检索结果-内蒙古大学图书馆

13th IEEE International Conference on CYBER Technology in Automation, Control, and intelligent Systems, CYBER 2023

作者： Niu, Ben Wei, Yangjie College of Computer Science and Engineering Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang110819 China

ISBN: (纸本)9798350315196

To improve the accuracy and robustness of existing speech denoising methods, this study proposes an adaptive speech noise reduction method based on noise classification. First, to adapt to different time-varying characteristics of various noises in complex environments, a new acoustic feature matrix is constructed by combining the LogFbank features and the perceptual linear prediction coefficients, and a noise classifier based on the support vector machine is designed to classify the experimental noise. Then, to address the problem of 'music noise' in traditional speech denoising methods, the voice activity detection threshold is adaptively updated according to the judgment result of background noise types, and the optimal parameters for the improved minima controlled recursive averaging noise estimation algorithm are obtained to accurately estimate current noise and reduce it. Finally, the performance of the proposed method is evaluated using a serial of experiments on different situations, and the experimental results prove the effectiveness and feasibility of our proposed method in this study. © 2023 IEEE.

关键词： Support vector machines

来源：评论

学校读者我要写书评

暂无评论

Feature Selection for Microarray Data via Community Detection Fusing Multiple Gene Relation Networks Information

Feature Selection for Microarray Data via Community Detectio...

引用

2022 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2022

作者： Zhang, Shoujia Li, Wei Xie, Weidong Wang, Linjie Northeastern University College of Computer Science and Engineering Shenyang China Northeastern University Key Laboratory of Intelligent Computing in Medical Image Shenyang China

ISBN: (纸本)9781665468190

In recent decades, the rapid development of gene sequencing and computer technology has increased the growth of high-dimensional microarray data. Some machine learning methods have been successfully applied to it to help classify cancer. In most cases, high dimensionality and the small sample size of microarray data restricted the performance of cancer classification. This problem usually issolved bysome feature selection methods. However, most of them neglect the exploitation of relations among genes. This paper proposes a novel feature selection method by fusing multiple gene relation network information based on community detection (MGRCD). The proposed method divides all genes into different communities. Then, the genes most associated with cancer classification are selected from each community. The proposed method satisfies both maximum relevances gene with cancer and minimum redundancy among genes for the selected optimal feature subset. The experiment results show that the proposed gene selection method can effectively improve classification performance. © 2022 IEEE.

关键词： Genes

来源：评论

学校读者我要写书评

暂无评论

Dual-Granularity Contrastive Learning for Session-Based Recommendation 9th

Dual-Granularity Contrastive Learning for Session-Based Rec...

引用

19th International Conference on Advanced Data Mining and Applications, ADMA 2023

作者： Wang, Zihan Wu, Gang Wang, Haotong School of Computer Science and Engineering Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Shenyang China

ISBN: (纸本)9783031466601

The data encountered by Session-based Recommendation System(SBRS) is typically highly sparse, which also serves as one of the bottlenecks limiting the accuracy of recommendations. So Contrastive Learning(CL) is applied in SBRS owing to its capability of improving embedding learning under the condition of sparse data. However, existing CL strategies are limited in their ability to enforce finer-grained (e.g., factor-level) comparisons and, as a result, are unable to capture subtle differences between instances. More than that, these strategies usually use item or segment dropout as a means of data augmentation which may result in sparser data and thus ineffective self-supervised signals. By addressing the two aforementioned limitations, we introduce a novel dual-granularity CL framework. Specifically, two extra augmentation views with different granularities are constructed and the embeddings learned by them are compared with those learned from original view to complete the CL tasks. At factor-level, we employ Disentangled Representation Learning to obtain finer-grained data, with which we can explore connections of items on latent factor independently and generate factor-level embeddings. At item-level, the star graph is deployed as the augmentation method. By setting an additional satellite node, non-adjacent nodes can establish additional connections through satellite nodes instead of reducing the connections of the original graph, so data sparsity can be avoided. Compare the learned embeddings of these two views with the learned embeddings of the original view to achieve CL at two granularities. Finally, the item-level and factor-level embeddings obtained are referenced to generate personalized recommendations for the user. The proposed model is validated through extensive experiments on two benchmark datasets, showcasing superior performance compared to existing methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2023.

