检索结果-内蒙古大学图书馆

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Zhenkun Jin Shuai Huang Xin Nie Xinlei Zhou Yuanyuan Yi Gefei Zhou Wuhan Business UIniversity Wuhan China Wuhan Research Institute of Posts and Telecommunications Wuhan China Hubei Key Laboratory of Distributed System Security Wuhan China Hubei Engineering Research Center on BigData Security Wuhan China School of Cyber Science and Engineering Huazhong University of Science and Technology Wuhan China School of Journalism and Information Communication Huazhong University of Science and Technology Wuhan China School of Computer Science and Technology Huazhong University of Science and Technology Wuhan China

In this research, we tackled the complex task of aligning audio and lyrics content automatically. This task entails the precise matching of lyrics with the corresponding audio segments in songs, necessitating the coordination of two distinct modalities: text and audio. To surmount this challenge, we employed a contrastive learning approach that generates cross-modal embeddings capable of establishing connections between the audio and text domains. Furthermore, we adopted a hierarchical and cascading design. Initially, the system predicts synchronization at the sentence level and subsequently refines the alignment at the word level. This design equips the system to handle extended sequences effectively, as cross-correlations leverage secondary memory that corresponds to sequence length. Through this innovative approach, we developed a trainable end-to-end system that can harness weakly annotated training data, concurrently learning a robust text model optimized for alignment tasks. Our experiments demonstrated substantial enhancements in average alignment accuracy when utilizing our proposed system, underscoring its robustness compared to previous state-of-the-art models.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Analysis of Deep Learning Algorithms for Prawn Aquaculture in a Challenging Environment

Analysis of Deep Learning Algorithms for Prawn Aquaculture i...

引用

Applied Computational Intelligence in Information systems (ACIIS), International Conference on

作者： Wafiq Zariful Najeebah Az-Zahra Tashim Tiong Hoo Lim Aida Maryam Basri Suriayati Chuprat Seno Adi Putra Pengcheng Liu Hanif Fakhrurroja Electrical and Electronic Engineering Universiti Teknologi Brunei Bandar Seri Begawan Brunei School of Applied Sciences and Mathematics Universiti Teknologi Brunei Bandar Seri Begawan Brunei Razak Faculty of Technology and Informatics Universiti Teknologi Malaysia Johor Bahru Malaysia School of Industrial and System Engineering Telkom Universiti Bandung Indonesia Department of Computer Science University of York York United Kingdom Research Center for Smart Mechatronics National Research and Innovation Agency Telkom University Bandung Indonesia

Deep Learning plays a vital role in various domains, spanning surveillance, agriculture, and healthcare. However, the current landscape lacks comprehensive comparative studies, underscoring the needs to explore various convolutional neural networks (CNNs) for aquaculture industries. This study conducts a comprehensive comparative analysis on state-of-the-art object detection models to identify the most suitable approach for detecting freshwater prawns, specifically in challenging turbid and murky water conditions as there is a lack of comparison studies for underwater images of freshwater prawns. The evaluated models, including YOLOv8, Faster R-CNN (FRCNN), Single Shot Detector (SSD), and EfficientDet, are assessed based on the following metrics namely inference time, accuracy, image cropping size, and model memory footprint. Using a dataset comprising 2976 manually collected images of freshwater prawns, augmented to a total of 7148 images, our results demonstrate that YOLOv8 outperforms its counterparts, achieving an impressive mean Average Precision (mAP) accuracy of 83.71% with an inference time of 32.9 milliseconds. This positions YOLOv8 as a dependable choice for real-time object detection in challenging underwater environments and contributes to addressing the limited research comparing YOLOv8 with other popular object detection algorithms, thereby aiding model selection for similar object detection applications.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Studying of Machine Learning Models for Forecasting Macroeconomic Indicators

Studying of Machine Learning Models for Forecasting Macroeco...

