Author name cluster

Jialin Wang

Possible papers associated with this exact author name in Arrow. This page groups case-insensitive exact name matches and is not a full identity disambiguation profile.

6 papers

1 author row

EAAI Journal 2025 Journal Article

A physical information guided method for bridge underwater crack detection based on two-stage pre-training learning with scarce samples

Shuai Teng
Airong Liu
Junchao Yang
Zuxiang Situ
Bingcong Chen
Jialin Wang
Zhihua Wu
Jiyang Fu

This paper proposes an innovative two-stage pre-training learning method guided by physical information for automatic detection of bridge underwater cracks under scarce sample conditions. Addressing the critical challenges of limited training data and complex underwater environmental interference, this paper uniquely integrates transfer learning with domain-specific physical insights to enhance detection accuracy. The key contributions include: (1) A novel two-stage pre-training framework that sequentially learns underwater environmental features from a large-scale dataset and crack-specific features from terrestrial crack images, effectively bridging domain gaps while preserving discriminative characteristics; (2) A physics-guided DeepLabv3+ architecture enhanced with skip connections, Convolutional block attention module (CBAM), and a hybrid Tversky-Dice loss function to address class imbalance and boundary ambiguity in turbid underwater conditions; (3) First-time integration of local standard deviation maps as physical guidance to amplify crack-related intensity variations, enabling precise segmentation even with minimal annotated samples. Experimental results demonstrate state-of-the-art performance, achieving an accuracy of 96. 57 %, a mean IoU (Intersection over Union) of 0. 95, and an F1-Score of 0. 96, outperforming baseline methods by 10. 8 % in accuracy and 0. 43 in IoU. The method's robustness is further validated against some mainstream segmentation models, showing significant advantages in both precision and computational efficiency. This work provides a paradigm for infrastructure health monitoring in data-scarce, environmentally challenging scenarios.

Details DOI

EAAI Journal 2025 Journal Article

Quantization-based deep diversified ensemble for medical image segmentation

Jiawei Zhang
Jialin Wang
Qi Wang
Yanchun Zhang
Weihong Han
Yangyang Mei
Yiyu Shi
Jian Zhuang

Recent advancements in fully convolutional networks (FCNs) have significantly improved medical image segmentation. Ensemble methods are often used to further enhance performance, with diversity among learners being a critical factor. However, many current approaches focus on diversifying training samples or predictions while overlooking the diversity of internal multi-scale features. This oversight can lead to high correlations among features across different learners, limiting overall effectiveness. Additionally, traditional quantization methods aim to minimize accuracy loss by maintaining a rigid quantization process. This rigidity can eliminate the randomness introduced by quantization, further reducing ensemble diversity and effectiveness. In this paper, we propose a novel approach called Quantization-based Deep Diversified Ensemble (QDD-Ens) for medical image segmentation. Our method enhances the diversity of internal features among ensemble learners through two mechanisms: deep diversified loss, which focuses on feature diversity rather than segmentation accuracy, and deep diversified quantization, which preserves beneficial randomness in quantization process. Furthermore, QDD-Ens facilitates a deeper form of ensemble learning by employing a meta-learner to integrate diversified features at multiple resolution levels from various base learners, which are diversified by two above diversify enhancement mechanisms. Extensive experiments on five public medical image segmentation datasets show that our method significantly improves segmentation accuracy and outperforms existing ensemble techniques. The source code is publicly available to support future research. (https: //github. com/JerRuy/QDD-Ens)

Details DOI

JBHI Journal 2025 Journal Article

SyncLearnNet: Generalized Epileptic Seizure Detection Network Based on Brain Signals

Yuer Ma
Jialin Wang
Jiaoyang Wang
Wenxiong Kang
Xiaofeng Yang

Epilepsy is a prevalent neurological disorder with significant detrimental effects on health. Accurate seizure detection is crucial for the precise diagnosis and effective treatment of epilepsy. Brain signals is widely recognized as a reliable clinical tool for diagnosing and evaluating severity of seizures. Traditionally, medical researchers have relied on visual inspection to identify and locate seizures and epileptogenic areas. However, manual analysis of brain data is both subjective and time-consuming. In recent years, there has been a surge in studies focusing on automatic seizure detection algorithms based on brain signals, driven by the advancements in artificial intelligence and digital brain signal technology. Nevertheless, in tackling this task, many of these studies have neglected to leverage the rich implicit information of samples to extract comprehensive feature representation for enhancing model performance. To address this gap, we propose a generalized model called SyncLearnNet for seizure detection based on brain signals. SyncLearnNet incorporates VariaScan and BatchAttention modules designed to fully utilize both intra-sample and inter-sample information, thereby improving feature discrimination without requiring additional data. Furthermore, the introduction of CurriClassifier aims to enhance the model's generalization performance. Experiments conducted on a public human seizure dataset CHB-MIT and a self-built animal seizure dataset comprising data from five rats demonstrated this method outperforms existing seizure detection methods in terms of generalization performance.

