检索结果-内蒙古大学图书馆

Mixed reality based respiratory liver tumor puncture navigation

学校读者我要写书评

暂无评论

Computational Visual Media 2019年第4期5卷 363-374页

作者： Ruotong Li Weixin Si Xiangyun Liao Qiong Wang Reinhard Klein Pheng-Ann Heng Institute of Computer Science II University of Bonn53115 BonnGermany Shenzhen Key Laboratory of Virtual Reality and Human Interaction Technology Shenzhen Institutes of Advanced TechnologyChinese Academy of SciencesChina Department of Computer Science and Engineering Chinese University of Hong KongHong KongChina

This paper presents a novel mixed reality based navigation system for accurate respiratory liver tumor punctures in radiofrequency ablation(RFA).Our system contains an optical see-through head-mounted display device(OST-HMD),Microsoft Holo Lens for perfectly overlaying the virtual information on the patient,and a optical tracking system NDI Polaris for calibrating the surgical utilities in the surgical *** with traditional navigation method with CT,our system aligns the virtual guidance information and real patient and real-timely updates the view of virtual guidance via a position tracking *** addition,to alleviate the difficulty during needle placement induced by respiratory motion,we reconstruct the patientspecific respiratory liver motion through statistical motion model to assist doctors precisely puncture liver *** proposed system has been experimentally validated on vivo pigs with an accurate real-time registration approximately 5-mm mean FRE and TRE,which has the potential to be applied in clinical RFA guidance.

关键词： mixed reality human computer interaction statistical motion model

The comparison of EEG features in specific Mandarin words’ speech

学校读者我要写书评

暂无评论

The comparison of EEG features in specific Mandarin words’ ...

International Conference on Fuzzy Theory and it's Applications (iFUZZY)

作者： Wen-Shan Tsai Syue-Guan Huang Kuan-Chih Huang Jung-Chih Chen Chin-Teng Lin Institute of Biomedical Engineering College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan Department of Electronics and Electrical Engineering College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan Brain Science and Technology Center College of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu Taiwan Human-Centric AI Centre (HAI) Faculty of Engineering and Information Technology University of Technology Sydney Ultimo NSW Australia

Due to advancements in brain signal application technology, there has been a growing focus on the human speech Brain-computer Interface (BCI) in recent years. An essential initial phase in crafting speech recognition systems is comprehending the inherent features of nature speech processing. To ensure the decoding capability of human speech BCI, researchers have to investigate the differences between overt speech and imagined speech, and they also need to find the best paradigm to build a reliable BCI. Thus, this study compared the differences in brain dynamics between overt speech and imagined speech while using the four Mandarin words "上" (up), "下" (down), "左" (left), and "右" (right). We first calculated the EEG alpha and beta band power for multiple channels situated in the regions of Broca's and Wernicke's areas (specifically F5, F7, FC3, FC5, and C5), to analyze the brain activity changes while speaking or imagining speech. Second, we used Daubechies 4 (db4) wavelet to do a 7-level decomposition to the EEG signal. The corresponding discrete wavelet transform (DWT) coefficients were further calculated with six statistical features for support vector machine (SVM) classification. We found that the "speak (overt speech)" task and the "imagine (imagined speech)" task resulted in significantly different alpha band power changes, and the beta band shows the same phenomenon. The result of average classification accuracy is 71.97% for "speak" and "imagine" distinction. In conclusion, we analyzed the brain dynamics and find that overt speech and imagined speech could be differentiate through DWT coefficients features. This may pave the way to establish a Mandarin imagined speech BCI.

