检索结果-内蒙古大学图书馆

Detection of low back muscle state based on electrical impedance myography

学校读者我要写书评

暂无评论

Detection of low back muscle state based on electrical imped...

IEEE MTT-S International Microwave Bio Conference ((IMBIOC)

作者： Jingting Shi Yanyan Liu Hongli Yan Yueming Gao Ž eljka Luč ev Vasić Mario Cifrek The College of Physics and Information Engineering Fuzhou University Fuzhou China Fujian province Key Lab. of medical Instrument and Pharmaceutical technology Fuzhou University Fuzhou China School of Advanced Manufacturing Fuzhou University Fuzhou China The Faculty of Electrical Engineering and Computing University of Zagreb Zagreb Croatia

ISBN: (数字)9781665423403

ISBN: (纸本)9781665423410

In the prevention and rehabilitation stage of low back diseases, it is necessary to detect the state of muscles to avoid excessive fatigue and injury caused by continuous exertion of lumbar muscles. In this paper, an in vivo experimental platform for measuring low back muscle impedance was established in order to detect the different force states of muscle and study the corresponding relationship between muscle force state and muscle impedance. In the experiment, Biering-Sorensen (BS) test was used to make the low back muscle contract continuously, and different weights (5 kg, 2.5 kg, 0 kg) were used to distinguish the force state of muscle. The impedance analyzer was used to measure the muscle impedance parameters under different load in the subject's low back muscle for studying the electrical impedance characteristics of different low back muscle states. The results showed that the relative resistance $R^{\prime}$ of EIM was a downward trend with time and the 5 kg load had the fastest decline; The relative reactance $X_{c}^{\prime}$ of EIM was an upward trend with time, the 5 kg load also had the fastest rise. The slope $k$ of the fitting curve of $R^{\prime}$ and $X_{c}^{\prime}\text{were}-5.8\times 10^{-4}$ and $8.76 \times 10^{-4}$ respectively. Therefore, EIM can effectively detect the state of low back muscles.

关键词： In vivo Impedance measurement Force Fitting Muscles Back Market research

A Learning-Exploring Method to Generate Diverse Paraphrases with Multi-Objective Deep Reinforcement Learning 28

学校读者我要写书评

暂无评论

A Learning-Exploring Method to Generate Diverse Paraphrases ...

28th International Conference on Computational Linguistics, COLING 2020

作者： Liu, Mingtong Yang, Erguang Xiong, Deyi Zhang, Yujie Meng, Yao Hu, Changjian Xu, Jinan Chen, Yufeng School of Computer Science and Information Technology Beijing Key Lab of Traffic Data Analysis and Mining Beijing Jiaotong University Beijing China College of Intelligence and Computing Tianjin University Tianjin China Lenovo Research AI Lab. Beijing China

ISBN: (纸本)9781952148279

Paraphrase generation (PG) is of great importance to many downstream tasks in natural language processing. Diversity is an essential nature to PG for enhancing generalization capability and robustness of downstream applications. Recently, neural sequence-to-sequence (Seq2Seq) models have shown promising results in PG. However, traditional model training for PG focuses on optimizing model prediction against single reference and employs cross-entropy loss, which objective is unable to encourage model to generate diverse paraphrases. In this work, we present a novel approach with multi-objective learning to PG. We propose a learning-exploring method to generate sentences as learning objectives from the learned data distribution, and employ reinforcement learning to combine these new learning objectives for model training. We first design a sample-based algorithm to explore diverse sentences. Then we introduce several reward functions to evaluate the sampled sentences as learning signals in terms of expressive diversity and semantic fidelity, aiming to generate diverse and high-quality paraphrases. To effectively optimize model performance satisfying different evaluating aspects, we use a GradNorm-based algorithm that automatically balances these training objectives. Experiments and analyses on Quora and Twitter datasets demonstrate that our proposed method not only gains a significant increase in diversity but also improves generation quality over several state-of-the-art baselines. © 2020 COLING 2020 - 28th International Conference on Computational Linguistics, Proceedings of the Conference. All rights reserved.

