检索结果-内蒙古大学图书馆

International Conference on computer Vision (ICCV)

作者： Peng Jin Hao Li Zesen Cheng Kehan Li Xiangyang Ji Chang Liu Li Yuan Jie Chen School of Electronic and Computer Engineering Peking University Shenzhen China AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School Shenzhen China Department of Automation and BNRist Tsinghua University Beijing China Peng Cheng Laboratory Shenzhen China

Existing text-video retrieval solutions are, in essence, discriminant models focused on maximizing the conditional likelihood, i.e., p(candidates|query). While straightforward, this de facto paradigm overlooks the underlying data distribution p(query), which makes it challenging to identify out-of-distribution data. To address this limitation, we creatively tackle this task from a generative viewpoint and model the correlation between the text and the video as their joint probability p(candidates,query). This is accomplished through a diffusion-based text-video retrieval framework (Diffusion-Ret), which models the retrieval task as a process of gradually generating joint distribution from noise. During training, DiffusionRet is optimized from both the generation and discrimination perspectives, with the generator being optimized by generation loss and the feature extractor trained with contrastive loss. In this way, DiffusionRet cleverly leverages the strengths of both generative and discriminative methods. Extensive experiments on five commonly used text-video retrieval benchmarks, including MSRVTT, LSMDC, MSVD, ActivityNet Captions, and DiDeMo, with superior performances, justify the efficacy of our method. More encouragingly, without any modification, DiffusionRet even performs well in out-domain retrieval settings. We believe this work brings fundamental insights into the related fields. Code is available at https://***/jpthu17/DiffusionRet.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Explainable machine learning models for estimating daily dissolved oxygen concentration of the Tualatin River

引用

engineering Applications of Computational Fluid Mechanics 2024年第1期18卷

作者： Li, Shuguang Qasem, Sultan Noman Band, Shahab S. Ameri, Rasoul Pai, Hao-Ting Mehdizadeh, Saeid School of Computer Science and Technology Shandong Technology and Business University Yantai China Computer Science Department College of Computer and Information Sciences Imam Mohammad Ibn Saud Islamic University (IMSIU) Riyadh Saudi Arabia Computer Science Department Faculty of Applied Science Taiz University Taiz Yemen Future Technology Research Center National Yunlin University of Science and Technology Douliu Taiwan Department of Information Management International Graduate School of Artificial Intelligence National Yunlin University of Science and Technology Douliu Taiwan Department of Information Management National Yunlin University of Science and Technology Douliu Taiwan Bachelor Program of Big Data Applications in Business National Pingtung University Pingtung Taiwan Water Engineering Department Urmia University Urmia Iran

Monitoring the quality of river water is of fundamental importance and needs to be taken into consideration when it comes to the research into the hydrological field. In this context, the concentration of the dissolved oxygen (DO) is one of the most significant indicators of the quality of river water. The current study aimed to estimate the minimum, maximum, and mean DO concentrations (DO min, DO max, DO mean) at a gauging station located on Tualatin River, United States. To that end, four machine learning models, such as support vector regression (SVR), multi-layer perceptron (MLP), random forest (RF), and gradient boosting (GB) were established. Root mean square error (RMSE), mean absolute error (MAE), coefficient of correlation (R), and Nash-Sutcliffe efficiency (NSE) metrics were employed to better assess the accuracies of these models. The modeling results demonstrated that the SVR and MLP surpassed the RF and GB models. Despite this, the SVR was concluded to be the best-performing method when used to estimate the DO min, DO max, and DO mean. The best error statistics in the testing phase were related to the SVR model with full (four) inputs to estimate DO mean concentration (RMSE = 0.663 mg/l, MAE = 0.508 mg/l, R = 0.945, NSE = 0.875). Finally, the explainability of the superior models (i.e. SVR models) was conducted using SHapley Additive exPlanations (SHAP) for the first time to estimate DO concentration. In fact, evaluating the explainability of machine learning models can provide useful information about the impact of each of the input estimators used in the procedure of models development. It was concluded that the specific conductance (SC) and followed by water temperature (WT) could provide the most contributions for estimating the DO min, DO max, and DO mean concentrations. © 2024 The Author(s). Published by Informa UK Limited, trading as Taylor & Francis Group.