关键词：

Correlation-Distance Graph Learning for Treatment Response Prediction from rs-fMRI

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Zhang, Xiatan Zheng, Sisi Shum, Hubert P.H. Zhang, Haozheng Song, Nan Song, Mingkang Jia, Hongxiao Beijing Key Laboratory of Mental Disorders National Clinical Research Center for Mental Disorders National Center for Mental Disorders Beijing Anding Hospital Capital Medical University Beijing China Advanced Innovation Center for Human Brain Protection Beijing Anding Hospital Capital Medical University Beijing China Department of Computer Science Durham University Durham United Kingdom

Resting-state fMRI (rs-fMRI) functional connectivity (FC) analysis provides valuable insights into the relationships between different brain regions and their potential implications for neurological or psychiatric disorders. However, specific design efforts to predict treatment response from rs-fMRI remain limited due to difficulties in understanding the current brain state and the underlying mechanisms driving the observed patterns, which limited the clinical application of rs-fMRI. To overcome that, we propose a graph learning framework that captures comprehensive features by integrating both correlation and distance-based similarity measures under a contrastive loss. This approach results in a more expressive framework that captures brain dynamic features at different scales and enables more accurate prediction of treatment response. Our experiments on the chronic pain and depersonalization disorder datasets demonstrate that our proposed method outperforms current methods in different scenarios. To the best of our knowledge, we are the first to explore the integration of distance-based and correlation-based neural similarity into graph learning for treatment response prediction. © 2023, CC BY.

关键词： Forecasting

No Fear of Representation Bias Graph Contrastive Learning with Calibration and Fusion

学校读者我要写书评

暂无评论

SSRN

SSRN 2024年

作者： Li, Jindong Liu, Yixin Xing, Qianli Wang, Qi Pan, Shirui The School of Artificial Intelligence Jilin University Changchun130012 China The Department of Data Science and AI Monash University MelbourneVIC3800 Australia The College of Computer Science and Technology Jilin University Changchun130012 China The School of Information and Communication Technology Griffith University Gold CoastQLD4222 Australia Engineering Research Center of Knowledge-Driven Human-Machine Intelligence Ministry of Education China

Graph contrastive learning (GCL) is receiving growing attention due to its promising self-supervised learning capability on graph-structured data. While GCL approaches have demonstrated significant potential, their inherited stochastic perturbation-based augmentation causes the representation bias on representation hyperspace. Such a serious issue, unfortunately, causes the representation drift between the distributions of original and augmented embeddings, misleading the contrastive training for the graph neural network encoders. Moreover, the information loss caused by bias can further result in incomplete representation problem, hindering the self-supervised framework from capturing comprehensive structural and attributive patterns. To address these challenges, this paper introduces the CAlibratioN aNd FusiON model (CANNON for short). CANNON introduces a cross-view calibrating contrast mechanism to enhance the agreement between the original and augmented representations, which effectively alleviates the representation drift. Concurrently, CANNON overcomes the incomplete representation problem with a fused-view calibrating contrast mechanism for contrastive learning application on the fused embeddings, where a transformer-based cross-view fusion block is used to integrate two augmented views into a comprehensive one. The extensive experimental results, executed on 9 real-world datasets, demonstrate that CANNON significantly outperforms existing state-of-the-art methods. The code is available at https://***/jindongli-Ai/CANNON. © 2024, The Authors. All rights reserved.

关键词： Calibration

Transfer learning to improve streamflow forecasts in data sparse regions

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Oruche, Roland Egede, Lisa Baker, Tracy O'Donncha, Fearghal Department of Electrical Engineering & Computer Science University of Missouri Columbia United States Human Computer Interaction Institute Carnegie Mellon University United States The Nature Conservancy New YorkNY United States IBM Research Europe IE Switzerland

Effective water resource management requires information on water availability - both in terms of quality and quantity - spatially and temporally. In this paper, we study the methodology behind Transfer Learning (TL) through fine-tuning and parameter transferring for better generalization performance of streamflow prediction in data-sparse regions. We propose a standard recurrent neural network in the form of Long Short-Term Memory (LSTM) to fit on a sufficiently large source domain dataset and repurpose the learned weights to a significantly smaller, yet similar target domain datasets. We present a methodology to implement transfer learning approaches for spatiotemporal applications by separating the spatial and temporal components of the model and training the model to generalize based on categorical datasets representing spatial variability. The framework is developed on a rich benchmark dataset from the US and evaluated on a smaller dataset collected by The Nature Conservancy in Kenya. The LSTM model exhibits generalization performance through our TL technique. Results from this current experiment demonstrate the effective predictive skill of forecasting streamflow responses when knowledge transferring and static descriptors are used to improve hydrologic model generalization in data-sparse regions. © 2021, CC BY.