关键词： Reinforcement learning

Study of a code comment decision method based on structural features

学校读者我要写书评

暂无评论

Study of a code comment decision method based on structural ...

2019 International Conference on Intelligent computing, Automation and Systems, ICICAS 2019

作者： Wang, Renmin Wang, Tao Wang, Huaimin Key Lab. of Parallel and Distributed Computing National University of Defense Technology Changsha China

ISBN: (纸本)9781728161068

Code comment is one of the most effective ways to help programmers to understand the source code. High-quality comment decisions can not only cover the core code snippets in the software system but also avoid generating redundant code comments. However, in actual development, there is no uniform comment specification, and most of the comment decisions depend on personal experience and domain knowledge. This paper has learned a common comment decision specification from a large number of code comment examples to assist programmers in making appropriate comment decisions during code development. This paper proposes a method to extract the code structure from the context code of the current code line, and use the machine learning algorithm to determine the possibility that the current code needs to add comments. The proposed method was evaluated on 8 well-known open-source Python projects in GitHub and the experimental results show the feasibility and effectiveness of the method in some code types. © 2019 IEEE.

关键词： Machine learning

DDIR: Domain-Disentangled Invariant Representation learning for tailored predictions

学校读者我要写书评

暂无评论

Knowledge-Based Systems 2025年 319卷

作者： Ma, Yuan Gu, Yang Qin, Xin Guo, Shuai Fan, Feiyi Dong, Fan Chen, Yiqiang Beijing Key Lab. of Mobile Computing and Pervasive Device Institute of Computing Technology Chinese Academy of Sciences 6 Kexueyuan Nanlu Zhongguancun Beijing China University of Chinese Academy of Sciences No. 1 Yanqihu East Rd Huairou District Beijing China

Traditional training methods often struggle to scale effectively with large datasets due to significant distributional differences. Domain generalization (DG) aims to address the challenge of generalizing across multiple-source domains and improving performance in unknown target domains. While many DG methods, such as domain-invariant representation (DIR) learning, excel in handling significant distribution shifts, they often sacrifice performance on in-distribution (IID) data. This trade-off is crucial in real-world applications with uncertain distribution shifts, spanning both out-of-distribution (OOD) and IID scenarios. To address this, we identify DIR's limitation in neglecting task-relevant non-domain-invariant information, termed Domain-Orthogonal Invariant (DOI) information. We propose the Domain-Disentangled Invariant Representation (DDIR) learning, which retains DOI information without introducing redundancy. Our method introduces an information disentanglement loss to extract domain-invariant and different DOI information within a single backbone, achieving lower spatial complexity. Moreover, during inference, we propose optimal DOI selection approaches for individual target samples to avoid utilizing redundant DOI information, enabling tailored predictions for each target sample. Experiments demonstrate DDIR's effectiveness in enhancing generalization performance across IID and OOD scenarios. © 2025

关键词： Domain generalization Domain-invariant representation Representation learning

User-inspired posterior network for recommendation reason generation

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Zhan, Haolan Zhang, Hainan Chen, Hongshen Shen, Lei Lan, Yanyan Ding, Zhuoye Yin, Dawei State Key Lab. of Computer Science Institute of Software Chinese Academy of Sciences Institute of Computing Technology Chinese Academy of Sciences University of Chinese Academy of Sciences Data Science Lab *** Baidu Inc. Beijing China