引用

International Conference on Advanced Communication Technology (ICACT)

作者： Lan Dong Thi Ngoc Ngo-Thi-Thu-Trang Kyoung-Mok Kim Vung Pham Ha-Nam Nguyen Department of Economic Information System Academy of Finance Hanoi Viet Nam Faculty of Information Technology University of Engineering and Technology Vietnam National University Hanoi Viet Nam Posts and Telecommunications Institute of Technology Hanoi CO Vietnam Department of Medical Information Sahmyook Health University Seoul Republic of Korea Computer Science Department Sam Houston State University Huntsville Texas TX USA Faculty of Information Technology Electric Power University Hanoi Viet Nam

ISBN: (数字)9791188428137

ISBN: (纸本)9798331507602

This study explores the application of machine learning models in forecasting macro-economic indicators, including GDP, inflation rate, unemployment rate, and exchange rate across 11 Southeast Asian countries. The models used include Linear Regression, ARIMA, Random Forest, XGBoost, LSTM, and SVM. We conducted a performance comparison of each model based on MAE, RMSE, and R 2 metrics to evaluate the accuracy of the *** experimental results indicate that Random Forest and XGBoost models excel in predicting nonlinear and complex indicators such as GDP and unemployment rate, while ARIMA and Linear Regression models perform better in time series with clear regular patterns, like inflation rate. The LSTM model shows inconsistent effective-ness, requiring large data volumes and complex optimization processes. SVM demonstrates potential in handling nonlinear data but requires careful *** study concludes that using machine learning models presents significant potential for improving the accuracy of macroeconomic forecasting. However, model tuning and optimization are essential to match the characteristics of each type of economic indicator. Future research directions include developing hybrid models and integrating additional factors such as market sentiment, social and environmental indicators (ESG) to enhance forecasting outcomes.

关键词： Support vector machines Economic indicators Biological system modeling Predictive models Macroeconomics Forecasting Unemployment Random forests Optimization Long short term memory

来源：评论

学校读者我要写书评

暂无评论

Application of Multispectral Data and Machine Learning Technology in Estimating Soil Organic Carbon in Forest Ecosystems

引用

International Journal of High Speed Electronics and systems 2025年

作者： Zhao, Xia Chen, Shuo Chen, Shouxue College of Computer Science and Engineering Guilin University of Technology Guilin541006 China Guangxi Key Laboratory of Embedded Technology and Intelligent System Guilin University of Technology Guilin541006 China

In this study, combined with visible and near-infrared spectroscopy data and Fourier transform infrared spectroscopy data, machine learning methods were used to estimate soil organic carbon (SOC) of Eucalyptus plantations in southern China. Three machine learning models of support vector machine (SVM), random forest (RF), and deep neural network (DNN) in machine learning are selected, and their performance in SOC estimation is compared. The results show that the DNN model outperformed the SVM and RF models in accuracy, with the highest correlation with measured SOC values, with an R2 value of 0.95 and the lowest root mean square error and mean absolute error, respectively. Although the DNN model performs well in prediction accuracy, it has large computational resource requirements and poor model interpretability. The study also found that the estimation result of SOC was affected by the quality of spectral data and environmental factors. By optimizing the data collection and pretreatment process and exploring the integrated learning methods, this study provides a scientific basis and technical support for regional SOC estimation and carbon cycle research. © 2025 The Author(s).

关键词： Fourier transform infrared spectroscopy

来源：评论

学校读者我要写书评

暂无评论

A PSO Based Multi-Domain Virtual Network Embedding Approach

引用

China Communications 2019年第4期16卷 105-119页

作者： Yongjing Ni Guoyan Huang Sheng Wu Chenxi Li Peiying Zhang Haipeng Yao College of Information Science and Engineering Yanshan University College of Information Science and Engineering Hebei University of Science and Technology The Key Laboratory for Computer Virtual Technology and System Integration of Hebei Province Yanshan University School of Information and Communication Engineering Beijing University of Posts and Telecommunications College of Computer & Communication Engineering China University of Petroleum (East China)

This paper proposed a multi-domain virtual network embedding algorithm based on multi-controller SDN architecture. The local controller first selects candidate substrate nodes for each virtual node in the domain. Then the global controller abstracts substrate network topology based on the candidate nodes and boundary nodes of each domain, and applies Particle Swarm Optimization Algorithm on it to divide virtual network requests. Each local controller then embeds the virtual nodes of the divided single-domain virtual network requests in the domain, and cooperates with other local controllers to embed the inter-domain virtual links. Simulation experimental results show that the proposed algorithm has good performance in reducing embedding cost with good stability and scalability.

