检索结果-内蒙古大学图书馆

Developing a deep neural network model for predicting ventilation rates in public housing buildings in Hong Kong

ENERGY AND BUILDINGS 2024年 307卷

作者： Dai, Ho Kam Shi, Yifu Chen, Chun Chinese Univ Hong Kong Dept Mech & Automat Engn Shatin Hong Kong 999077 Peoples R China Chinese Univ Hong Kong Inst Environm Energy & Sustainabil Shatin Hong Kong 999077 Peoples R China

In Hong Kong, 45 % of the population live in public housing buildings. This study aimed to develop deep neural network (DNN) models for efficiently predicting the ventilation rates in public housing buildings in Hong Kong in the era of modular flat design. First, a database of ventilation rates in Cheung Tai House, a representative public housing building, under 23 wind conditions and 32 different ventilation settings, was obtained by means of computational fluid dynamic (CFD) and multi -zone airflow network models. On -site measurements were conducted in two residential units to validate the numerical models. The database was then used to train the DNN models for the 32 ventilation settings, respectively, for predicting the ventilation rate. The trained DNN models can accurately predict the ventilation rates in Cheung Tai House with a mean absolute percentage error (MAPE) of 4.3 %. The trained DNN models were further validated by numerical simulation results for Hung Fuk Estate and field measurement results for Chun Yeung Estate. The results show that the trained DNN models based on the Cheung Tai House database could predict the ventilation rates of other public housing buildings reasonably well, with a MAPE of 10 % regardless of the building's structural shape.

关键词： Multi -zone airflow network model Computational fluid dynamics deep neural network model Public housing Modular flat design

来源：评论

学校读者我要写书评

暂无评论

DVC-Net: A deep neural network model for dense video captioning

引用

IET COMPUTER VISION 2021年第1期15卷 12-23页

作者： Lee, Sujin Kim, Incheol Kyonggi Univ Dept Comp Sci 154-42 Gwanggyosan Ro Suwon Gyeonggi Do South Korea

Dense video captioning (DVC) detects multiple events in an input video and generates natural language sentences to describe each event. Previous studies predominantly used convolutional neural networks to extract visual features from videos but failed to employ high-level semantics to effectively explain video content such as people, objects, actions, and places, and utilized only limited context information in generating natural language. To overcome these deficiencies, DVC-Net is proposed, a new deep neural network model that uses high-level semantics to efficiently represent important events as well as visual features. Additionally, DVC-Net uses a bidirectional long short-term memory network, a type of recurrent neural network, to detect events over time. Furthermore, DVC-Net applies an attention mechanism and context gating to effectively exploit context information in a caption generation step. In experiments conducted versus state-of-the-art models, DVC-Net presented relative gains of over 1.72% (BLEU@1 score increases from 12.22 to 13.94) and 3.19% (CIDEr score increases from 12.61 to 15.80) on the large-scale benchmark datasets, namely ActivityNet Captions and MSR-VTT, respectively.

关键词： deep neural network model computer vision short-term memory network convolutional neural networks high-level semantics image motion analysis learning (artificial intelligence) language translation recurrent neural nets feature extraction neural nets object detection video signal processing video content input video caption generation step visual features natural language processing context information natural languages recurrent neural network dense video captioning natural language sentences DVC-Net uses

来源：评论

学校读者我要写书评

暂无评论

A residual connection enabled deep neural network model for optic disk and optic cup segmentation for glaucoma diagnosis

引用

SCIENCE PROGRESS 2023年第3期106卷 368504231201329页

作者： Aurangzeb, Khursheed King Saud Univ Coll Comp & Informat Sci Dept Comp Engn POB 51178 Riyadh 11543 Saudi Arabia

Glaucoma diagnosis at an early stage is vital for the timely initiation of its treatment for and preventing possible vision loss. For glaucoma diagnosis, an accurate estimation of the cup-to-disk ratio (CDR) is required. The current automatic CDR computation techniques attribute lower accuracy and higher complexity, which are important considerations for diagnostics system design to be used for such critical diagnoses. The current methods involve a deeper deep learning model, comprising a large number of parameters, which results in higher system complexity and training/testing time. To address these challenges, this paper proposes a Residual Connection (non-identity)-based deep neural network (RC-DNN), which is based on non-identity residual connectivity for joint optic disk (OD) and optic cup (OC) detection. The proposed model is emboldened by efficient residual connectivity, which is beneficial in several ways. First, the model is efficient and can perform simultaneous segmentation of the OC and OD. Second, the efficient residual information flow permeates the vanishing gradient problem which results in faster converges of the model. Third, feature inspiration empowers the network to perform the segmentation with only a few network layers. We performed a comprehensive performance evaluation of the developed model based on its training in RIM-ONE and DRISHTIGS databases. For OC segmentation, for the images (test set) from {DRISHTI-GS and RIM-ONE} datasets, our proposed model achieves the dice coefficient, Jaccard coefficient, sensitivity, specificity, and balanced accuracy of {92.62, 86.52}, {86.87, 77.54}, {94.21, 95.36}, {99.83, 99.639}, and {94.2, 98.9}, respectively. These experimental results indicate that the developed model provides significant performance enhancement for joint OC and OD segmentation. Additionally, the reduced computational complexity based on reduced model parameters and higher segmentation accuracy provides the additional features of effi