关键词： Benchmarking

来源：评论

学校读者我要写书评

暂无评论

Few-shot small vessel segmentation using a detail-preserving network enhanced by discriminator

引用

medical and Biological Engineering and computing 2025年 2025 May 13页

作者： Huang, Yan Yang, Jinzhu Sun, Qi Yuan, Yuliang Hou, Yang Shang, Jin Key Laboratory of Intelligent Computing in Medical image Ministry of Education Northeastern University Shenyang 110819 China School of Computer Science and Engineering Northeastern University Shenyang 110819 China National Frontiers Science Center for Industrial Intelligence and Systems Optimization Liaoning Shenyang China Department of Radiology Shengjing Hospital of China Medical University Liaoning Shenyang China

Abstract: Accurate segmentation of small vessels, such as coronary and pulmonary arteries, is crucial for early detection and treatment of vascular diseases. However, challenges persist due to the vessel’s small size, complex structures, morphological variations, and limited annotated data. To address these challenges, we propose a detail-preserving network enhanced by a discriminator to improve the few-shot small vessel segmentation performance. The detail-preserving network constructs a complex module with multi-residual hybrid dilated convolution, which can enhance the network’s receptive field while preserving the image’s full detail features, enabling it to better capture the small vessel’s structural features. Simultaneously, discriminator enhancement is incorporated into the training process through adversarial learning, effectively utilizing large amounts of unlabeled data to boost the generalization and robustness of the segmentation model. We validate the proposed method on in-house and public coronary artery datasets and public pulmonary artery datasets. Experimental results demonstrate that the proposed method significantly improves segmentation accuracy, particularly for small vessels. Compared with other state-of-the-art methods, the proposed method achieves higher accuracy, a lower false positive rate, and superior generalization capability, effectively assisting the clinical diagnosis of vessel diseases. © International Federation for medical and Biological Engineering 2025.

关键词： Adversarial learning Dilated convolutions Few-shot learning Vessel segmentation

来源：评论

学校读者我要写书评

暂无评论

Optimizing Empathetic Response by Generating and Integrating Emotion Feedback and Topic Discussion 28th

Optimizing Empathetic Response by Generating and Integrati...

引用

28th International Conference on Database Systems for Advanced Applications, DASFAA 2023

作者： Li, Jing Han, Donghong Feng, Shi Zhang, Yifei School of Computer Science and Engineering Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image of Ministry of Education Northeastern University Shenyang China

ISBN: (纸本)9783031306747

Expressing empathy is a trait in human daily conversation, in which people are willing to give responses containing appropriate emotions and topics on the basis of understanding the interlocutor’s situation. However, empathetic dialogue models trained by data-driven training method tend to generate general responses, which are usually monotonous and difficult to infuse emotions and topics concurrently. To solve this issue, we propose a novel model that generates two sub-responses, namely, emotion feedback and topic discussion, then integrates them to optimize empathetic responses. Specifically, in the sub-response generation stage, we introduce emotion lexicon and commonsense knowledge to make sub-responses focus on emotional words and topic-related words respectively, which drives the sub-responses to be contextually related from different perspectives. Afterward, we utilize cross attention to integrate the global information to optimize the final response. Our model is trained on the pre-trained language model BART. Experimental results show that our method can generate responses involving emotion and topic well, and compared with existing methods, empathy and relevance are improved. Our code is available at https://***/outsider-lj/edsgi_bart. © 2023, The Author(s), under exclusive license to Springer Nature Switzerland AG.