关键词： multi-domain virtual network embedding candidate node particle swarm optimization algorithm virtual network request division

来源：评论

学校读者我要写书评

暂无评论

Hardware architecture design of HEVC entropy decoding

Hardware architecture design of HEVC entropy decoding

引用

IEEE International Conference on Big Data and Cloud Computing (BdCloud)

作者： Shiyu Wang Shengbing Zhang Jihe Wang Libo Chang Liangyou Feng Xiaoya Fan Engineering Research Center of Embedded System Integration Ministry of Education School of Computer Science Northwestern Polytechnical University Xian China National Engineering Laboratory for Integrated Aero-Space-Ground-Ocean Big Data Application Technology School of Computer Science Northwestern Polytechnical University Xian China

As the latest generation of digital video coding standard, HEVC has technically optimized multiple modules such as related frame prediction, block processing and entropy coding in the frequency coding and decoding framework. However, flexible and efficient coding algorithms make the amount of calculation in the video decoding and reconstruction process increase dramatically. The energy efficiency of traditional processors is limited, and the decoding calculation process is difficult to meet the current needs of ultra-high-definition video playback. For the most important and time-consuming bitstream analysis and entropy decoding part of the HEVC decoding process, a new hardware architecture strategy is provided, which can effectively improve the HEVC decoding performance. In this paper, the designed data access module, bitstream analysis and entropy decoding unit are simulated and verified. Build an FPGA verification platform, and use the main tier standard test sequence to simulate and verify the designed hardware acceleration architecture. The experimental results show that the hardware architecture of bitstream analysis and entropy decoding designed in this paper can reach the functions and performance indicators specified by the HEVC standard Level-4 main tier, and the bitstream analysis acceleration effect is good. This thesis aims at the current HEVC decoding calculation characteristics, and through the design of hardware architecture verification, it provides new solutions and hardware architecture ideas for subsequent HEVC encoding and decoding performance optimization.

关键词： Analytical models Program processors Video sequences Bit rate Syntactics Prediction algorithms Entropy

来源：评论

学校读者我要写书评

暂无评论

Reconstructing Suspended Sediment Concentrations in the Mekong River Basin Via Semi-Supervised-Based Deep Neural Networks

SSRN

引用

SSRN 2024年

作者： Nguyen, Thi-Thu-Ha Vu, Duc Quang Doan, Ngoc Phu Thi Khanh Chi, Huynh Li, Peixin Van Binh, Doan An, Yimeng Tuan Dung, Pham Hoang, Tuan A. Thai Son, Mai Laboratory of Environmental Sciences and Climate Change Institute for Computational Science and Artificial Intelligence Van Lang University Ho Chi Minh City70000 Viet Nam Faculty of Environment School of Technology Van Lang University Ho Chi Minh City70000 Viet Nam Department of Computer Science and Information System Thai Nguyen University of Education Viet Nam School of Electronics Electrical Engineering and Computer Science Queen’s University Belfast United Kingdom College of Economics and Management Nanjing University of Aeronautics and Astronautics China Master program in Water Technology Reuse and Management Faculty of Engineering Vietnamese-German University Binh Duong Province Ben Cat Town820000 Viet Nam

