检索结果-内蒙古大学图书馆

arXiv 2023年

作者： Wu, Yanan Chi, Zhixiang Wang, Yang Plataniotis, Konstantinos N. Feng, Songhe Key Laboratory of Big Data & Artificial Intelligence in Transportation Ministry of Education Beijing Jiaotong University Beijing100044 China School of Computer and Information Technology Beijing Jiaotong University Beijing100044 China The Edward S Rogers Sr. ECE Department University of Toronto TorontoM5S3G8 Canada Department of Computer Science and Software Engineering Concordia University MontrealH3G2J1 Canada

Test-time domain adaptation aims to adapt the model trained on source domains to unseen target domains using a few unlabeled images. Emerging research has shown that the label and domain information is separately embedded in the weight matrix and batch normalization (BN) layer. Previous works normally update the whole network naively without explicitly decoupling the knowledge between label and domain. As a result, it leads to knowledge interference and defective distribution adaptation. In this work, we propose to reduce such learning interference and elevate the domain knowledge learning by only manipulating the BN layer. However, the normalization step in BN is intrinsically unstable when the statistics are re-estimated from a few samples. We find that ambiguities can be greatly reduced when only updating the two affine parameters in BN while keeping the source domain statistics. To further enhance the domain knowledge extraction from unlabeled data, we construct an auxiliary branch with label-independent self-supervised learning (SSL) to provide supervision. Moreover, we propose a bi-level optimization based on meta-learning to enforce the alignment of two learning objectives of auxiliary and main branches. The goal is to use the auxiliary branch to adapt the domain and benefit main task for subsequent inference. Our method keeps the same computational cost at inference as the auxiliary branch can be thoroughly discarded after adaptation. Extensive experiments show that our method outperforms the prior works on five WILDS real-world domain shift datasets. Our method can also be integrated with methods with label-dependent optimization to further push the performance boundary. Our code is available at https://***/ynanwu/MABN. © 2023, CC BY.

关键词： Time domain analysis

来源：评论

学校读者我要写书评

暂无评论

Sherlock in OSS: A Novel Approach of Content-Based Searching in Object Storage System

arXiv

引用

arXiv 2023年

作者： Noor, Jannatun Ratul, Rizwanul Haque Uday, Mir Rownak Ali Mondal, Joyanta Jyoti Sakif, Md. Sadiqul Islam Islam, A.B.M. Alim Al The Department of CSE Bangladesh University of Engineering and Technology Dhaka Bangladesh Research Group School of Data and Sciences BRAC University Dhaka Bangladesh C2SG Research Group Optimizely Dhaka Bangladesh C2SG Research Group Bangladesh The Department of Computer Science University of Alabama Birmingham United States mPower-Social Enterprise Dhaka Bangladesh Next-generation Computing Research Group Department of CSE Bangladesh University of Engineering and Technology Dhaka Bangladesh

Object Storage Systems (OSS) inside a cloud promise scalability, durability, availability, and concurrency. However, open-source OSS does not have a specific approach to letting users and administrators search based on the data, which is contained inside the object storage, without involving the entire cloud infrastructure. Therefore, in this paper, we propose Sherlock, a novel Content-Based Searching (CoBS) architecture to extract additional information from images and documents. Here, we store the additional information in an Elasticsearch-enabled database, which helps us to search for our desired data based on its contents. This approach works in two sequential stages. First, the data will be uploaded to a classifier that will determine the data type and send it to the specific model for the data. Here, the images that are being uploaded are sent to our trained model for object detection, and the documents are sent for keyword extraction. Next, the extracted information is sent to Elasticsearch, which enables searching based on the contents. Because the precision of the models is so fundamental to the search’s correctness, we train our models with comprehensive datasets (Microsoft COCO Dataset for multimedia data and SemEval2017 Dataset for document data). Furthermore, we put our designed architecture to the test with a real-world implementation of an open-source OSS called OpenStack Swift. We upload images into the dataset of our implementation in various segments to find out the efficacy of our proposed model in real-life Swift object storage. © 2023, CC BY-NC-SA.