关键词： Digital storage

来源：评论

学校读者我要写书评

暂无评论

A Bald Eagle Search Optimization Based Weighted Rank Aggregation Method for Microarray Data Classification 23

A Bald Eagle Search Optimization Based Weighted Rank Aggrega...

引用

15th International Conference on Bioinformatics and Biomedical Technology, ICBBT 2023

作者： Li, Wei Shi, Tengfei Wang, Linjie Xie, Weidong Key Laboratory of Intelligent Computing in Medical Image MIIC Northeastern University Ministry of Education China School of Computer Science and Engineering Northeastern University Shenyang China

ISBN: (纸本)9798400700385

The rapid development of microarray technology has generated a large amount of microarray data, and the classification of these data is meaningful for cancer diagnosis, treatment and prognosis. The classification of high-dimensional microarray data with small samples is a challenging problem, which usually requires feature selection methods to reduce the data dimensionality first. However, different feature selection methods usually generate different feature lists for the same data. Researchers need to choose among many feature selection methods, which reduces the research efficiency. Therefore, rank aggregation method is used to generate a optimal list by aggregating all ordered feature lists generated by different feature selection methods. It can combine the advantages of multiple feature selection methods and does not prefer a particular method, so it is more robust to outliers, noises and errors. In this paper, we propose a weighted rank aggregation method based on the Bald Eagle Search optimization. A positional weight is designed to emphasize the importance of the top features in the list, so that the distance between lists can be measured more accurately. In addition, we improve the Bald Eagle Search algorithm for optimizing rank aggregation method to obtain a optimal ordered list. The experimental results on six public microarray datasets indicate that the features selected by our method can significantly improve the classification performance. © 2023 ACM.

关键词： Feature Selection

来源：评论

学校读者我要写书评

暂无评论

Automatic Heart Segmentation Based On Convolutional Networks Using Attention Mechanism 14

Automatic Heart Segmentation Based On Convolutional Networks...

引用

14th International Conference on Digital image Processing, ICDIP 2022

作者： Zhang, Guodong Liu, Yu Guo, Wei Tan, Wenjun Gong, Zhaoxuan Farooq, Muhammad Azaz Shenyang Aerospace University Liaoning Shenyang110136 China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Liaoning 110819 China

ISBN: (纸本)9781510657564

Heart segmentation is challenging due to the poor image contrast of heart in the CT images. Since manual segmentation of the heart is tedious and time-consuming, we propose an attention based- Convolution Neural Network(CNN) for heart segmentation. First, one-hot preprocessing is performed on the multi-tissue CT images. U-Net network with Attention-gate is then applied to obtain the heart region. We compared our method with several CNN methods in terms of dice coefficient. Results show that our method outperforms other methods for segmentation. © 2022 SPIE.

关键词： Heart

来源：评论

学校读者我要写书评

暂无评论

Altered spatiotemporal consistency of local neural activities in Parkinson’s disease 3

Altered spatiotemporal consistency of local neural activitie...

引用

3rd International Conference on Optics and image Processing, ICOIP 2023

作者： Jin, Chaoyang Yang, Lei Qi, Shouliang College of Medicine and Biological Information Engineering Northeastern University Shenyang China Key Laboratory of Intelligent Computing in Medical Image Ministry of Education Northeastern University Shenyang China

