检索结果-内蒙古大学图书馆

arXiv 2024年

作者： Rajakumar, Joel Watson, James D. Joint Center for Quantum Information & Computer Science National Institute of Standards & Technology University of Maryland College Park United States Department of Computer Science Institute for Advanced Computer Studies University of Maryland College Park United States

Sampling from Gibbs states — states corresponding to system in thermal equilibrium — has recently been shown to be a task for which quantum computers are expected to achieve super-polynomial speed-up compared to classical computers, provided the locality of the Hamiltonian increases with the system size [BCL24]. We extend these results to show that this quantum advantage still occurs for Gibbs states of Hamiltonians with O(1)-local interactions at constant temperature by showing classical hardness-of-sampling and demonstrating such Gibbs states can be prepared efficiently using a quantum computer. In particular, we show hardness-of-sampling is maintained even for 5-local Hamiltonians on a 3D lattice. We additionally show that the hardness-of-sampling is robust when we are only able to make imperfect measurements. Copyright © 2024, The Authors. All rights reserved.

关键词： Quantum computers

来源：评论

学校读者我要写书评

暂无评论

Segmenting Anything in the Dark via Depth Perception

引用

IEEE Transactions on Multimedia 2025年 27卷 2975-2986页

作者： Liu, Peng Deng, Jinhong Duan, Lixin Li, Wen Lv, Fengmao University of Electronic Science and Technology of China Chengdu611731 China University of Electronic Science and Technology of China School of Computer Science and Engineering Chengdu611731 China UESTC Shenzhen Institute for Advanced Study Shenzhen518110 China University of Electronic Science and Technology of China Sichuan Provincial Key Laboratory for Human Disease Gene Study Center for Medical Genetics Department of Laboratory Medicine Sichuan Academy of Medical Sciences Sichuan Provincial People's Hospital Chengdu610032 China Southwest Jiaotong University Engineering Research Center of Sustainable Urban Intelligent Transportation Ministry of Education School of Computing and Artificial Intelligence Chengdu611756 China

Image segmentation under low-light conditions is essential in real-world applications, such as autonomous driving and video surveillance systems. The recent Segment Anything Model (SAM) exhibits strong segmentation capability in various vision applications. However, its performance could be severely degraded under low-light conditions. On the other hand, multimodal information has been exploited to help models construct more comprehensive understanding of scenes under low-light conditions by providing complementary information (e.g., depth). Therefore, in this work, we present a pioneer attempt that elevates a unimodal vision foundation model (e.g., SAM) to a multimodal one, by efficiently integrating additional depth information under low-light conditions. To achieve that, we propose a novel method called Depth Perception SAM (DPSAM) based on the SAM framework. Specifically, we design a modality encoder to extract the depth information and the Depth Perception Layers (DPLs) for mutual feature refinement between RGB and depth features. The DPLs employ the cross-modal attention mechanism to mutually query effective information from both RGB and depth for the subsequent feature refinement. Thus, DPLs can effectively leverage the complementary information from depth to enrich the RGB representations and obtain comprehensive multimodal visual representations for segmenting anything in the dark. To this end, our DPSAM maximally maintains the instinct expertise of SAM for RGB image segmentation and further leverages on the strength of depth for enhanced segmenting anything capability, especially for cases that are likely to fail with RGB only (e.g., low-light or complex textures). As demonstrated by extensive experiments on four RGBD benchmark datasets, DPSAM clearly improves the performance for the segmenting anything performance in the dark, e.g., +12.90% mIoU and +16.23% mIoU on LLRGBD and DeLiVER, respectively. © 1999-2012 IEEE.

关键词： Image segmentation

来源：评论

学校读者我要写书评

暂无评论

STMAE: Spatial Temporal Masked Auto-Encoder for Traffic Forecasting 27th

STMAE: Spatial Temporal Masked Auto-Encoder for Traffic For...

引用

27th International Conference on Pattern Recognition, ICPR 2024

作者： Wu, Xing Cai, Chengyou Wang, Xiaoxiao Wang, Jianjia Yao, Junfeng Qian, Quan Song, Jun School of Computer Engineering and Science Shanghai University Shanghai China Shanghai Institute for Advanced Communication and Data Science Shanghai University Shanghai China Shanghai Shentong Metro Co. Ltd. Shanghai China School of AI and Advanced Computing XJTLU Entrepreneur College Xi’an Jiaotong-Liverpool University Suzhou China CSSC Seago System Technology Co. Ltd. Shanghai China Department of Geography Hong Kong Baptist University Hong Kong