The Mekong River Basin (MRB) is one of the highest biodiversity areas in the world and is the vital source of livelihoods for more than 60 millions of people over six countries in Southeast Asia. However, it is suffering from a severe sediment starvation problem caused by climate change and human activities, particularly dam constructions. Understanding long-term sediment changes thus plays a crucial role for management and contingency plans. Current sediment concentration data in the MRB are extremely sporadic, making it a non-trivial task to analyze them. This paper focuses on the sediment reconstruction to provide long-term reliable suspended sediment concentration (SSC) data using Machine Learning (ML) perspectives. In particular, a novel semi-supervised ML model, which can effectively deal with data sparsity, is introduced to predict/reconstruct missing sediment data. The key idea of this approach is to exploit abundant available hydroclimate data to reduce training overfitting rather than solely relying on sediment concentration data, thus enhancing the accuracy of the employed ML models. Extensive experiments on data obtained from 1979 to 2019 at the three main stations (i.e., Chiang Saen, Nong Khai, and Mukdahan) are conducted to demonstrate the performances of the proposed method compared to other state-of-the-art supervised techniques and traditional simulation methods commonly used in previous sediment forecasting/reconstruction studies. To the best of our knowledge, this approach is the first semi-supervised method to reconstruct sediment data in the field. Though this study focuses on the MRB, sediment sparsity is a very common problem in other river systems worldwide. Thus, this method can be widely applied for them for more effective sediment reconstruction/prediction in general. © 2024, The Authors. All rights reserved.

关键词： Biodiversity

来源：评论

学校读者我要写书评

暂无评论

Assessment of chronic radiation proctopathy and radiofrequency ablation treatment follow-up with optical coherence tomography angiography: A pilot study

引用

World Journal of Gastroenterology 2019年第16期25卷 1997-2009页

作者： Osman Oguz Ahsen Kaicheng Liang Hsiang-Chieh Lee Zhao Wang James G Fujimoto Hiroshi Mashimo Department of Electrical Engineering and Computer Science Massachusetts Institute of Technology Gastroenterology Section VA Boston Healthcare System Harvard School of Medicine Boston

BACKGROUND Chronic radiation proctopathy(CRP) occurs as a result of pelvic radiation therapy and is associated with formation of abnormal vasculature that may lead to persistent rectal bleeding. While incidence is declining due to refinement of radiation delivery techniques, CRP remains one of the major complications of pelvic radiation therapy and significantly affects patient quality of *** ablation(RFA) is an emerging treatment modality for eradicating abnormal vasculature associated with CRP. However, questions remain regarding CRP pathophysiology and optimal disease *** To study feasibility of optical coherence tomography angiography(OCTA) for investigating subsurface vascular alterations in CRP and response to RFA *** Two patients with normal rectum and 8 patients referred for, or undergoing endoscopic RFA treatment for CRP were imaged with a prototype ultrahighspeed optical coherence tomography(OCT) system over 15 OCT/colonoscopy visits(2 normal patients, 5 RFA-na?ve patients, 8 RFA-follow-up visits). OCT and OCTA was performed by placing the OCT catheter onto the dentate line and rectum without endoscopic guidance. OCTA enabled depth-resolved microvasculature imaging using motion contrast from flowing blood, withoutrequiring injected dyes. OCTA features of normal and abnormal microvasculature were assessed in the mucosa and submucosa. Blinded reading of OCTA images was performed to assess the association of abnormal rectal microvasculature with CRP and RFA treatment, and rectal telangiectasia density endoscopic *** OCTA/OCT images are intrinsically co-registered and enabled depth-resolved visualization of microvasculature in the mucosa and submucosa. OCTA visualized normal vascular patterns with regular honeycomb patterns vs abnormal vasculature with distorted honeycomb patterns and ectatic/tortuous microvasculature in the rectal mucosa. Normal arterioles and venules < 200 μm in diameter versus abnormal he

关键词： Optical coherence tomography Optical coherence tomography angiography Radiofrequency ablation Chronic radiation proctopathy Rectal telangiectasia density scoring system Subsurface microvascular imaging