关键词： Long short-term memory

AVTENet: A human-Cognition-Inspired Audio-Visual Transformer-Based Ensemble Network for Video Deepfake Detection

学校读者我要写书评

暂无评论

IEEE Transactions on Cognitive and Developmental Systems 2025年

作者： Hashmi, Ammarah Shahzad, Sahibzada Adil Lin, Chia-Wen Tsao, Yu Wang, Hsin-Min Taiwan International Graduate Program Academia Sinica Social Networks and Human-Centered Computing Program Taipei11529 Taiwan National Tsing Hua University Institute of Information Systems and Applications Hsinchu30013 Taiwan National Chengchi University Department of Computer Science Taipei11605 Taiwan National Tsing Hua University Department of Electrical Engineering Institute of Communications Engineering Hsinchu300044 Taiwan Academia Sinica Research Center for Information Technology Innovation Taipei11529 Taiwan

The recent proliferation of hyper-realistic deepfake videos has drawn attention to the threat of audio and visual forgeries. Most previous studies on detecting artificial intelligence-generated fake videos only utilize visual modality or audio modality. While some methods exploit audio and visual modalities to detect forged videos, they have not been comprehensively evaluated on multimodal datasets of deepfake videos involving acoustic and visual manipulations, and are mostly based on convolutional neural networks with low detection accuracy. Considering that human cognition instinctively integrates multisensory information including audio and visual cues to perceive and interpret content and the success of transformer in various fields, this study introduces the audio-visual transformer-based ensemble network (AVTENet). This innovative framework tackles the complexities of deepfake technology by integrating both acoustic and visual manipulations to enhance the accuracy of video forgery detection. Specifically, the proposed model integrates several purely transformer-based variants that capture video, audio, and audio-visual salient cues to reach a consensus in prediction. For evaluation, we use the recently released benchmark multimodal audio-video FakeAVCeleb dataset. For a detailed analysis, we evaluate AVTENet, its variants, and several existing methods on multiple test sets of the FakeAVCeleb dataset. Experimental results show that the proposed model outperforms all existing methods and achieves state-of-the-art performance on Testset-I and Testset-II of the FakeAVCeleb dataset. We also compare AVTENet against humans in detecting video forgery. The results show that AVTENet significantly outperforms humans. © 2016 IEEE.

关键词： audio-visual AVTENet Deepfake detection

Performance Evaluation of Query Plan Recommendation with Apache Hadoop and Apache Spark

学校读者我要写书评

暂无评论

arXiv 2022年

作者： Azhir, Elham Hosseinzadeh, Mehdi Khan, Faheem Mosavi, Amir Department of Computer Engineering Science and Research Branch Islamic Azad University Tehran*** Iran Research and Development Center Mobile Telecommunication Company of Iran Tehran Iran Mental Health Research Center Psychosocial Health Research Institute Iran University of Medical Sciences Tehran*** Iran Computer Science University of Human Development Sulaymaniyah0778-6 Iraq Department of Computer Engineering Gachon University Seongnam13120 Korea Republic of Faculty of Civil Engineering Technische Universität Dresden Dresden01069 Germany

Access plan recommendation is a query optimization approach that executes new queries using prior created query execution plans (QEPs). The query optimizer divides the query space into clusters in the mentioned method. However, traditional clustering algorithms take a significant amount of execution time for clustering such large datasets. The MapReduce distributed computing model provides efficient solutions for storing and processing vast quantities of data. Apache Spark and Apache Hadoop frameworks are used in the present investigation to cluster different sizes of query datasets in the MapReduce-based access plan recommendation method. The performance evaluation is performed based on execution time. The results of the experiments demonstrated the effectiveness of parallel query clustering in achieving high scalability. Furthermore, Apache Spark achieved better performance than Apache Hadoop, reaching an average speedup of *** Codes 68T05 © 2022, CC BY.

