检索结果-内蒙古大学图书馆

16th international conference on machine learning and Computing (ICMLC)

作者： Xue, B. Zheng, Q. Li, Z. Zhao, W. Wang, H. Feng, X. Tsinghua Univ Xian Jiaotong Univ Natl Univ Def Technol Beijing Peoples R China Tongji Univ Xian Jiaotong Univ Shanghai Peoples R China Natl Univ Def Technol Changsha Peoples R China Tsinghua Univ Beijing Peoples R China

ISBN: (纸本)9798400709234

Object detection and tracking are critical and fundamental problems in machine vision task. In this paper, an object detection and tracking method is proposed based on deep feature distillation. Particularly, an adaptive unsupervised Teacher-Student unified framework is developed. The Teacher module is performed by an expandable generative adversarial network mixture model. And knowledge discrepancy ranking (KDR) is designed to optimize Teacher resource allocation with the historical underlying knowledge. The Student module is developed based on a lightweight probabilistic generative model. And an unsupervised learning scheme is presented based on Gumbel-Soft sampling optimization to train jointly. A series of experiments are performed on authoritative dataset, demonstrating that the proposed method outperforms the state-of-the-art comparison methods.

关键词： Object detection object tracking deep learning knowledge distillation

来源：评论

学校读者我要写书评

暂无评论

How can machine learning improve waste-to-energy plant operation 28

How can machine learning improve waste-to-energy plant opera...

引用

Joint conference of the IEEE 28th international conference on engineering, Technology and Innovation (ICE/ITMC) / 31st conference of the international-Association-for-Management-of-Technology (IAMOT)

作者： Pehlken, Alexandra Garmatter, Henriette Dawel, Lisa Cyris, Fabian Beck, Hendrik Schwark, Fenja Scharf, Roland Niesse, Astrid OFFIS Inst Informat Technol R&D Div Mfg Oldenburg Germany Leibniz Univ Hannover Inst Kraftwerkstechn & Warmeubertragung Hannover Germany Energy Waste GmbH Abt Techn EEW Helmstedt Germany

ISBN: (纸本)9781665488174

This paper deals with the integration and the role of waste-to-energy plants. The hygienic and safe disposal of waste is a central aspect of human infrastructure. It is a prerequisite for preventing the spread of disease in society and is a very important issue today as it has been in the past. While serving as waste disposal in the past, today, waste incineration has changed to waste-to-energy plants, in addition to keeping the first goal of waste reducing and sanitation. Therefore, the highest energy harvesting is not the primary goal of the plant. The plant operation is difficult to control related to the stochastical variation of the properties of municipal waste due to its heterogeneous nature. Hence, it is expected that the optimization of waste-to-energy plants will benefit significantly if any applied method may handle the stochastic properties well. The work presented here aims to provide insights into a novel approach to develop a new method for enhancing the performance of the waste-to-energy plant related to blast cleanings to prevent build-up of particles. This also ensures that the overall performance of the plant improves. Artificial Intelligence was applied to sensor emission data directly from an operating real incinerator and with machine learning the data shows the effects of the blast cleanings related to typical plant properties. The results of this paper give first indications that forecasting of the incineration process is possible. With these results, the plant operator could handle the plant efficiently with the least performance reduction.

关键词： waste-to-energy machine learning artificial intelligence regression XGBoost

来源：评论

学校读者我要写书评

暂无评论

Aspect-Based Sentiment Analysis for Virtual Reality Roaming System 6

Aspect-Based Sentiment Analysis for Virtual Reality Roaming ...

引用

6th international conference on Communications, Information System and Computer engineering, CISCE 2024

作者： Wang, Biqing School of Mathematics and Computer Tongling University Tongling China

ISBN: (纸本)9798350353174

Through sentiment analysis technology, NPCs (Non-Player-Controlled Character) in virtual reality roaming system are able to recognize the user's emotional state and react accordingly. In aspect-based sentiment analysis, NLP techniques often use manually constructed features combined with machine learning models for classification. However, these methods are complex in feature engineering and lack generalisation capabilities. At the same time, traditional models often ignore the importance of local context for the correct classification of the sentiment polarity of aspect term, and process all input data indiscriminately. In order to solve the above problems and improve the processing efficiency of aspect-based sentiment analysis, an attention weight decay mechanism is proposed. On this basis, a multi-module model is constructed by fusing BERT, BiLSTM and TextCNN, and the performance of the model is verified experimentally. This model can be better applied to virtual reality roaming systems. © 2024 IEEE.

关键词： Adversarial machine learning

来源：评论

学校读者我要写书评

暂无评论

UNCERTAINTY QUANTIFICATION OF PHYSICS-BASED LABEL-FREE DEEP learning AND PROBABILISTIC PREDICTION OF EXTREME EVENTS

UNCERTAINTY QUANTIFICATION OF PHYSICS-BASED LABEL-FREE DEEP ...