来源：评论

学校读者我要写书评

暂无评论

Random resistive memory-based deep extreme point learning machine for unified visual processing

arXiv

引用

arXiv 2023年

作者： Wang, Shaocong Gao, Yizhao Li, Yi Zhang, Woyu Yu, Yifei Wang, Bo Lin, Ning Chen, Hegan Zhang, Yue Jiang, Yang Wang, Dingchen Chen, Jia Dai, Peng Jiang, Hao Lin, Peng Zhang, Xumeng Qi, Xiaojuan Xu, Xiaoxin So, Hayden Wang, Zhongrui Shang, Dashan Liu, Qi Cheng, Kwang-Ting Liu, Ming Department of Electrical and Electronic Engineering The University of Hong Kong Hong Kong Key Laboratory of Microelectronic Devices & Integrated Technology Institute of Microelectronics Chinese Academy of Sciences Beijing100029 China ACCESS - AI Chip Center for Emerging Smart Systems InnoHK Centers Hong Kong Science Park Hong Kong University of Chinese Academy of Sciences Beijing100049 China Frontier Institute of Chip and System Fudan University Shanghai200433 China College of Computer Science and Technology Zhejiang University Zhejiang310027 China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong

Visual sensors, including 3D LiDAR, neuromorphic DVS sensors, and conventional frame cameras, are increasingly integrated into edge-side intelligent machines. Realizing intensive multi-sensory data analysis directly on edge intelligent machines is crucial for numerous emerging edge applications, such as augmented and virtual reality and unmanned aerial vehicles, which necessitates unified data representation, unprecedented hardware energy efficiency and rapid model training. However, multi-sensory data are intrinsically heterogeneous, causing significant complexity in the system development for edge-side intelligent machines. In addition, the performance of conventional digital hardware is limited by the physically separated processing and memory units, known as the von Neumann bottleneck, and the physical limit of transistor scaling, which contributes to the slowdown of Moore's law. These limitations are further intensified by the tedious training of models with ever-increasing sizes. In this study, we propose a novel hardware-software co-design, random resistive memory-based deep extreme point learning machine (DEPLM), that offers efficient unified point set analysis. Data-wise, the multi-sensory data are unified as point sets and can be processed universally. Software-wise, most weights of deep extreme point learning machines are exempted from training, which significantly reduce training complexity. Hardware-wise, nanoscale resistive memory not only enables collocation of memory and processing, mitigating the von Neumann bottleneck and the slowdown of Moore's law, but also leverages the inherent programming stochasticity for generating the random and sparse weights of the DEPLM, which also lessens the impact of read noise. We demonstrate the system's versatility across various data modalities and two different learning tasks. Compared to a conventional digital hardware-based system, our co-design system achieves 5.90×, 21.04×, and 15.79× energy efficiency improv

关键词： Cost reduction

来源：评论

学校读者我要写书评

暂无评论

Feature Extraction and Matching of 3D Face Model Based on Facial Landmark Detection

Feature Extraction and Matching of 3D Face Model Based on Fa...

引用

2020 International Conference on Virtual Reality and Visualization, ICVRV 2020

作者： Zhu, Yunrui Luo, Xun Zuniga, Claudia Lozano-Garzon, Carlos Alomia, Gustavo School of Computer Science and Engineering Tianjin University of Technology Tianjin China State Key Laboratory of Virtual Reality Technology and Systems Beihang University Beijing China Faculty of Engineering Santiago Cali University Cali Colombia Los Andes University Department of System Engineering and Computation Bogota Colombia

ISBN: (纸本)9780738142524

Building a high-quality 3D face model is one of the important issues in computer graphics. High-fidelity 3D face model can be obtained through 3D reconstruction methods from measured data, but the reconstructed models are often flawed with missing measurement data. In order to improve the usability and robustness of the 3D face models, repair and optimization of the face model are critically important. The traditional solutions rely on geometric heuristics to complete repairing work. Considering the characteristics of the face, it is possible to utilize the semantic information to improve the quality of repairing process for the three-dimensional face models, thereby improving the accuracy of the repaired models. In this paper, we combine artificial intelligence and computer graphics methods, and proposes a feature extraction and matching of 3D face model method based on facial landmark detection. Our method combines the facial feature recognition algorithm of 2D facial image and the mapping relationship of 3D face mesh model, and realizes the function of semanticsegmentation and extraction of the 3D face model features. It can be used for the next step of 3D face mesh repair research. © 2020 IEEE.

关键词： Face recognition

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：