Recommendation reason generation, aiming at showing the selling points of products for customers, plays a vital role in attracting customers’ attention as well as improving user experience. A simple and effective way is to extract keywords directly from the knowledge-base of products, i.e., attributes or title, as the recommendation reason. However, generating recommendation reason from product knowledge doesn’t naturally respond to users’ interests. Fortunately, on some E-commerce websites, there exists more and more user-generated content (user-content for short), i.e., product question-answering (QA) discussions, which reflect user-cared aspects. Therefore, in this paper, we consider generating the recommendation reason by taking into account not only the product attributes but also the customer-generated product QA discussions. In reality, adequate user-content is only possible for the most popular commodities, whereas large sums of long-tail products or new products cannot gather a sufficient number of user-content. To tackle this problem, we propose a user-inspired multi-source posterior transformer (MSPT), which induces the model reflecting the users’ interests with a posterior multiple QA discussions module, and generating recommendation reasons containing the product attributes as well as the user-cared aspects. Experimental results show that our model is superior to traditional generative models. Additionally, the analysis also shows that our model can focus more on the user-cared aspects than baselines. Copyright © 2021, The Authors. All rights reserved.

关键词： Sales

MVSS-Net: Multi-View Multi-Scale Supervised Networks for Image Manipulation Detection

学校读者我要写书评

暂无评论

arXiv 2021年

作者： Dong, Chengbo Chen, Xinru Hu, Ruohan Cao, Juan Li, Xirong The Key Lab of Data Engineering and Kowledge Engineering Renmin University of China Beijing100872 China The AIMC Lab. School of Information Renmin University of China Beijing100872 China Institute of Computing Technology Chinese Academy of Sciences The the Key Laboratory of Media Convergence Production Technology and Systems Beijing100864 China

As manipulating images by copy-move, splicing and/or inpainting may lead to misinterpretation of the visual content, detecting these sorts of manipulations is crucial for media forensics. Given the variety of possible attacks on the content, devising a generic method is nontrivial. Current deep learning based methods are promising when training and test data are well aligned, but perform poorly on independent tests. Moreover, due to the absence of authentic test images, their image-level detection specificity is in doubt. The key question is how to design and train a deep neural network capable of learning generalizable features sensitive to manipulations in novel data, whilst specific to prevent false alarms on the authentic. We propose multi-view feature learning to jointly exploit tampering boundary artifacts and the noise view of the input image. As both clues are meant to be semantic-agnostic, the learned features are thus generalizable. For effectively learning from authentic images, we train with multi-scale (pixel/edge/image) supervision. We term the new network MVSS-Net and its enhanced version MVSS-Net++. Experiments are conducted in both within-dataset and cross-dataset scenarios, showing that MVSS-Net++ performs the best, and exhibits better robustness against JPEG compression, Gaussian blur and screenshot based image re-capturing. Copyright © 2021, The Authors. All rights reserved.

关键词： Deep neural networks

Interpreting Object-level Foundation Models via Visual Precision Search

学校读者我要写书评

暂无评论

arXiv 2024年

作者： Chen, Ruoyu Liang, Siyuan Li, Jingzhi Liu, Shiming Li, Maosen Huang, Zhen Zhang, Hua Cao, Xiaochun Institute of Information Engineering Chinese Academy of Sciences Beijing100093 China School of Cyber Security University of Chinese Academy of Sciences Beijing100049 China School of Computing NUS Singapore RAMS Lab Huawei Technologies Co. Ltd. China IAS BU Huawei Technologies Co. Ltd. China College of Computer NUDT China Key Lab. of Edu. Inf. for Nationalities YNNU Ministry of Education Kunming China School of Cyber Science and Technology Sun Yat-sen University Shenzhen Campus Shenzhen518107 China

Advances in multimodal pre-training have propelled object-level foundation models, such as Grounding DINO and Florence-2, in tasks like visual grounding and object detection. However, interpreting these models’ decisions has grown increasingly challenging. Existing interpretable attribution methods for object-level task interpretation have notable limitations: (1) gradient-based methods lack precise localization due to visual-textual fusion in foundation models, and (2) perturbation-based methods produce noisy saliency maps, limiting fine-grained interpretability. To address these, we propose a Visual Precision Search method that generates accurate attribution maps with fewer regions. Our method bypasses internal model parameters to overcome attribution issues from multimodal fusion, dividing inputs into sparse sub-regions and using consistency and collab.ration scores to accurately identify critical decision-making regions. We also conducted a theoretical analysis of the boundary guarantees and scope of applicability of our method. Experiments on RefCOCO, MS COCO, and LVIS show our approach enhances object-level task interpretability over SOTA for Grounding DINO and Florence-2 across various evaluation metrics, with faithfulness gains of 23.7%, 31.6%, and 20.1% on MS COCO, LVIS, and RefCOCO for Grounding DINO, and 50.7% and 66.9% on MS COCO and RefCOCO for Florence-2. Additionally, our method can interpret failures in visual grounding and object detection tasks, surpassing existing methods across multiple evaluation metrics. The code is released at https://***/RuoyuChen10/VPS. Copyright © 2024, The Authors. All rights reserved.

