Yang Jiang

EAAI Journal 2026 Journal Article

Metal work-pieces sorting method based on the convolutional neural networks

• Xuejiao Zhang
• Yang Jiang

The intelligent sorting system of the metal parts is a crucial component to realize the intelligent manufacturing. In order to improve the efficiency and identification accuracy of this system and apply it in real production environment, this paper proposes a method for the classification and grasping detection of metal parts based on the convolutional neural networks. First, this paper produces the classification and grasping detection datasets, which contains the category labels and grasping model labels of nine kinds of metal parts. Second, this paper proposes the fast and lightweight classification network to realize the category prediction of metal parts and compare with the current mainstream methods. This network contributes significantly to the field of artificial intelligence. Third, we use the grasping detection network to realize the pixel-level capture detection on the image. Besides, this paper formulates the corresponding classification and grasping strategy to realize the sorting of objects, which can be applied to the engineering. Finally, the effectiveness and engineering practicability of the system are verified by the experiments on the robotic arm. The classification prediction accuracy is 99. 2 %, the grasping prediction accuracy is 99. 99 %, and the actual grasping accuracy is 95 %.

JBHI Journal 2025 Journal Article

Rethinking Data Augmentation for Single-Source Domain Generalization in OCT Image Segmentation

• Jiayi Lu
• Shaodong Ma
• Yonghuai Liu
• Yuhui Ma
• Lei Mou
• Yang Jiang
• Yitian Zhao

Domain shifts between samples acquired with different instruments are one of the major challenges in accurate segmentation of Optical Coherence Tomography (OCT) images. Given that OCT images may be acquired with different devices in different clinical centers, this study presents astyle and structure data augmentation (SSDA) method to improve the adaptability of segmentation models. Inspired by our initial analysis of OCT domain differences, we propose an innovative hypothesis that domain shifts are primarily due to differences in image style and anatomical structure, which further guides the design of our method. By designing a modality-specific NURBS curve for style enhancement and implementing global and local elastic deformation fields, SSDA addresses both stylistic and structural variations in OCT data. Global deformations simulate changes in retinal curvature, while local deformations model layer-specific changes observed in OCT images. We validate our hypothesis through a comprehensive evaluation conducted on five OCT data domains, each differing in device type and imaging conditions. We train models on each of these domains for single-domain generalisation experiments and evaluate performance on the remaining unseen domains. The results show that SSDA outperforms existing methods when segmenting OCT images from different sources with different requirements for retinal layer segmentation. Specifically, across five different source domain generalisation experiments, SSDA achieves approximately 1. 6% higher Dice and 2. 6% improved MIOU, underscoring its superior segmentation accuracy and robust generalisation across all evaluated unseen domains.

ECAI Conference 2025 Conference Paper

Subconscious Robotic Imitation Learning

• Jun Xie
• Zhicheng Wang
• Jianwei Tan
• Huanxu Lin
• Yang Jiang
• Xiaoguang Ma

While imitation learning (IL) emerges as a promising paradigm for embodied intelligent robots, its practical application is constrained by slow execution speeds, caused by the computational intensity of precise multi-model trajectory prediction, especially in complex dynamic environments. In contrast, humans can efficiently perform long-duration tasks through subconscious-driven habitual actions, such as riding bikes, without focusing on execution details. Motivated by this insight, we proposed Subconscious Robotic Imitation Learning (SRIL) framework, which mimicked the subconscious information extraction and decision-making abilities through intent-aware sampling and cognitive hierarchical reasoning, thereby significantly improving IL task execution efficiency. Experimental results demonstrated that execution speeds of the SRIL were 100% to 200% faster over SOTA policies for comprehensive bimanual tasks, with consistently higher success rates.

NeurIPS Conference 2024 Conference Paper

DiffLight: A Partial Rewards Conditioned Diffusion Model for Traffic Signal Control with Missing Data

• Hanyang Chen
• Yang Jiang
• Shengnan Guo
• Xiaowei Mao
• Youfang Lin
• Huaiyu Wan

The application of reinforcement learning in traffic signal control (TSC) has been extensively researched and yielded notable achievements. However, most existing works for TSC assume that traffic data from all surrounding intersections is fully and continuously available through sensors. In real-world applications, this assumption often fails due to sensor malfunctions or data loss, making TSC with missing data a critical challenge. To meet the needs of practical applications, we introduce DiffLight, a novel conditional diffusion model for TSC under data-missing scenarios in the offline setting. Specifically, we integrate two essential sub-tasks, i. e. , traffic data imputation and decision-making, by leveraging a Partial Rewards Conditioned Diffusion (PRCD) model to prevent missing rewards from interfering with the learning process. Meanwhile, to effectively capture the spatial-temporal dependencies among intersections, we design a Spatial-Temporal transFormer (STFormer) architecture. In addition, we propose a Diffusion Communication Mechanism (DCM) to promote better communication and control performance under data-missing scenarios. Extensive experiments on five datasets with various data-missing scenarios demonstrate that DiffLight is an effective controller to address TSC with missing data. The code of DiffLight is released at https: //github. com/lokol5579/DiffLight-release.