关键词： MapReduce

Genetic evidence for facial variation being a composite phenotype of cranial variation and facial soft tissue thickness

学校读者我要写书评

暂无评论

Journal of Genetics and Genomics 2022年第10期49卷 934-942页

作者： Wei Qian Manfei Zhang Kaiwen Wan Yunxia Xie Siyuan Du Jiarui Li Xiongzheng Mu Jiange Qiu Xiangyang Xue Xiahai Zhuang Yingzhi Wu Fan Liu Sijia Wang State Key Laboratory of Genetic Engineering Human Phenome InstituteZhangjiang Fudan International Innovation CenterFudan UniversityShanghai 201203China School of Computer Science Fudan UniversityShanghai 200438China CAS Key Laboratory of Computational Biology Shanghai Institute of Nutrition and HealthUniversity of Chinese Academy of SciencesChinese Academy of SciencesShanghai 200031China School of Data Science Fudan UniversityShanghai 200433China Academy of Medical Science Zhengzhou UniversityZhengzhouHenan 450052China Department of Plastic Surgery Huashan HospitalFudan UniversityShanghai 200040China CAS Key Laboratory of Genomic and Precision Medicine Beijing Institute of GenomicsUniversity of Chinese Academy of SciencesBeijing 100101China School of Future Technology University of Chinese Academy of SciencesBeijing 101408China Center for Excellence in Animal Evolution and Genetics Chinese Academy of SciencesKunmingYunnan 650223China

Facial and cranial variation represent a multidimensional set of highly correlated and heritable *** is known about the genetic basis explaining this *** develop a software package ALo SFL for simultaneous localization of facial and cranial landmarks from head computed tomography(CT)images,apply it in the analysis of head CT images of 777 Han Chinese women,and obtain a set of phenotypes representing variation in face,skull and facial soft tissue thickness(FSTT).Association analysis of 301 single nucleotide polymorphisms(SNPs)from 191 distinct genomic loci previously associated with facial variation reveals an unexpected larger number of loci showing significant associations(P<1e-3)with cranial phenotypes than expected under the null(O/E=3.39),suggesting facial and cranial phenotypes share a substantial proportion of genetic *** FSTT to a SNP-only model shows a large impact in explaining facial variance.A gene ontology analysis reveals that bone morphogenesis and osteoblast differentiation likely underlie our cranial-significant ***,this study simultaneously investigates the genetic effects on both facial and cranial variation of the same sample,supporting that facial variation is a composite phenotype of cranial variation and FSTT.

关键词： Facial variation Cranial variation Association analysis Single nucleotide polymorphism Facial soft tissue thickness Computed tomography

B-Spine: Learning B-Spline Curve Representation for Robust and Interpretable Spinal Curvature Estimation

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Wang, Hao Song, Qiang Yin, Ruofeng Ma, Rui Yu, Yizhou Chang, Yi School of Artificial Intelligence Jilin University Changchun130012 China China-Japan Union Hospital Jilin University Changchun130031 China Engineering Research Center of Knowledge-Driven Human-Machine Intelligence MOE China Department of Computer Science University of Hong Kong Pokfulam Hong Kong

Spinal curvature estimation is important to the diagnosis and treatment of the scoliosis. Existing methods face several issues such as the need of expensive annotations on the vertebral landmarks and being sensitive to the image quality. It is challenging to achieve robust estimation and obtain interpretable results, especially for low-quality images which are blurry and hazy. In this paper, we propose B-Spine, a novel deep learning pipeline to learn B-spline curve representation of the spine and estimate the Cobb angles for spinal curvature estimation from low-quality X-ray images. Given a low-quality input, a novel SegRefine network which employs the unpaired image-to-image translation is proposed to generate a high quality spine mask from the initial segmentation result. Next, a novel mask-based B-spline prediction model is proposed to predict the B-spline curve for the spine centerline. Finally, the Cobb angles are estimated by a hybrid approach which combines the curve slope analysis and a curve-based regression model. We conduct quantitative and qualitative comparisons with the representative and SOTA learning-based methods on the public AASCE2019 dataset and our new proposed CJUH-JLU dataset which contains more challenging low-quality images. The superior performance on both datasets shows our method can achieve both robustness and interpretability for spinal curvature estimation.. Copyright © 2023, The Authors. All rights reserved.

关键词： Curve fitting