关键词： dissolved oxygen concentration estimation Explainable machine learning SHapley additive explanations

来源：评论

学校读者我要写书评

暂无评论

Machine Learning Techniques for Improving Multiclass Anomaly Detection on Conveyor Belts

Machine Learning Techniques for Improving Multiclass Anomaly...

引用

IEEE Instrumentation and Measurement Technology Conference

作者： Saulo N. Matos Otávio F. Coletti Rafael Zimmer Fernando U. Filho Ricardo C.C. L. de Carvalho Victor R. da Silva Jorge L. Franco Thomas V. B. Pinto Luiz G. D. de Barros Caetano M. Ranieri Bruno E. Lopes Diego F. Silva Jó Ueyama Gustavo Pessin Institute of Mathematics and Computer Science University of Sã o Paulo Brazil São Carlos School of Engineering University of São Paulo Brazil Vale Institute of Technology Ouro Preto Brazil Graduate Program in Electrical Engineering Universidade Federal of Minas Gerais Belo Horizonte MG Brazil Vale SA Vitória Brazil

ISBN: (数字)9798350380903

ISBN: (纸本)9798350380910

Industrial conveyor belt systems are an efficient means of transport due to their adaptability and extension. Nonetheless, such systems are prone to various failures, including but not limited to: idler anomalies; belt tears; and pin misalignment which can cause significant disruptions in the production process. Preemptive maintenance and health monitoring of these conveyor belts is a common practice for avoiding these failures, but a challenging task due to the rarity of comprehensive anomaly detection datasets in the area, with current works aimed at evaluating the belt's immediate condition at fixed points. This study addresses this research gap by comparing multiple machine learning techniques, such as a proposed Hybrid Neural Network (HNN) tailored for classification of multiple anomaly classes, as well as machine learning approaches for time series based on feature extraction, Catch22, Minirocket Arsenal, and Time Series Forest. Our proposed HNN architecture performed better in classifying and distinguishing between different types of anomalies, with an accuracy of 95.55%. The obtained results suggest a promising approach for the area of predictive maintenance for industrial conveyor systems, as well as gives insights on possible improvements on the model and future research.

关键词： Machine learning algorithms Accuracy Time series analysis Machine learning Belts Transformers Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Invasive or More Direct Measurements Can Provide an Objective Early-Stopping Ceiling for Training Deep Neural Networks on Non-invasive or Less-Direct Biomedical Data

引用

SN computer science 2023年第2期4卷 161页

作者： Bartlett, Christopher W. Bossenbroek, Jamie Ueyama, Yukie McCallinhart, Patricia Peters, Olivia A. Santillan, Donna A. Santillan, Mark K. Trask, Aaron J. Ray, William C. Department of Pediatrics The Ohio State University College of Medicine Columbus OH United States The Steve and Cindy Rasmussen Institute for Genomic Medicine Battelle Center for Computational Biology The Abigail Wexner Research Institute at Nationwide Children’s Hospital Columbus OH United States Department of Computer Science and Engineering The Ohio State University College of Engineering Columbus OH United States Center for Cardiovascular Research The Abigail Wexner Research Institute at Nationwide Children’s Hospital Columbus OH United States Department of Obstetrics & Gynecology University of Iowa Hospitals & Clinics Iowa City IA United States The Interdisciplinary Graduate Program in Biophysics The Ohio State University Graduate School Columbus OH United States