关键词： deep neural network model joint optic cup and disk segmentation glaucoma deep learning healthcare

来源：评论

学校读者我要写书评

暂无评论

A distributed deep neural network model for credit card fraud detection

引用

FINANCE RESEARCH LETTERS 2023年 58卷

作者： Lei, Yu-Tian Ma, Chao-Qun Ren, Yi-Shuai Chen, Xun-Qi Narayan, Seema Huynh, Anh Ngoc Quang Hunan Univ Business Sch Changsha Peoples R China Hunan Univ Sch Publ Adm Changsha Peoples R China Hunan Univ Res Inst Digital Soc & Blockchain Changsha Peoples R China Hunan Univ Ctr Resource & Environm Management Changsha Peoples R China Univ Auckland Energy Ctr 12 Grafton Rd Auckland 1010 New Zealand Monash Univ Monash Business Sch Melbourne Australia Univ Econ Ho Chi Minh City UEH Univ Coll Technol & Design Ho Chi Minh City Vietnam

This paper develops a distributed neural network model (DDNN) for detecting credit card fraud to federate credit card transaction data among different financial institutions. In addition, the convergence of the DDNN model is achieved by introducing a model optimization algorithm. The results demonstrate that (1) The use of a distributed model can avoid privacy leakage and data handling costs;(2) The DDNN model accelerates the convergence of the model through simultaneous computation of multiple clients;(3) The DDNN model detects credit card fraud better than multiple types of centralized models.

关键词： Credit card fraud Fraud detection deep neural network model Distributed model

来源：评论

学校读者我要写书评

暂无评论

A hybrid deep neural network model for query intent classification

引用

JOURNAL OF INTELLIGENT & FUZZY SYSTEMS 2019年第6期36卷 6413-6423页

作者： Xu, Bo Ma, Yunlong Lin, Hongfei Dalian Univ Technol Fac Elect Informat & Elect Engn Room A923Chuangxinyuan Bldg Dalian Peoples R China

Query intents describe user information needs for searching on the web. How to capture the query intents is a crucial research topic in information retrieval. Search engine users always employ insufficient or unclear words as queries, thus making query intents ambiguous and uncertain to be interpreted by search engines. Query intent classification can deal with the problem by clarifying user queries and interpreting information needs for improving user satisfaction. Two main challenges have been addressed to classify query intents: one is how to effectively represent short and ambiguous queries;the other is how to generate a set of appropriate categories for matching diverse queries. In the paper, we propose a hybrid deep neural network model for query intent classification to meet the challenges. Our model adopts two state-of-the-art neural network models to comprehensively represent queries as feature vectors. We then employ query logs to automatically generate intermediate categories for fine-grained query intent clarification. Experimental results show that our method can outperform other baseline models, and effectively improve the performance in query intent classification.

关键词： Information retrieval query intent classification query representation deep neural network model machine learning

来源：评论

学校读者我要写书评

暂无评论

A deep neural network model for Target-based Sentiment Analysis

A Deep Neural Network Model for Target-based Sentiment Analy...

引用

International Joint Conference on neural networks (IJCNN)

作者： Chen, Siyuan Peng, Chao Cai, Linsen Guo, Lanying East China Normal Univ Sch Comp Sci & Software Engn Shanghai Peoples R China East China Normal Univ Sch Comp Sci & Software Engn Shanghai Key Lab Trustworthy Comp Shanghai Peoples R China

ISBN: (纸本)9781509060146

In recent years, with the development of social networks, sentiment analysis has become one of the most important research topics in the field of natural language processing. The deep neural network model combining attention mechanism has achieved remarkable success in the task of target-based sentiment analysis. In current research, however, the attention mechanism is more combined with LSTM networks, such neural network-based architectures generally rely on complex computation and only focus on the single target, thus it is difficult to effectively distinguish the different polarities of variant targets in the same sentence. To address this problem, we propose a deep neural network model combining convolutional neural network and regional long short-term memory (CNN-RLSTM) for the task of target-based sentiment analysis. The approach can reduce the training time of neural network model through a regional LSTM. At the same time, the CNN-RLSTM uses a sentence-level CNN to extract sentiment features of the whole sentence, and controls the transmission of information through different weight matrices, which can effectively infer the sentiment polarities of different targets in the same sentence. Finally, experimental results on multi-domain datasets of two languages from SemEval2016 and auto data show that, our approach yields better performance than SVM and several other neural network models.

