & Related papers  (2026-07-17T00:35:52Z)
• Rewarding the Scientific Process: Process-Level Reward Modeling for Agentic Data Analysis [68.28714988482703]
  Process Reward Models (PRMs) have achieved remarkable success in augmenting the reasoning capabilities of Large Language Models (LLMs)<n>We present a study revealing that general-domain PRMs struggle to supervise data analysis agents.<n>We introduce DataPRM, a novel environment-aware generative process reward model.
  arXiv  Detail & Related papers  (2026-04-27T09:00:30Z)
• Personalized Fall Detection by Balancing Data with Selective Feedback Using Contrastive Learning [3.579200789027982]
  We propose a personalization framework that combines semi-supervised clustering with contrastive learning to identify and balance user feedback samples.<n>The framework is evaluated under three retraining strategies, including Training from Scratch (TFS), Transfer Learning (TL), and FewShot Learning.
  arXiv  Detail & Related papers  (2026-03-17T21:22:21Z)
• Rethinking Adam for Time Series Forecasting: A Simple Heuristic to Improve Optimization under Distribution Shifts [1.8022002874089529]
  Time-series forecasting often faces challenges from distributional drift.<n>This dynamic behavior can undermine the effectiveness of adaptive landscapes, such as Adam.<n>We propose TS_Adam, a lightweight variant that removes the second-order correction from the learning rate.
  arXiv  Detail & Related papers  (2026-03-10T16:31:02Z)
• Identifying and Transferring Reasoning-Critical Neurons: Improving LLM Inference Reliability via Activation Steering [50.63386303357225]
  We propose AdaRAS, a lightweight test-time framework that improves reasoning reliability by selectively intervening on neuron activations.<n>AdaRAS identifies Reasoning-Critical Neurons (RCNs) via a polarity-aware mean-difference criterion and adaptively steers their activations during inference.<n> Experiments on 10 mathematics and coding benchmarks demonstrate consistent improvements, including over 13% gains on AIME-24 and AIME-25.
  arXiv  Detail & Related papers  (2026-01-27T17:53:01Z)
• Ustnlp16 at SemEval-2025 Task 9: Improving Model Performance through Imbalance Handling and Focal Loss [38.70308073598037]
  classification tasks often suffer from severe class imbalances, short and unstructured text, and overlapping semantic categories.<n>We present our system for SemEval- 2025 Task 9: Food Hazard Detection, which ad- dresses these issues by applying data augmenta- tion techniques to improve classification perfor- mance.
  arXiv  Detail & Related papers  (2025-04-24T16:35:44Z)
• Dynamic Noise Preference Optimization for LLM Self-Improvement via Synthetic Data [51.62162460809116]
  We introduce Dynamic Noise Preference Optimization (DNPO) to ensure consistent improvements across iterations.<n>In experiments with Zephyr-7B, DNPO consistently outperforms existing methods, showing an average performance boost of 2.6%.<n> DNPO shows a significant improvement in model-generated data quality, with a 29.4% win-loss rate gap compared to the baseline in GPT-4 evaluations.
  arXiv  Detail & Related papers  (2025-02-08T01:20:09Z)
• Survival Analysis with Adversarial Regularization [3.9686445409447617]
  Survival Analysis (SA) models the time until an event occurs, with applications in fields like medicine, defense, finance, and aerospace.<n>Recent research indicates that Neural Networks (NNs) can effectively capture complex data patterns in SA.<n>We leverage advances in NN verification to develop training objectives for robust, fully-parametric SA models.
  arXiv  Detail & Related papers  (2023-12-26T12:18:31Z)
• Breaking Boundaries: Balancing Performance and Robustness in Deep Wireless Traffic Forecasting [11.029214459961114]
  Balancing the trade-off between accuracy and robustness is a long-standing challenge in time series forecasting. We study a wide array of perturbation scenarios and propose novel defense mechanisms against adversarial attacks using real-world telecom data.
  arXiv  Detail & Related papers  (2023-11-16T11:10:38Z)
• Robust Trajectory Prediction against Adversarial Attacks [84.10405251683713]
  Trajectory prediction using deep neural networks (DNNs) is an essential component of autonomous driving systems. These methods are vulnerable to adversarial attacks, leading to serious consequences such as collisions. In this work, we identify two key ingredients to defend trajectory prediction models against adversarial attacks.
  arXiv  Detail & Related papers  (2022-07-29T22:35:05Z)
• Scale-Equivalent Distillation for Semi-Supervised Object Detection [57.59525453301374]
  Recent Semi-Supervised Object Detection (SS-OD) methods are mainly based on self-training, generating hard pseudo-labels by a teacher model on unlabeled data as supervisory signals. We analyze the challenges these methods meet with the empirical experiment results. We introduce a novel approach, Scale-Equivalent Distillation (SED), which is a simple yet effective end-to-end knowledge distillation framework robust to large object size variance and class imbalance.
  arXiv  Detail & Related papers  (2022-03-23T07:33:37Z)
• Bootstrapping Your Own Positive Sample: Contrastive Learning With Electronic Health Record Data [62.29031007761901]
  This paper proposes a novel contrastive regularized clinical classification model. We introduce two unique positive sampling strategies specifically tailored for EHR data. Our framework yields highly competitive experimental results in predicting the mortality risk on real-world COVID-19 EHR data.
  arXiv  Detail & Related papers  (2021-04-07T06:02:04Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.