ISBN: (纸本)9783031781681

The advancement of intelligent transportation systems underscores the importance of data-driven approaches in traffic forecasting, which plays a crucial role in tasks such as traffic signal control and route guidance, among others. However, the inherent uncertainty stemming from regional traffic dynamics, coupled with intricate spatio-temporal correlations, poses formidable challenges to accurate traffic prediction. Moreover, the complexities inherent in sequence forecasting across varying scales further exacerbate the accuracy dilemma. Recognizing the need for integrating information across spatial and temporal dimensions to enhance forecasting precision, a novel solution termed Spatial Temporal Masked Autoencoder (STMAE) is introduced. The STMAE framework addresses these challenges through a two-stage learning process. In the pre-training phase, an autoencoder architecture is employed to extract spatio-temporal features from the data. In the fine-tuning phase, the pre-trained encoder of the STMAE model undergoes further refinement to specifically target traffic forecasting tasks. Extensive evaluations validate the effectiveness of the proposed STMAE model. Notably, STMAE demonstrates competitive performance, achieving 3.32 Vehs MAE for long-term (60 min) traffic forecasting while operating within a reduced computational budget. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Budget control

来源：评论

学校读者我要写书评

暂无评论

Microteaching: Binary Heaps, Side-Channel Attacks, Equitable Grading, Java Classes, Loops, and 3D Java 2024

Microteaching: Binary Heaps, Side-Channel Attacks, Equitable...

引用

55th ACM Technical Symposium on computer science Education, SIGCSE 2024

作者： Lewis, Colleen M. Bailey Lee, Cynthia Blank, Adam Camarena, Maria Hernandez, Manuel Vahid, Frank Computer Science Department Univ. of Illinois Urbana-Champaign UrbanaIL United States Computer Science Department Stanford University StanfordCA United States Computing and Mathematical Sciences California Institute of Technology PasadenaCA United States Maywood Center for Enriched Studies Los Angeles Unified School District MaywoodCA United States Mathematics Department Bell Gardens High School Musd and Math for America - Los Angeles Bell GardensCA United States Computer Science and Engineering University of California Riverside RiversideCA United States

ISBN: (纸本)9798400704246

This microteaching session is like Nifty Assignments for instruction. Instead of having the presenters just talk about their teaching, they will simulate how they would actually teach something. Covering a range of topics and grade levels, six educators will demo how they would teach a specific topic. To help identify the pedagogical practices that cut across grade bands and topics, the moderator, Colleen Lewis, will describe how their pedagogical practices connect with education research. The goal of the session is to inspire SIGCSE attendees by highlighting innovative instruction by exceptional educators. Attendees can adopt the content and/or pedagogical practices from each microteaching example. © 2024 Owner/Author.

关键词： Side channel attack

来源：评论

学校读者我要写书评

暂无评论

Sound Tagging in Infant-centric Home Soundscapes

Sound Tagging in Infant-centric Home Soundscapes

引用

IEEE International Conference on Connected Health: Applications, Systems and Engineering Technologies (CHASE)

作者： Mohammad Nur Hossain Khan Jialu Li Nancy L. McElwain Mark Hasegawa–Johnson Bashima Islam Department of Electrical and Computer Engineering Worcester Polytechnic Institute Department of Electrical and Computer Engineering University of Illinois Department of Human Development and Family Studies University of Illinois Beckman Institute for Advanced Science and Technology University of Illinois

ISBN: (数字)9798350345018

ISBN: (纸本)9798350345025

Certain environmental noises have been associated with negative developmental outcomes for infants and young children. Though classifying or tagging sound events in a domestic environment is an active research area, previous studies focused on data collected from a non-stationary microphone placed in the environment or from the perspective of adults. Further, many of these works ignore infants or young children in the environment or have data collected from only a single family where noise from the fixed sound source can be moderate at the infant's position or vice versa. Thus, despite the recent success of large pre-trained models for noise event detection, the performance of these models on infant-centric noise soundscapes in the home is yet to be explored. To bridge this gap, we have collected and labeled noises in home soundscapes from 22 families in an unobtrusive manner, where the data are collected through an infant-worn recording device. In this paper, we explore the performance of a large pre-trained model (Audio Spectrogram Transformer [AST]) on our noise-conditioned infant-centric environmental data as well as publicly available home environmental datasets. Utilizing different training strategies such as resampling, utilizing public datasets, mixing public and infant-centric training sets, and data augmentation using noise and masking, we evaluate the performance of a large pre-trained model on sparse and imbalanced infant-centric data. Our results show that fine-tuning the large pre-trained model by combining our collected dataset with public datasets increases the F1-score from 0.11 (public datasets) and 0.76 (collected datasets) to 0.84 (combined datasets) and Cohen's Kappa from 0.013 (public datasets) and 0.77 (collected datasets) to 0.83 (combined datasets) compared to only training with public or collected datasets, respectively.