YNIMG Journal 2015 Journal Article

Influence of neurobehavioral incentive valence and magnitude on alcohol drinking behavior

• Jane E. Joseph
• Xun Zhu
• Christine R. Corbly
• Stacia DeSantis
• Dustin C. Lee
• Grace Baik
• Seth Kiser
• Yang Jiang

The monetary incentive delay (MID) task is a widely used probe for isolating neural circuitry in the human brain associated with incentive motivation. In the present functional magnetic resonance imaging (fMRI) study, 82 young adults, characterized along dimensions of impulsive sensation seeking, completed a MID task. fMRI and behavioral incentive functions were decomposed into incentive valence and magnitude parameters, which were used as predictors in linear regression to determine whether mesolimbic response is associated with problem drinking and recent alcohol use. Alcohol use was best explained by higher fMRI response to anticipation of losses and feedback on high gains in the thalamus. In contrast, problem drinking was best explained by reduced sensitivity to large incentive values in mesolimbic regions in the anticipation phase and increased sensitivity to small incentive values in the dorsal caudate nucleus in the feedback phase. Altered fMRI responses to monetary incentives in mesolimbic circuitry, particularly those alterations associated with problem drinking, may serve as potential early indicators of substance abuse trajectories.

YNICL Journal 2015 Journal Article

Sugihara causality analysis of scalp EEG for detection of early Alzheimer's disease

• Joseph C. McBride
• Xiaopeng Zhao
• Nancy B. Munro
• Gregory A. Jicha
• Frederick A. Schmitt
• Richard J. Kryscio
• Charles D. Smith
• Yang Jiang

Recently, Sugihara proposed an innovative causality concept, which, in contrast to statistical predictability in Granger sense, characterizes underlying deterministic causation of the system. This work exploits Sugihara causality analysis to develop novel EEG biomarkers for discriminating normal aging from mild cognitive impairment (MCI) and early Alzheimer's disease (AD). The hypothesis of this work is that scalp EEG based causality measurements have different distributions for different cognitive groups and hence the causality measurements can be used to distinguish between NC, MCI, and AD participants. The current results are based on 30-channel resting EEG records from 48 age-matched participants (mean age 75.7 years) - 15 normal controls (NCs), 16 MCI, and 17 early-stage AD. First, a reconstruction model is developed for each EEG channel, which predicts the signal in the current channel using data of the other 29 channels. The reconstruction model of the target channel is trained using NC, MCI, or AD records to generate an NC-, MCI-, or AD-specific model, respectively. To avoid over fitting, the training is based on the leave-one-out principle. Sugihara causality between the channels is described by a quality score based on comparison between the reconstructed signal and the original signal. The quality scores are studied for their potential as biomarkers to distinguish between the different cognitive groups. First, the dimension of the quality scores is reduced to two principal components. Then, a three-way classification based on the principal components is conducted. Accuracies of 95.8%, 95.8%, and 97.9% are achieved for resting eyes open, counting eyes closed, and resting eyes closed protocols, respectively. This work presents a novel application of Sugihara causality analysis to capture characteristic changes in EEG activity due to cognitive deficits. The developed method has excellent potential as individualized biomarkers in the detection of pathophysiological changes in early-stage AD.

YNIMG Journal 2012 Journal Article

Individual differences in cognition, affect, and performance: Behavioral, neuroimaging, and molecular genetic approaches

• Raja Parasuraman
• Yang Jiang

We describe the use of behavioral, neuroimaging, and genetic methods to examine individual differences in cognition and affect, guided by three criteria: (1) relevance to human performance in work and everyday settings; (2) interactions between working memory, decision-making, and affective processing; and (3) examination of individual differences. The results of behavioral, functional MRI (fMRI), event-related potential (ERP), and molecular genetic studies show that analyses at the group level often mask important findings associated with sub-groups of individuals. Dopaminergic/noradrenergic genes influencing prefrontal cortex activity contribute to inter-individual variation in working memory and decision behavior, including performance in complex simulations of military decision-making. The interactive influences of individual differences in anxiety, sensation seeking, and boredom susceptibility on evaluative decision-making can be systematically described using ERP and fMRI methods. We conclude that a multi-modal neuroergonomic approach to examining brain function (using both neuroimaging and molecular genetics) can be usefully applied to understanding individual differences in cognition and affect and has implications for human performance at work.

YNIMG Journal 2000 Journal Article

Electrophysiological effects of visual motion priming in young and old

• Yuejia Luo
• Yang Jiang
• Catalina Lawsin
• Raja Parasuraman