Early stopping is an extremely common tool to minimize overfitting, which would otherwise be a cause of poor generalization of the model to novel data. However, early stopping is a heuristic that, while effective, primarily relies on ad hoc parameters and metrics. Optimizing when to stop remains a challenge. In this paper, we suggest that for some biomedical applications, a natural dichotomy of invasive/non-invasive measurements, or more generally proximal vs distal measurements of a biological system can be exploited to provide objective advice on early stopping. We discuss the conditions where invasive measurements of a biological process should provide better predictions than non-invasive measurements, or at best offer parity. Hence, if data from an invasive measurement are available locally, or from the literature, that information can be leveraged to know with high certainty whether a model of non-invasive data is overfitted. We present paired invasive/non-invasive cardiac and coronary artery measurements from two mouse strains, one of which spontaneously develops type 2 diabetes, posed as a classification problem. Examination of the various stopping rules shows that generalization is reduced with more training epochs and commonly applied stopping rules give widely different generalization error estimates. The use of an empirically derived training ceiling is demonstrated to be helpful as added information to leverage early stopping in order to reduce overfitting. © 2023, The Author(s).

关键词： Health Invasive Machine learning Model Non-invasive Overfitting

来源：评论

学校读者我要写书评

暂无评论

A Multi-phase Deep Learning Approach for Predicting HCC Response to TACE using Complete Computed Tomography

A Multi-phase Deep Learning Approach for Predicting HCC Resp...

引用

Data science and engineering in Healthcare, Medicine and Biology, IEEE EMBS Special Topic Conference on

作者： Shun Cheng Chang Chien Fu Liu Marta Misztal Yi Hsien Hsieh Che Lin Graduate Institute of Communication Engineering National Taiwan University (NTU) Taiwan School of Electronic Engineering and Computer Science Queen Mary University of London UK Department of Electrical Engineering NTU Taiwan Center for Computational and Systems Biology and Center for Biotechnology NTU Taiwan Smart Medicine and Health Informatics Program NTU Taiwan

In this research study, we compare the predictive performance of two advanced deep learning-based models in order to provide a solution to TACE (Transarterial Chemoembolization) response prediction in HCC (Hepatocellular Carcinoma) patients. Using entire abdominal CT scans enabled a broader perspective available for the model, eliminating the need for segmentation during the preprocessing. Making use of both single-phase and multi-phase CT imaging, we have used DenseNet121 and have obtained an accuracy of 80% for the multi-phase *** Relevance: The ability to predict the effectiveness of TACE treatment prior to its administration makes it possible to provide a better decision-making aid for physicians and patients.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Diffusion-based Reinforcement Learning for Edge-enabled AI-Generated Content Services

TechRxiv

引用

TechRxiv 2023年

作者： Du, Hongyang Li, Zonghang Niyato, Dusit Kang, Jiawen Xiong, Zehui Huang, Huawei Mao, Shiwen School of Computer Science and Engineering The Energy Research Institute @ NTU Interdisciplinary Graduate Program Nanyang Technological University Singapore School of Information and Communication Engineering University of Electronic Sciences and Technology of China Chengdu China School of Automation Guangdong University of Technology China Pillar of Information Systems Technology and Design Singapore University of Technology and Design Singapore School of Software Engineering Sun Yat-Sen University Zhuhai China Department of Electrical and Computer Engineering Auburn University Auburn United States

As Metaverse emerges as the next-generation Internet paradigm, the ability to efficiently generate content is paramount. AI-Generated Content (AIGC) emerges as a key solution, yet the resource-intensive nature of large Generative AI (GAI) models presents challenges. To address this issue, we introduce an AIGC-as-a-Service (AaaS) architecture, which deploys AIGC models in wireless edge networks to ensure broad AIGC services accessibility for Metaverse users. Nonetheless, an important aspect of providing personalized user experiences requires carefully selecting AIGC Service Providers (ASPs) capable of effectively executing user tasks, which is complicated by environmental uncertainty and variability. Addressing this gap in current research, we introduce the AI-Generated Optimal Decision (AGOD) algorithm, a diffusion model-based approach for generating the optimal ASP selection decisions. Integrating AGOD with Deep Reinforcement Learning (DRL), we develop the Deep Diffusion Soft Actor-Critic (D2SAC) algorithm, enhancing the efficiency and effectiveness of ASP selection. Our comprehensive experiments demonstrate that D2SAC outperforms seven leading DRL algorithms. Furthermore, the proposed AGOD algorithm has the potential for extension to various optimization problems in wireless networks, positioning it as a promising approach for future research on AIGC-driven services. The implementation of our proposed method is available at: https://***/Lizonghang/AGOD. © 2023, CC BY.