关键词： Training Performance evaluation Pediatrics Working environment noise Noise Tagging Transformers

来源：评论

学校读者我要写书评

暂无评论

Integrating Deep Learning in Project Management: Improving Efficiency and Effectiveness in Project Planning and Execution 4

Integrating Deep Learning in Project Management: Improving E...

引用

4th IEEE Asian Conference on Innovation in Technology, ASIANCON 2024

作者： Shukla, Sunil Singh, Jagendra Sahu, Hemant Kanthalia, Shilpa Taufikin Elangovan, Muniyandy Graphic Era Hill University School of Computing Dehradun India Bennett University School of Computer Science Engineering & Technology Greater Noida India Department of Cs & It Udaipur India Faculty of Management Studies Udaipur India Kudus Department of Postgraduate Kudus Indonesia Saveetha Institute of Medical and Technical Sciences Saveetha School of Engineering Department of Biosciences Chennai India

ISBN: (纸本)9798350354218

The purpose of this research is to explore the use of deep learning technologies, namely the K-Nearest Neighbors model within the textile manufacturing process to test the improvement of the said process. To properly implement the model, we must use real-time data from the process and evaluate the improvement depending on a number of factors: how much does the maintenance cost decrease, how accurate is the inventory management, and how well the program forecasts demand, all of which should lead to an improvement of profit. First, the analysis of the results proved that the implementation of KNN model leads to a significant decrease of maintenance costs: while without the model the reduction was 15%, with it cost maintenance cost a 25% decrease. Second, the usage of a model improves inventory management accuracy: before the use of KNN, it was 85%, while after it rose to 95%. Third, demand forecasting becomes more accurate, as the difference was 75% to the positive without the model and 90% with it. The use of a model improved all aspects, and the most improved was profit: before the implementation of the KNN model, profit was 10%, and it was 40% after, which led to the conclusion that the implementation of deep learning models, namely the KNN model, improves the effectiveness of textile manufacturing process and positively affects the profitability and the production process as a whole. © 2024 IEEE.

关键词： Inventory control

来源：评论

学校读者我要写书评

暂无评论

A systematic assessment and meta-analysis of machine learning methods for predicting and Classifying severe Long Term kidney disease

A systematic assessment and meta-analysis of machine learnin...

引用

New Frontiers in Communication, Automation, Management and Security (ICCAMS), International Conference on

作者： Shibi Mathai K.S. Thirunavukkarasu Department of Computer Application St.Thomas College of Arts and Science Chennai India Department of Computer Science Vels Institute of Science Technology and Advanced Studies Chennai India

ISBN: (数字)9798350317060

ISBN: (纸本)9798350317077

Heart failure (HF), atherosclerotic cardiovascular disease, and end-stage kidney disease are all signs of long term kidney disease brought on by type II diabetes (CKD). However, because it has no symptoms, CKD is frequently overlooked or misdiagnosed. Without kidneys, a human beings can able live for about 18 days, necessitating dialysis and a kidney transplant. It is complex to have accurate tools for early diagnosis of kidney diseases. Additionally, patients frequently forego the common urine protein-based CKD detection test. It describes a medical condition that damages the kidneys and has an impact on the body as a whole. Inadequate diagnosis and care can lead to end-stage renal disease, which eventually kills the patient. In response to the shortcomings of conventional biomarkers and the requirement for early therapeutic intervention in cats with CKD to improve outcomes, new renal biomarkers for the detection of glomerular or tubular dysfunction have been discovered and validated. Changes in the concentrations of these biomarkers in the blood or urine may reveal early kidney damage or forecast the development of kidney disease before changes in conventional biomarkers can be seen. On Utilization of machine learning (ML) approaches, CKD prediction is simple. The method of the present study for predicting long term kidney disease and classifying it on basis of the clinical diagnosis information includes data preprocessing, a method for handling missing data, feature reduction and feature extraction. We examine some recent works on ML-based CKD detection and classification in this systematic review. It analyze of the step of data processing from data collection to data classification on utilizing the dataset preprocessing step, hybrid or ensemble feature extraction technique, meta-heuristics based feature selection technique and finally detection and classification of the kidney disease. To be more precise, we group this systematic review into two important types:

关键词： Systematics Reviews Supervised learning Machine learning Biomarkers Feature extraction Chronic kidney disease