关键词： Object detection

来源：评论

学校读者我要写书评

暂无评论

Where Shall I Touch? Vision-Guided Tactile Poking for Transparent Object Grasping

arXiv

引用

arXiv 2022年

作者： Jiang, Jiaqi Cao, Guanqun Butterworth, Aaron Do, Thanh-Toan Luo, Shan The smART-Lab Department of Computer Science University of Liverpool LiverpoolL69 3BX United Kingdom Department of Engineering King's College London LondonWC2R 2LS United Kingdom Department of Data Science and AI Monash University ClaytonVIC3800 Australia

Picking up transparent objects is still a challenging task for robots. The visual properties of transparent objects such as reflection and refraction make the current grasping methods that rely on camera sensing fail to detect and localise them. However, humans can handle the transparent object well by first observing its coarse profile and then poking an area of interest to get a fine profile for grasping. Inspired by this, we propose a novel framework of vision-guided tactile poking for transparent objects grasping. In the proposed framework, a segmentation network is first used to predict the horizontal upper regions named as poking regions, where the robot can poke the object to obtain a good tactile reading while leading to minimal disturbance to the object's state. A poke is then performed with a high-resolution GelSight tactile sensor. Given the local profiles improved with the tactile reading, a heuristic grasp is planned for grasping the transparent object. To mitigate the limitations of real-world data collection and labelling for transparent objects, a large-scale realistic synthetic dataset was constructed. Extensive experiments demonstrate that our proposed segmentation network can predict the potential poking region with a high mean Average Precision (mAP) of 0.360, and the vision-guided tactile poking can enhance the grasping success rate significantly from 38.9% to 85.2%. Thanks to its simplicity, our proposed approach could also be adopted by other force or tactile sensors and could be used for grasping of other challenging objects. All the materials used in this paper are available at https://***/view/tactilepoking. Copyright © 2022, The Authors. All rights reserved.

关键词： Large dataset

来源：评论

学校读者我要写书评

暂无评论

Lifetime of photoexcited carriers in space-controlled Si nanopillar/SiGe composite films investigated by a laser heterodyne photothermal displacement method

引用

Journal of Applied Physics 2023年第12期133卷

作者： Harada, Tomoki Ohori, Daisuke Endo, Kazuhiko Samukawa, Seiji Ikari, Tetsuo Fukuyama, Atsuhiko Faculty of Engineering University of Miyazaki 1-1 Gakuen-Kibanadai-Nishi Miyazaki889-2192 Japan Institute of Fluid Science Tohoku University 2-1-1 Katahira Aoba-ku Sendai-shi Miyagi980-8577 Japan Department of Electrical and Computer Engineering National Yang Ming Chiao Tung University Hsinchu30010 Taiwan

Thermal management has become more critical as semiconductor devices are miniaturized. In metal-oxide-semiconductor field-effect transistors, the problem is the reduction in electron mobility in the channel layer owing to the temperature rise caused by heat generation near the channel-drain region. Focusing on the mean free paths of phonons and electrons in Si, nanostructures of a few 10 nm may only hinder heat propagation without affecting electron transportation. Therefore, inserting nanostructures into the channel layer may prevent a temperature rise and maintain a higher electron mobility. To discuss the relationship between the spacing between the nanopillars (NPs) and the heat generation and carrier behavior of the Si-NP/SiGe composite film, samples with NP spacings of 13, 27, or 47 nm were prepared. We previously confirmed that the thermal conductivity of the Si-NP/SiGe composite film decreased as NP spacing narrowed. The NPs scattered phonon propagation and suppressed heat propagation. However, carrier transport properties such as electrical conductivity, carrier mobility, and carrier lifetime have never been discussed. The laser heterodyne photothermal displacement method was used to examine the effect of nanostructures on carrier mobility and carrier lifetime of Si-NP/SiGe composite films. We observed that the carrier lifetime became longer when the NP spacing was comparable to the electron mean-free path of approximately 27 nm. © 2023 Author(s).

关键词： Phonons

来源：评论

学校读者我要写书评

暂无评论

Constrained Optimization with Decision-Dependent Distributions

arXiv

引用

arXiv 2023年

作者： Wang, Zifan Liu, Changxin Parisini, Thomas Zavlanos, Michael M. Johansson, Karl H. Division of Decision and Control Systems School of Electrical Engineering and Computer Science KTH Royal Institute of Technology Sweden Digital Futures StockholmSE-10044 Sweden The Department of Electrical and Electronic Engineering Imperial College London LondonSW7 2AZ United Kingdom The Department of Engineering and Architecture University of Trieste Trieste34127 Italy The KIOS Research and Innovation Center of Excellence University of Cyprus NicosiaCY-1678 Cyprus The Department of Mechanical Engineering and Materials Science Duke University DurhamNC United States

In this paper we deal with stochastic optimization problems where the data distributions change in response to the decision variables. Traditionally, the study of optimization problems with decision-dependent distributions has assumed either the absence of constraints or fixed constraints. This work considers a more general setting where the constraints can also dynamically adjust in response to changes in the decision variables. Specifically, we consider linear constraints and analyze the effect of decision-dependent distributions in both the objective function and constraints. Firstly, we establish a sufficient condition for the existence of a constrained equilibrium point, at which the distributions remain invariant under retraining. Morevoer, we propose and analyze two algorithms: repeated constrained optimization and repeated dual ascent. For each algorithm, we provide sufficient conditions for convergence to the constrained equilibrium point. Furthermore, we explore the relationship between the equilibrium point and the optimal point for the constrained decision-dependent optimization problem. Notably, our results encompass previous findings as special cases when the constraints remain fixed. To show the effectiveness of our theoretical analysis, we provide numerical experiments on both a market problem and a dynamic pricing problem for parking based on real-world data. Copyright © 2023, The Authors. All rights reserved.