关键词： Object detection

LEARNING CAUSAL ALIGNMENT FOR RELIABLE DISEASE DIAGNOSIS

学校读者我要写书评

暂无评论

arXiv 2023年

作者： Liu, Mingzhou Lee, Ching-Wen Sun, Xinwei Yu, Xueqing Yu, Qiao Wang, Yizhou School of Computer Science Peking University China School of Data Science Fudan University China Computer Science Department Shanghai Jiao Tong University China Center on Frontiers of Computing Studies Peking University China Institute for Artificial Intelligence Peking University China Nat’l Eng. Research Center of Visual Technology Peking University China State Key Lab. of General Artificial Intelligence Peking University China

Aligning the decision-making process of machine learning algorithms with that of experienced radiologists is crucial for reliable diagnosis. While existing methods have attempted to align their diagnosis behaviors to those of radiologists reflected in the training data, this alignment is primarily associational rather than causal, resulting in pseudo-correlations that may not transfer well. In this paper, we propose a causality-based alignment framework towards aligning the model’s decision process with that of experts. Specifically, we first employ counterfactual generation to identify the causal chain of model decisions. To align this causal chain with that of experts, we propose a causal alignment loss that enforces the model to focus on causal factors underlying each decision step in the whole causal chain. To optimize this loss that involves the counterfactual generator as an implicit function of the model’s parameters, we employ the implicit function theorem equipped with the conjugate gradient method for efficient estimation. We demonstrate the effectiveness of our method on two medical diagnosis applications, showcasing faithful alignment to radiologists. Code is publicly availab.e at https://***/lmz123321/Causal_alignment. © 2023, CC BY.

关键词： Radiology

Investigating gesture typing for indirect touch

学校读者我要写书评

暂无评论

Proceedings of the ACM on Interactive, Mobile, Wearable and Ubiquitous Technologies 2019年第3期3卷 1-22页

作者： Yang, Zhican Yu, Chun Yi, Xin Shi, Yuanchun Key Laboratory of Pervasive Computing Ministry of Education Beijing Key Lab. of Networked Multimedia Beijing National Research Center for Information Science and Technology Department of Computer Science and Technology Tsinghua University Beijing100084 China

With the development of ubiquitous computing, entering text on HMDs and smart TVs using handheld touchscreen devices (e.g., smartphone and controller) is becoming more and more attractive. In these indirect touch scenarios, the touch input surface is decoupled from the visual display. Compared with direct touch input, entering text using a keyboard in indirect touch is more challenging because before the finger touch, no visual feedback is availab.e for locating the touch finger. Aiming at this problem, in this paper, we investigate the feasibility of gesture typing for indirect touch since keeping the finger in touch with the screen during typing makes it possible to provide continuous visual feedback, which is beneficial for increasing the input performance. We first examine users' gesture typing ability in terms of the appropriate keyboard size and location in motor space and then compare the typing performance in direct and indirect touch mode. We then propose an improved design to address the uncertainty and inaccuracy of the first touch. Our evaluation result shows that users can quickly acquire indirect gesture typing, and type 22.3 words per minute after 30 phases, which significantly outperforms previous numbers in literature. Our work provides the empirical support for leveraging gesture typing for indirect touch. © 2019 Association for computing Machinery.

关键词： Touch screens