来源：评论

学校读者我要写书评

暂无评论

Literature review on sentiment analysis in tourism

引用

Test Engineering and Management 2020年 83卷 2466-2474页

作者： Devi, Chingakham Nirma Renuga Devi, R. Department of Computer Science Vels Institute of Science Technology and Advanced Studies Chennai India

Tourism is growing to be a crucial source of income across globe. As a source of socio-economic phenomenon, tourism has evolved into one of the greatest and fastest growing industries of the world. The vital part to collect the data is often appearing as what the people assume. Most users express their views and opinions relating to products and services through social *** opinions are subjective info that represents user's sentiments, feelings or appraisal associated with a similar. Nowadays, millions of people travel around the globe for business, vacations, sightseeing, or alternative reasons for their need. Tourists will currently have the opportunity from different data sources, and that create their own content and share their aspects and experiences. Through internet, tourism content shared has an extremely prestigious data that effects *** present, online customer reviews on tourism meant hotels and restaurants which play an important role within the decision making while they were selecting hotels and restaurants destination. © 2020 Mattingley Publishing. All rights reserved.

关键词： Tourism

来源：评论

学校读者我要写书评

暂无评论

Comparison of Machine Learning Models for Injury Prediction in Athletes

Comparison of Machine Learning Models for Injury Prediction ...

引用

2025 International Conference on Visual Analytics and Data Visualization, ICVADV 2025

作者： Murugan, Suganiya Kumar, S. Pradeep Kalaiarasi, G. Saritha, B. Rubini, B. Srm Institute of Science and Technology Department of Computing Technologies Tamil Nadu Chennai India Vels Institute of Science Technology and Advanced Studies Department of Eee Tamil Nadu Chennai India Vignan Foundation for Science Technology and Research Department of Acse Andhrapradesh India Erode Sengunthar Engineering College Thudupathi Erode Department of Biomedical Engineering Tamil Nadu India Vels Institute of Science Technology and Advanced Studies Department of Eee TamilNadu Chennai India

ISBN: (纸本)9798331521394

Running is a favoured exercise for millions, but it carries a risk of musculoskeletal injuries, particularly to the lower extremities. Identifying and predicting potential injuries is crucial for prevention. This study explores the use of machine learning techniques to predict injuries among runners, leveraging data on demographics, running habits, health conditions, and previous injuries. Using models like Random Forest, K-Nearest Neighbours, Decision Trees, and Logistic Regression, the study examines the relevance of various attributes and assesses the predictive power of these models. Remarkably, our model achieved an impressive accuracy of over 99%, setting a new benchmark for predictive precision in injury prevention. Visualizations provide insight into attribute interactions and their influence on injury risk, facilitating the development of targeted prevention strategies. © 2025 IEEE.

关键词： Logistic regression

来源：评论

学校读者我要写书评

暂无评论

Fault Secured JPEG-Codec Hardware Accelerator with Piracy Detective Control using Secure Fingerprint Template

Fault Secured JPEG-Codec Hardware Accelerator with Piracy De...

引用

IEEE International Symposium on Defect and Fault Tolerance in VLSI Systems

作者： Rahul Chaurasia Abhinav Reddy Asireddy Anirban Sengupta Computer Science and Engineering Indian Institute of Technology Indore India Department of Computer Science and Engineering Indian Institute of Technology Indore Advanced Computing and Microelectronics Unit Indian Statistical Institute Kolkata India

This paper presents a novel methodology to design fault secured JPEG-compression-decompression (codec) hardware accelerator with piracy detective control using secure fingerprint template of intellectual property (IP) vendor. In the proposed approach, firstly, the fault secured schedule for JPEG-codec design is generated from its behavioral description. Subsequently, in order to enable detective control against piracy, secure digital template corresponding to fingerprint biometric of IP vendor is generated and implanted into the design. In order to do so, firstly, fingerprint features are transformed based on IP vendor specified key-set. Subsequently, the generated secure fingerprint template in the form of encoded hardware security constraints is implanted into the design during behavioral/ high-level synthesis phase of integrated circuit (IC) design. The implanted hardware security constraints thereby ensure the seamless detection and isolation of fake/pirated design versions during piracy detection process, before their conjunction into system on chip (SoC) of electronic systems. The proposed approach achieves the following: i) fault secured hardware accelerator for JPEG-codec with integrated piracy detective control at negligible design cost overhead ii) higher resiliency against tampering attack and iii) lower probability of coincidence (indicating definitive proof of ownership for genuine IP vendor).

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：