关键词： Constrained optimization

来源：评论

学校读者我要写书评

暂无评论

Robust State Estimation in Textureless Scenes Via Rf-Visual-Inertial Fusion for Unmanned Aerial Vehicles

SSRN

引用

SSRN 2024年

作者： Zhang, Shengkai Tang, Sheyang Chen, Mozi Liu, Kezhong He, Jianhua Ma, Jun Xiao, Fei Wang, Wei School of Information Engineering Wuhan University of Technology Gongda Road No. 21 Hubei Wuhan430070 China Department of Electrical and Computer Engineering University of Waterloo 200 University Avenue West WaterlooONN2L 3G1 Canada School of Navigation Wuhan University of Technology Heping Avenue No. 1178 Hubei Wuhan430070 China School of Computer Science and Electronic Engineering University of Essex Wivenhoe Park Essex ColchesterCO4 3SQ United Kingdom Department of Urban Planning and Design The University of Hong Kong Pokfulam Road Hong Kong School of Electronic Information and Communications Huazhong University of Science and Technology Luoyu Road No. 1037 Hubei Wuhan430070 China

The widespread applications of agile micro aerial vehicles (MAVs) require the robust state estimation that works in various complex environments. In particular, working in textureless scenes is one of the missing pieces in the puzzle. Previous solutions either seek a remedy with visual loop closure or leverage RF localizability with inferior accuracy. None of them supports accurate MAV state estimation in textureless scenes. This paper presents RFSift+, a new state estimator that conquers the textureless challenge with RF-referenced monocular vision, achieving centimeter-level accuracy in dark and textureless scenes. Our key observation is that RF and visual measurements are tied up with pose constraints. Mapping RF to feature quality and sift well-matched ones significantly improves accuracy. RFSift+ consists of 1) an RF-sifting algorithm that maps 3D UWB measurements to 2D visual features for sifting the best features;2) an RF bias estimation algorithm that takes the sifted features to reversely estimate the RF bias for better accuracy;3) an RF-visual-inertial sensor fusion algorithm that leverages inertial sensors to combat the occasional loss of visual odometry. We implement the prototype with off-the-shelf products and conduct large-scale experiments. The results demonstrate that RFSift+ is robust in textureless settings, 10× more accurate than the state-of-the-art monocular vision system. © 2024, The Authors. All rights reserved.

关键词： State estimation

来源：评论

学校读者我要写书评

暂无评论

Item Recommendation Using User Feedback Data and Item Profile

arXiv

引用

arXiv 2022年

作者： Roy, Debashish Chowdhury, Rajarshi Roy Nasser, Abdullah Bin Azmi, Afdhal Babaeianjelodar, Marzieh Information Technology Management Ryerson University 350 Victoria Street TorontoONM5B 2K3 Canada Faculty of Integrated Technologies Universiti Brunei Darussalam Jalan Tungku Link GadongBE1410 Brunei Department of Computer Science and Engineering Sylhet International University Shamimabad Road Sylhet3100 Bangladesh School of Technology and Innovation University of Vaasa VaasaFI-65200 Finland Department of Electrical and Computer Engineering Faculty of Engineering Universitas Syiah Kuala Banda Aceh Indonesia Department of Computer Science Clarkson University New York United States

Matrix factorization (MS) is a collaborative filtering (CF) based approach, which is widely used for recommendation systems (RS). In this research work, we deal with the content recommendation problem for users in a content management system (CMS) based on users' feedback data. The CMS is applied for publishing and pushing curated content to the employees of a company or an organization. Here, we have used the users' feedback data and content data to solve the content recommendation problem. We prepare individual user-profiles and then generate recommendation results based on different categories, including Direct Interaction, Social Share and Reading Statistics, of user's feedback data. Subsequently, we analyze the effect of the different categories on the recommendation results. The results have shown that different categories of feedback data have different impacts on recommendation accuracy. The best performance achieves if we include all types of data for the recommendation task. We also incorporate content similarity as a regularization term into an MF model for designing a hybrid model. Experimental results have shown that the proposed hybrid model demonstrates better performance compared with the traditional MF-based models. Copyright © 2022, The Authors. All rights reserved.