Details DOI

EAAI Journal 2024 Journal Article

Unsupervised learning method for underwater concrete crack image enhancement and augmentation based on cross domain translation strategy

Shuai Teng
Airong Liu
Bingcong Chen
Jialin Wang
Zhihua Wu
Jiyang Fu

In response to the challenges of low clarity and insufficient training samples in underwater concrete crack detection, this paper proposes an improved unsupervised learning method for the underwater concrete crack image enhancement (increase image quality) and augmentation (increase in number of images). Detecting structural defects underwater is vital for ensuring the proper functioning of underwater structures. However, the harsh underwater environment often leads to low-resolution images of concrete cracks, which in turn diminishes detection accuracy. Additionally, the challenges associated with underwater image collection make it difficult to gather an ample number of samples for training deep learning models to effectively detect these defects. Therefore, this paper proposes an unsupervised learning model that can simultaneously enhance and augment underwater concrete crack images in order to achieve better detection results. For the enhancement of underwater concrete crack images, the proposed method significantly improves the recognizability of images in turbid water environments and exhibits significant superiority compared to other similar methods, the values of the three evaluation indicators decreased by 45. 2%, 40. 4%, and 69. 1%, respectively. Regarding the augmentation of underwater concrete crack images, the proposed method can translate images from clear water and waterless environments to muddy water environments. Compared to other methods, improved image quality by at least 61. 2%, the proposed method generates images with better authenticity. This validates that the proposed cross domain translation strategy can simultaneously enhancing and augmenting underwater concrete crack images.

Details DOI

YNICL Journal 2019 Journal Article

Non-pharmacological and pharmacological interventions relieve insomnia symptoms by modulating a shared network: A controlled longitudinal study

Fen Feng
Siyi Yu
Zhengyan Wang
Jialin Wang
Joel Park
Georgia Wilson
Mou Deng
Youping Hu

BACKGROUND: Primary insomnia (PI) is one of the most common complaints among the general population. Both non-pharmacological and pharmacological therapies have proven effective in treating primary insomnia. However, the underlying mechanism of treatment remains unclear, and no studies have compared the underlying mechanisms of different treatments. METHODS: In this study, we investigated gray matter volume (GMV) and resting-state functional connectivity (rsFC) changes following both pharmacological and non-pharmacological treatments in patients with PI. A total of 67 PI patients were randomized into benzodiazepine treatment, cupping treatment, or a wait-list control group for 4 weeks. The Pittsburgh Sleep Quality Index (PSQI), gray matter volume (GMV), and resting-state functional connectivity (rsFC) of the hippocampus were measured at the beginning and end of the experiment. RESULTS: We found 1) significantly decreased PSQI scores in the cupping and benzodiazepine treatment groups compared to the control group with no significant differences between the two treatment groups; 2) significant GMV increases in the cupping group compared to the control group at the right hippocampus after 4 weeks of treatment; 3) significantly increased rsFC between the right hippocampus and left rostral anterior cingulate cortex/medial prefrontal cortex (rACC/mPFC) in the two treatment groups, which was significantly associated with PSQI score decreases. DISCUSSION: Our findings suggest that benzodiazepine and cupping may share a common mechanism to relieve the symptoms of patients with PI.

Details DOI

AAAI Conference 2018 Conference Paper

GraphGAN: Graph Representation Learning With Generative Adversarial Nets

Hongwei Wang
Jia Wang
Jialin Wang
Miao Zhao
Weinan Zhang
Fuzheng Zhang
Xing Xie
Minyi Guo

The goal of graph representation learning is to embed each vertex in a graph into a low-dimensional vector space. Existing graph representation learning methods can be classiﬁed into two categories: generative models that learn the underlying connectivity distribution in the graph, and discriminative models that predict the probability of edge existence between a pair of vertices. In this paper, we propose Graph- GAN, an innovative graph representation learning framework unifying above two classes of methods, in which the generative model and discriminative model play a game-theoretical minimax game. Speciﬁcally, for a given vertex, the generative model tries to ﬁt its underlying true connectivity distribution over all other vertices and produces “fake” samples to fool the discriminative model, while the discriminative model tries to detect whether the sampled vertex is from ground truth or generated by the generative model. With the competition between these two models, both of them can alternately and iteratively boost their performance. Moreover, when considering the implementation of generative model, we propose a novel graph softmax to overcome the limitations of traditional softmax function, which can be proven satisfying desirable properties of normalization, graph structure awareness, and computational efﬁciency. Through extensive experiments on real-world datasets, we demonstrate that Graph- GAN achieves substantial gains in a variety of applications, including link prediction, node classiﬁcation, and recommendation, over state-of-the-art baselines.

PDF Details