Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2510.26203

An Intelligent Multi-task Supply Chain Model Based on Bio-inspired Networks

Mehdi Khaleghi·Sobhan Sheykhivand·Nastaran Khaleghi·Sebelan Danishvar
View original source ↗Read source document ↗Export metadata ↓

Abstract

The sustainability of supply chain plays a key role in achieving optimal performance in controlling the supply chain. The management of risks that occur in a supply chain is a fundamental problem for the purpose of developing the sustainability of the network and elevating the performance efficiency of the supply chain. The correct classification of products is another essential element in a sustainable supply chain. Acknowledging recent breakthroughs in the context of deep networks, several architectural options have been deployed to analyze supply chain datasets. A novel geometric deep network is used to propose an ensemble deep network. The proposed Chebyshev ensemble geometric network (Ch-EGN) is a hybrid convolutional and geometric deep learning. This network is proposed to leverage the information dependencies in supply chain to derive invisible states of samples in the database. The functionality of the proposed deep network is assessed on the two different databases. The SupplyGraph Dataset and DataCo are considered in this research. The prediction of delivery status of DataCo supply chain is done for risk administration. The product classification and edge classification are performed using the SupplyGraph database to enhance the sustainability of the supply network. An average accuracy of 98.95% is obtained for the ensemble network for risk management. The average accuracy of 100% and 98.07% are obtained for sustainable supply chain in terms of 5 product group classification and 4 product relation classification, respectively. The average accuracy of 92.37% is attained for 25 company relation classification. The results confirm an average improvement and efficiency of the proposed method compared to the state-of-the-art approaches.

Explore related subjects

cs.CV

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Mehdi Khaleghi, Sobhan Sheykhivand, Nastaran Khaleghi, Sebelan Danishvar. 2026-02-06. An Intelligent Multi-task Supply Chain Model Based on Bio-inspired Networks. https://doi.org/10.3390/biomimetics11020123

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

SSP-GNN: Learning to Track via Bilevel Optimization

We propose a graph-based tracking formulation for multi-object tracking (MOT) where target detections contain kinematic information and re-identification features (attributes). Our method applies a successive shortest paths (SSP) algorithm to a tracking graph defined over a batch of frames. The edge costs in this tracking graph are computed via a message-passing network, a graph neural network (GNN) variant. The parameters of the GNN, and hence, the tracker, are learned end-to-end on a training set of example ground-truth tracks and detections. Specifically, learning takes the form of bilevel optimization guided by our novel loss function. We evaluate our algorithm on simulated scenarios to understand its sensitivity to scenario aspects and model hyperparameters. Across varied scenario complexities, our method compares favorably to a strong baseline.

cs.CV↗
arXiv2026

AdaptiveCDM: Source-Free Few-Shot Domain Adaptation for Cell Detection in Microscopic Images

Cross-domain cell detection for microscopic images suffers from performance degradation due to distribution shifts across imaging domains. Unsupervised Domain Adaptation (UDA) strategies, attempt to overcome domain sift without requiring annotated data from target. However, requirement of availability of annotated data from the source domain and large-size data from target domain are both challenging limitations for realistic scenarios. This is especially true in medical imaging, where privacy requirements might prevent access to annotated source data, and costly data acquisition restricts extensive sampling of the target domain. To address these challenges, we propose AdaptiveCDM, a modular framework for Source-Free Few-Shot Domain Adaptive Object Detection (SF-FSDAOD) setting, that adapts a pretrained source model using only few labeled target images without accessing source data. AdaptiveCDM combines Resolution-Aware Augmentation (RAug) and Category-Aware Representation Learning (CARL). RAug alleviates the scarcity and class imbalance by augmenting instance balanced training examples, while preserving the scale fidelity and morphological properties of cellular structures. CARL enhances discriminative representation learning by encouraging class-consistent proposals, improving both localization and classification. We also introduce two competitive baselines for proposed setting: Faster-FreeShot and MT-FreeShot. Our approach achieves 40.4/43.4 mAP0.5 on M5 and 67.1/75.5 mAP0.5 on Raabin-WBC under 2-/5-shot adaptation. Despite using only a few labeled target images and no source data, AdaptiveCDM achieves competitive or superior performance compared with SOTA methods under their respective supervision settings. Ablations and qualitative analyses further substantiate the contribution of each component and the effectiveness of AdaptiveCDM in low-data regimes. Code/models will be available.

cs.CV↗
arXiv2026

Uncertainty-Weighted Fusion of Image and Synthetic Event for Video Anomaly Detection

Most existing video anomaly detectors rely on RGB frames alone, which limit their ability to capture abrupt or transient motion cues that are critical for identifying anomalous events. We propose Uncertainty Weighted Image Event Fusion (IEF-VAD), a framework that integrates complementary RGB and synthetic motion information through a principled weighting mechanism. The method models the high variance and heavy tailed characteristics of synthetic motion cues with a Student's t likelihood, computes value level inverse variance weights using a Laplace approximation to prevent the image modality from overshadowing motion information, and performs iterative refinement to suppress residual cross modal noise. This formulation provides a more balanced and reliable fusion process compared to cross attention or gating based approaches that often suffer from modality dominance. Without requiring an event camera or frame level annotations, IEF-VAD achieves new state of the art performance on multiple real world anomaly detection benchmarks and remains stable under degradation applied to individual modalities. The results indicate that extracting and integrating complementary motion cues is an effective direction for robust video understanding across diverse environments.

cs.CV↗