关键词： Collaborative filtering

来源：评论

学校读者我要写书评

暂无评论

Generalized diffusion process with nonlocal interactions: Continuous time random walk model and stochastic resetting

arXiv

引用

arXiv 2025年

作者： Trajanovski, Pece Petreska, Irina Górska, Katarzyna Kocarev, Ljupco Sandev, Trifce Research Center for Computer Science and Information Technologies Macedonian Academy of Sciences and Arts Bul. Krste Misirkov 2 Skopje1000 Macedonia Institute of Physics Faculty of Natural Sciences and Mathematics Ss. Cyril and Methodius University Arhimedova 3 Skopje1000 Macedonia Institute of Nuclear Physics Polish Academy of Sciences ul. Radzikowskiego 152 KrakówPL-31342 Poland Faculty of Computer Science and Engineering Ss. Cyril and Methodius University PO Box 393 Skopje1000 Macedonia Department of Physics Korea University Seoul02841 Korea Republic of

A space fractional diffusion-like equation is introduced, which embodies the nonlocality in time, represented by the memory kernel and the non-locality in space. A specific example of the nonlocal term is considered in combination with three different forms of the memory kernel. To analyse the probability density function, we utilize the subordination approach. Subsequently, the corresponding continuous time random walk model is presented. Furthermore, we investigate the effects of the stochastic resetting on the dynamics of the process and we showed that in the long time limit the system approaches a nonequilibrium stationary state. © 2025, CC BY.

关键词： Probability density function

来源：评论

学校读者我要写书评

暂无评论

Performance evaluation of classifiers for non communicable diseases

引用

AIP Conference Proceedings 2023年第1期2523卷

作者： S. Srinivasan S. Selvakumar Pacha Shobha Rani D. JayaKumar 1Department of Computer Science and Engineering R.M.D Engineering College Kavaraipettai Tamil Nadu India 2Department of Computer Science and Engineering Visvesvaraya College of Engineering and Technology Hyderabad Telangana India

Non-Communicable Diseases (NCD) has been drastically increased across the world in the recent years. Diseases that are not transmissible from one person to another are known as Non-Communicable Diseases (NCDs). Parkinson's disease, Autoimmune Disorders, Strokes, Heart Diseases, Cancers, Diabetes are examples of NCDs. It is found that certain Non-Communicable Diseases are believed to be exacerbated by lifestyle and climate which cause of death in the world. Many Machine Learning methods such as Nave Bayes, Support Vector Machine have been applied to predict NCDs. The aim of this paper is to predict the Non-Communicable Diseases (NCDs) and evaluate the performance of the key classifiers in terms of Prediction accuracy, Kappa and F-Measure. The progress in computer training and AI can remarkably help the analysis of Non-Communicable Diseases (NCDs). Nevertheless, the intrinsic complication of black-box samples controls the understanding of the sample. Consequently, likely regulative concerns arise. Furthermore, the lack of faith inside the therapeutic society is obvious due to the absence of understanding of how and why a sample prophesies. This research illustrates how sample-cynical ways of explainable AI (XAI) can assist give descriptions to assume black-box samples on NCDs information collection better.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Object Semantics Give Us the Depth We Need: Multi-task Approach to Aerial Depth Completion

arXiv

引用

arXiv 2023年

作者： Gazani, Sara Hatami Dadboud, Fardad Bolic, Miodrag Mantegh, Iraj Najjaran, Homayoun Department of Mechanical Engineering University of Victoria 3800 Finnerty Road VictoriaBCV8P 5C2 Canada School of Electrical Engineering and Computer Science University of Ottawa 800 King Edward OttawaONK1N 6N5 Canada MontrealQC Canada

Depth completion and object detection are two crucial tasks often used for aerial 3D mapping, path planning, and collision avoidance of Uncrewed Aerial Vehicles (UAVs). Common solutions include using measurements from a LiDAR sensor;however, the generated point cloud is often sparse and irregular and limits the system’s capabilities in 3D rendering and safety-critical decision-making. To mitigate this challenge, information from other sensors on the UAV (viz., a camera used for object detection) is utilized to help the depth completion process generate denser 3D models. Performing both aerial depth completion and object detection tasks while fusing the data from the two sensors poses a challenge to resource efficiency. We address this challenge by proposing a novel approach to jointly execute the two tasks in a single pass. The proposed method is based on an encoder-focused multi-task learning model that exposes the two tasks to jointly learned features. We demonstrate how semantic expectations of the objects in the scene learned by the object detection pathway can boost the performance of the depth completion pathway while placing the missing depth values. Experimental results show that the proposed multi-task network outperforms its single-task counterpart, particularly when exposed to defective inputs. © 2023, CC BY-SA.

关键词： Object detection

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：