关键词： deep learning Sentiment analysis Target-based sentiment analysis Convolutional neural network Long short-term memory network deep neural network model

来源：评论

学校读者我要写书评

暂无评论

A Data-Driven Battery Degradation Estimation Method for Low-Earth-Orbit (LEO) Satellites

引用

APPLIED SCIENCES-BASEL 2025年第4期15卷 2182-2182页

作者： Park, Kyun-Sang Yun, Seok-Teak Korea Aerosp Res Inst Div KOMPSAT Program 7 Daejeon 34133 South Korea Gyeongsang Natl Univ Sch Elect Engn Jinju 34158 South Korea

Battery degradation is a critical challenge in the operation and longevity of low-Earth-orbit (LEO) satellites because of its direct impact on mission reliability and power system performance. This study proposes a data-driven approach to accurately estimating the degradation of satellite batteries by integrating a transformer network model for voltage prediction and unscented Kalman filter (UKF) techniques for online state estimation. By utilizing on-orbit telemetry data and machine-learning-based modeling, the proposed method provides processing-time improvements by addressing the limitations of traditional methods imposed by their reliance on predefined conditions and user expertise. The proposed framework is validated using real satellite telemetry data from KOMPSAT-5, demonstrating its ability to predict battery degradation trends over time and under varying operational conditions. This approach minimizes manual data processing requirements and enables the consistent and precise monitoring of battery health.

关键词： low-Earth-orbit (LEO) satellite battery battery state of health (SOH) battery state of charge (SOC) deep neural network model

来源：评论

学校读者我要写书评

暂无评论

Investigation of derailment and wheel wear in a BEML metro coach under different operating conditions

引用

JOURNAL OF THE BRAZILIAN SOCIETY OF MECHANICAL SCIENCES AND ENGINEERING 2024年第10期46卷 1-19页

作者： Singh, Sudhir Kumar Das, Amit Kumar Singh, Sanjay R. Racherla, Vikranth Indian Inst Technol Kharagpur Dept Mech Engn Kharagpur 729302 West Bengal India Indian Inst Management Mumbai 400087 Maharashtra India BEML Ltd Bangalore 560027 Karnataka India

Derailment and wheel wear in railways are of major concern which involve complex operating and conflicting dynamics parameters. Metro trains undergoes through sharp turns, steep gradients, frequent high acceleration and decelerations, and overloading during peak hours which heighten the multivariate ate aspect of the problems. In this work, an attempt has been made to investigate the derailment coefficient and wheel wear of all the eight wheels of a BEML (Bharat Earth Movers Limited) metro coach under different operating scenarios. Various running conditions are generated through response surface methodology (RSM) approach by varying vehicle speed, axle load and friction at the rail-wheel contact. For this, a multibody vehicle dynamics model replicating BEML metro coach is built in commercial software Simpack. The developed multibody dynamics model is validated from the field trials conducted in Kolkata, India, by matching vehicle motion and ride comfort indices along the track. Validated multibody dynamics model is then used for simulating different running scenarios according to the central composite design (CCD) scheme. Data generated from the multibody dynamics model under different operating scenarios are taken as inputs and outputs target data for a deep neural network (DNN) model. Results of the RSM approach indicate that lower friction at the rail-wheel contact is desirable for lower wear indices and smaller derailment coefficients. Operating speed, in the speed range considered, has little influence on wear index and derailment coefficient. Results of the developed DNN model demonstrate that the mean absolute percentage error (MAPE) value is lower than 4% for all the eight wheels in both training and test.