关键词： Reinforcement learning

来源：评论

学校读者我要写书评

暂无评论

Evaluating Conveyor Belt Health With Signal Processing Applied to Inertial Sensing

Evaluating Conveyor Belt Health With Signal Processing Appli...

引用

International Workshop on Secure Internet of Things (SIoT)

作者： Saulo Neves Matos Otávio Ferracioli Coletti Fernando Ugucioni Filho Ricardo C. C. L. de Carvalho Thomas V. B. Pinto Luiz G. D. de Barros Caetano Mazzoni Ranieri Bruno Eduardo Lopes Jó Ueyama Gustavo Pessin Institute of Mathematics and Computer Science University of sao Paulo Brazil Sao Carlos School of Engineering University of Sao Paulo Brazil Vale Institute of Technology Ouro Preto Brazil Graduate Program in Electrical Engineering Universidade Federal of Minas Gerais Belo Horizonte MG Brazil Vale -SA Vitoria Brazil

Conveyor belts are commonly used in the mining industry for efficient material transport. However, they are prone to failures such as idler anomalies, belt tears, and misalignment. Current monitoring systems only evaluate the conveyor or idle belt's condition at the installation point. This study proposes a method to detect faults in conveyor belts, specifically idler anomalies and belt deviation, using two IMUs installed at the lateral extremities of the belt to evaluate its health along its route. In a reduced-scale conveyor belt, we conducted experiments by collecting gyroscopes and accelerometer data in various scenarios, including normal conditions and anomaly situations. We modified the idlers' physical structure or changed the belt tracks to create these scenarios. We used similarity analysis techniques to compare the data collected and performed statistical hypothesis analysis to observe the influence of the anomaly scenarios on the gyroscope and accelerometer data. We used Dynamic Time Warping (DTW) for gyroscope data to compare ground truth with anomaly scenarios. For the acceleration data, we performed vibration analysis by converting the time domain data to the frequency using Fast Fourier Transform (FFT) and evaluating the difference in spectral density between the reference and anomaly data. Statistical hypothesis analysis revealed that anomaly scenar-ios influenced the gyroscope x-axis and z-axis more. According to the spectral density analysis of the accelerometer, it was revealed that belt misalignment on the y-axis may be detected.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Characterizations of Second-order Nonlinear Optical Susceptibility for ϵ-phase Gallium Oxide

Characterizations of Second-order Nonlinear Optical Suscepti...

引用

2022 Compound Semiconductor Week, CSW 2022

作者： Zhou, Jingan Zhao, Xuan Xu, Rui Fu, Kai Li, Tao Xu, Mingfei He, Ziyi Robinson, Jacob T. Zhu, Hanyu Zhang, Xiaodong Zhao, Yuji Rice University Department of Electrical and Computer Engineering HoustonTX77005 United States Rice University Smalley-Curl Institute Applied Physics Graduate Program HoustonTX77005 United States Rice University Department of Materials Science and NanoEngineering HoustonTX77005 United States Arizona State University School of Electrical Computer and Energy Engineering TempeAZ85287 United States Suzhou Institute of Nano-tech and Nano-bionics CAS Key Laboratory of Nanodevices and Applications Suzhou215123 China

ISBN: (数字)9781665453400

ISBN: (纸本)9781665453400

In this work, we report the second-order nonlinear optical susceptibility χ(2) for epsilon phase Gallium Oxide (ϵ-Ga2O3) thin film on sapphire. ϵ-Ga2O3 exhibits hexagonal P63mc space group symmetry, which is a non-centrosymmetric structure with non-zero second order susceptibility. By focusing a pulsed laser beam on to a polished ϵ-Ga2O3 thin film, we collected the generated second harmonic photons with an ultra-sensitive femtowatt photodetector, obtaining effective second-order nonlinear optical susceptibility of χ(2) = 4.89×10-3 pm/V at wavelength of 800 nm. Two different measurement systems collecting reflected and transmitted photons were applied separately to make the result more convincing. The wavelength dependence from 790 nm to 900 nm and polarization dependence from TM mode to TE mode were measured as well. These results will be helpful for the design and fabrication of Ga2O3 based integrated photonics platform in the infrared-visible spectral range. © 2022 IEEE.