ISBN: (纸本)9781510667426

The present study aims to explore the local spatiotemporal consistency of brain connectivity in PD patients. In total, 30 PD patients and 20 health controls (HC) were collected from the Parkinson’s progression markers initiative (PPMI) and their resting state functional MRI images are acquired. FOur-dimensional Consistency of local neural Activities (FOCA) was employed for the first time to explore local brain activity differences between the two groups. To explore the relationship between FOCA values and neuropsychological indices, the Pearson correlation analysis was performed. And receiver operating characteristic (ROC) analysis was carried out to distinguish PD from HC. Compared with HC, PD patients demonstrated decreased FOCA values in the right inferior temporal gyrus (ITG.R), right middle temporal gyrus (MTG.R), right middle occipital gyrus (MOG.R), right superior occipital gyrus, right inferior occipital gyrus, left precentral gyrus (PreCG.L), left postcentral gyrus (PoCG.L) and left rolandic operculum. The FOCA values in MTG.R and ITG.R were positively related to Montreal Cognitive Assessment (MoCA) values. Negative relationships had been found in FOCA values of PreCG.L and MOG.R and Unified Parkinson’s Disease Rating Scale (UPDRS) III scores. What’s more, the ROC analysis showed that the FOCA values of altered brain regions can be used to distinguish PD patients from HC with high performance. PD patients demonstrated disrupted local brain activity in several brain regions. These brain regions are mainly involved in motor, cognitive and emotional functions. The current study provides important insights into understanding the pathophysiological mechanism of PD symptoms. © 2023 SPIE. All rights reserved.

关键词： Magnetic resonance imaging

来源：评论

学校读者我要写书评

暂无评论

TIDE: a Timing-Deterministic and Efficient Executor for micro-ROS

TIDE: a Timing-Deterministic and Efficient Executor for micr...

引用

IEEE/ACM Int'l Conference on & Int'l Conference on Cyber, Physical and Social computing (CPSCom) Green computing and Communications (GreenCom)

作者： Zilong Wang Songran Liu Xu Jiang Dong Ji Yi Wang Key Laboratory of Intelligent Computing in Medical Image Northeastern University China

The micro-ROS is widely used to bridge the gap between resource-constrained microcontrollers and larger processors in ROS-based robotic applications. We found that there are some performance issues in micro-ROS because of the unreasonable design of the micro-ROS default RCLC Executor. To improve the timing predictability and run-time efficiency in micro-ROS, we have designed and implemented a new executor called the TIDE Executor, and conducted comprehensive experiments to evaluate the TIDE Executor. The experimental results demonstrate that our TIDE Executor exhibits superior performance compared to the default RCLC Executor.

关键词：

来源：评论

学校读者我要写书评

暂无评论

A Pulmonary Artery-Vein Separation algorithm based on the relationship between sub-trees 2020

A Pulmonary Artery-Vein Separation algorithm based on the re...

引用

The Fourth International Symposium on image computing and Digital Medicine

作者： Wenjun Tan Key Laboratory of Intelligent Computing in Medical Image Ministry of Education China

ISBN: (纸本)9781450389686

This article presents a combined algorithm of pulmonary artery-vein (A/V) separation considering both global and local information, including: the transformation of geometric graph, sub-tree separation, and A/V classification. During the process, geometric graphs are firstly built based on the centerlines; A separation of the adhesion points is performed by applying the information stored in the data structure of the nodes and links in the geometric graphs; Sub-trees are then combined according to the local and global information; The combined sub-trees are growing into vascular trees using 2D area growth method; And finally, classification of the arterial and venous vascular trees based on the knowledge of anatomy. An average accuracy of 85% has been achieved of the overall process with a processing time range between 40 s to 50 s, which indicates good performance and stability of this algorithm.

关键词： algorithm Artery-Vein Separation

来源：评论

学校读者我要写书评

暂无评论

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案：

请选择收藏分类：

通借通还

建议与咨询 留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

时间限定

文献类型

馆藏选择

核心期刊

语言

文献类型

帮助

文字说明：

检索规则说明：

检索范例：

分类表

所选分类

限定检索结果

文献类型

馆藏范围

日期分布

学科分类号

主题

机构

作者

语言

请选择保存的检索档案： 新增检索档案 确定 取消

请选择收藏分类： 新增自定义分类 确定 取消

通借通还

建议与咨询留下您的常用邮箱和电话号码，以便我们向您反馈解决方案和替代方法

请选择保存的检索档案：

请选择收藏分类：