关键词： Wheel wear Derailment coefficient Field trials Multibody dynamics model deep neural network model Response surface methodology

来源：评论

学校读者我要写书评

暂无评论

ONNXPruner: ONNX-Based General model Pruning Adapter

引用

IEEE Transactions on Pattern Analysis and Machine Intelligence 2025年第7期47卷 5806-5817页

作者： Ren, Dongdong Li, Wenbin Ding, Tianyu Wang, Lei Fan, Qi Huo, Jing Pan, Hongbing Gao, Yang Nanjing University School of Electronic Science and Engineering China Nanjing University State Key Laboratory for Novel Software Technology School of Intelligence Science and Technology China Microsoft Corporation Applied Sciences Group RedmondWA98052 United States University of Wollongong School of Computing and Information Technology NSW2522 Australia

Recent advancements in model pruning have focused on developing new algorithms and improving upon benchmarks. However, the practical application of these algorithms across various models and platforms remains a significant challenge. To address this challenge, we propose ONNXPruner, a versatile pruning adapter designed for the ONNX format models. ONNXPruner streamlines the adaptation process across diverse deep learning frameworks and hardware platforms. A novel aspect of ONNXPruner is its use of node association trees, which automatically adapt to various model architectures. These trees clarify the structural relationships between nodes, guiding the pruning process, particularly highlighting the impact on interconnected nodes. Furthermore, we introduce a tree-level evaluation method. By leveraging node association trees, this method allows for a comprehensive analysis beyond traditional single-node evaluations, enhancing pruning performance without the need for extra operations. Experiments across multiple models and datasets confirm ONNXPruner's strong adaptability and increased efficacy. Our work aims to advance the practical application of model pruning. © 1979-2012 IEEE.

关键词： Adaptation models Training Filters deep Learning Computational modeling Software Interoperability Load modeling Software Algorithms Electronic Mail General model Pruning ONNX Tree Level Evaluation deep neural network model Pruning deep Learning model Architecture deep Learning Framework Hardware Platform Superior Performance deep neural network Feature Maps Py Torch Image Net Training Images Sparse Matrix Root Node Type Of Operation Single Node deep neural network model Validation Images Extra Components Importance Of Filtering Pruning Method Squeeze Net

来源：评论

学校读者我要写书评

暂无评论

Predicting tissue distribution and tumor delivery of nanoparticles in mice using machine learning models

引用

JOURNAL OF CONTROLLED RELEASE 2024年 374卷 219-229页

作者： Mi, Kun Chou, Wei-Chun Chen, Qiran Yuan, Long Kamineni, Venkata N. Kuchimanchi, Yashas He, Chunla Monteiro-Riviere, Nancy A. Riviere, Jim E. Lin, Zhoumeng Univ Florida Coll Publ Hlth & Hlth Profess Dept Environm & Global Hlth 1225 Ctr Dr Gainesville FL 32610 USA Univ Florida Ctr Environm & Human Toxicol Gainesville FL 32610 USA Univ Calif Riverside Coll Nat & Agr Sci Dept Environm Sci Riverside CA 92521 USA Univ Florida Coll Publ Hlth & Hlth Profess Dept Biostat Gainesville FL 32608 USA Kansas State Univ Nanotechnol Innovat Ctr Kansas State Manhattan KS 66506 USA North Carolina State Univ Ctr Chem Toxicol Res & Pharmacokinet Raleigh NC 27606 USA Kansas State Univ Consortium 1Data Olathe KS 66061 USA

Nanoparticles (NPs) can be designed for targeted delivery in cancer nanomedicine, but the challenge is a low delivery efficiency (DE) to the tumor site. Understanding the impact of NPs' physicochemical properties on target tissue distribution and tumor DE can help improve the design of nanomedicines. Multiple machine learning and artificial intelligence models, including linear regression, support vector machine, random forest, gradient boosting, and deep neural networks (DNN), were trained and validated to predict tissue distribution and tumor delivery based on NPs' physicochemical properties and tumor therapeutic strategies with the dataset from NanoTumor Database. Compared to other machine learning models, the DNN model had superior predictions of DE to tumors and major tissues. The determination coefficients (R2) for the test datasets were 0.41, 0.42, 0.45, 0.79, 0.87, and 0.83 for DE in tumor, heart, liver, spleen, lung, and kidney, respectively. All the R2 and root mean squared error (RMSE) results of the test datasets were similar to the 5-fold cross validation results. Feature importance analysis showed that the core material of NPs played an important role in output predictions among all physicochemical properties. Furthermore, multiple NP formulations with greater DE to the tumor were determined by the DNN model. To facilitate model applications, the final model was converted to a web dashboard. This model could serve as a high-throughput pre-screening tool to support the design of new and efficient nanomedicines with greater tumor DE and serve as an alternative tool to reduce, refine, and partially replace animal experimentation in cancer nanomedicine research.

关键词： Nanoparticles Artificial intelligence Machine learning Nanomedicine Drug delivery Biodistribution Quantitative structure-activity relationship (QSAR) deep neural network model

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：