关键词： Gallium compounds

来源：评论

学校读者我要写书评

暂无评论

Video-Text as Game Players: Hierarchical Banzhaf Interaction for Cross-Modal Representation Learning

Video-Text as Game Players: Hierarchical Banzhaf Interaction...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Peng Jin Jinfa Huang Pengfei Xiong Shangxuan Tian Chang Liu Xiangyang Ji Li Yuan Jie Chen School of Electronic and Computer Engineering Peking University Shenzhen China AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School Shenzhen China Shopee Shenzhen China Department of Automation and BNRist Tsinghua University Beijing China Peng Cheng Laboratory Shenzhen China

Contrastive learning-based video-language representation learning approaches, e.g., CLIP, have achieved outstanding performance, which pursue semantic interaction upon pre-defined video-text pairs. To clarify this coarse-grained global interaction and move a step further, we have to encounter challenging shell-breaking interactions for fine-grained cross-modal learning. In this paper, we creatively model video-text as game players with multivariate cooperative game theory to wisely handle the uncertainty during fine-grained semantic interaction with diverse granularity, flexible combination, and vague intensity. Concretely, we propose Hierarchical Banzhaf Interaction (HBI) to value possible correspondence between video frames and text words for sensitive and explainable cross-modal contrast. To efficiently realize the cooperative game of multiple video frames and multiple text words, the proposed method clusters the original video frames (text words) and computes the Banzhaf Interaction between the merged tokens. By stacking token merge modules, we achieve cooperative games at different semantic levels. Extensive experiments on commonly used text-video retrieval and video-question answering bench-marks with superior performances justify the efficacy of our HBI. More encouragingly, it can also serve as a visualization tool to promote the understanding of cross-modal interaction, which have a far-reaching impact on the community. Project page is available at https://***/HBI/.

关键词：

来源：评论

学校读者我要写书评

暂无评论

ACSeg: Adaptive Conceptualization for Unsupervised Semantic Segmentation

ACSeg: Adaptive Conceptualization for Unsupervised Semantic ...

引用

Conference on computer Vision and Pattern Recognition (CVPR)

作者： Kehan Li Zhennan Wang Zesen Cheng Runyi Yu Yian Zhao Guoli Song Chang Liu Li Yuan Jie Chen School of Electronic and Computer Engineering Peking University Shenzhen China AI for Science (AI4S)-Preferred Program Peking University Shenzhen Graduate School Shenzhen China Peng Cheng Laboratory Shenzhen China Dalian University of Technology Department of Automation and BNRist Tsinghua University Beijing China

Recently, self-supervised large-scale visual pre-training models have shown great promise in representing pixel-level semantic relationships, significantly promoting the development of unsupervised dense prediction tasks, e.g., unsupervised semantic segmentation (USS). The extracted relationship among pixel-level representations typically contains rich class-aware information that semantically identical pixel embeddings in the representation space gather together to form sophisticated concepts. However, leveraging the learned models to ascertain semantically consistent pixel groups or regions in the image is non-trivial since over/ under-clustering overwhelms the conceptualization procedure under various semantic distributions of different images. In this work, we investigate the pixel-level semantic aggregation in self-supervised ViT pre-trained models as image Segmentation and propose the Adaptive Conceptualization approach for USS, termed ACSeg. Concretely, we explicitly encode concepts into learnable prototypes and design the Adaptive Concept Generator (ACG), which adaptively maps these prototypes to informative concepts for each image. Meanwhile, considering the scene complexity of different images, we propose the modularity loss to optimize ACG independent of the concept number based on estimating the intensity of pixel pairs belonging to the same concept. Finally, we turn the USS task into classifying the discovered concepts in an unsupervised manner. Extensive experiments with state-of-the-art results demonstrate the effectiveness of the proposed ACSeg.

关键词：

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：