引用

ASME international Design engineering Technical conferences / 42nd Annual Computers and Information in engineering conference (IDETC-CIE) / 48th Design Automation conference (DAC)

作者： Li, Huiru Yin, Jianhua Du, Xiaoping Purdue Univ Sch Mech Engn W Lafayette IN 47907 USA Indiana Univ Purdue Univ Indianapolis Dept Mech & Energy Engn 723 W Michigan St Indianapolis IN 46202 USA

ISBN: (纸本)9780791886236

Surrogate models from machine learning regression have been increasingly used in engineering analysis and design. Since surrogate models are usually built using data from solving expensive physical models, label-free machine learning methodologies have been developed to reduce the computational cost. Understanding and quantifying the model (epistemic) uncertainty of surrogate models is critical for their applications with quantified confidence. It is, however, much more computationally expensive, or even impossible to quantifying the model uncertainty for label-free machine learning. In this work we propose an uncertainty quantification method for the epistemic uncertainty of physics-based label-free regression. The method is used after a surrogate model has already been built by deep neural network based on the data of only input variables without labels (data of responses) and a system of physical equations. A surrogate model of the neural network regression model error is built with Gaussian Process regression using the existing training points and the derivatives of the system of physical equations at the training points. The error model is then used to compensate the error of the neural network surrogate model, therefore producing more accurate predictions. With higher accuracy, the proposed method is applied to probabilistic prediction of extreme events where both (aleatory) data uncertainty and model uncertainty coexist, and higher accuracy is required. Its application to time-dependent reliability prediction of a four-bar linkage mechanism demonstrates the high accuracy of the proposed method.

关键词： Uncertainty deep learning Gaussian process reliability extreme events

来源：评论

学校读者我要写书评

暂无评论

JEPX spot prices forecasting system using GIS

引用

ENERGY REPORTS 2023年 9卷 329-336页

作者： Nakayama, Shuntaro Shiota, Atsushi Mitani, Yasunori Watanabe, Masayuki Kyushu Inst Technol Tobata Ku 1-1 Sensui Cho Kitakyushu Fukuoka 8048550 Japan Kitakyushu City Off Kokurakita Ku 1-1 Jonai Kitakyushu Fukuoka 8030813 Japan

Japan Electric Power Exchange (JEPX) is the only electricity market in Japan that allows transactions for electric power established in 2005. Several commodities are traded there, such as the spot market and the forward market. In particular, the spot market is a major trading market. The price of the spot market changes depending on the relationship between supply and demand. Therefore, it is important to forecast spot market prices to make a supply and demand plan for the next day. This research focused on the factors that determine supply and demand are related to geospatial information-first, deriving the explanatory variables for JEPX spot prices using Geographic Information System (GIS). Then, constructing the spot price forecasting system by machine learning using the derived explanatory variables. By using this system, it is possible to forecast electricity prices with higher accuracy than existing methods. (c) 2022 The Authors. Published by Elsevier Ltd. This is an open access article under the CC BY license (http://***/licenses/by/4.0/).

关键词： Japan electric power exchange Geographic information system Spot price Meteorological data

来源：评论

学校读者我要写书评

暂无评论

Cluster and Denoise data with General Ratio Density 3

Cluster and Denoise Data with General Ratio Density

引用

3rd international conference on machine learning and Computer Application, ICMLCA 2022

作者： Wu, Junliang Yu, Ziniu Zhu, William Institude of Fundamental and Frontier Sciences University of Electronic Science and Technology of China No.2006 Xiyuan Ave West Hi-Tech Zone Chengdu611731 China

ISBN: (纸本)9781510664814

Density-based clustering is famous for its ability to extract clusters of arbitrary shapes and to detect noise samples, but many existing density-based clustering algorithms suffer from high dimensional or varying density data. To address these issues, we introduce a novel density-based clustering algorithm, general ratio density (GRD). Based on k-NN graph, it combines global density estimation and local density estimation to better detect noise points in varying density situations. During the process of shifting noise points and dividing clusters, our clustering algorithm can cluster and denoise at the same time. Experiment results on real life dataset and synthetic dataset demonstrates the state-of-the-art performance of our algorithm compared to other methods. © 2023 SPIE.

关键词： Cluster analysis

来源：评论

学校读者我要写书评

暂无评论

An Efficient Decision Support System for Stock Market Prediction using Technical Indicators as Features by machine learning Approaches 4

An Efficient Decision Support System for Stock Market Predic...

引用

4th international conference for Emerging Technology, INCET 2023

作者： Naga Pranava Shashank, V. Ramanan, Vimal S Altrin Lloyd Hudson, D. Sheik Abdullah, A. Vellore Institute of Technology School of Computer Science & Engineering Tamil Nadu Chennai India

ISBN: (纸本)9798350335750

In this Research, we have built machine learning Models to predict the next day price for the Nifty Index, Reliance and TCS Stocks. We will use R Project Library, quantmod, TTR for data acquisition and technical analysis. We have used the R Project machine learning Library caret along with the daily data for the last five years (June 2017 - June 2022) for the NIFTY Index and the Reliance and TCS Stocks. Our data will consist of Open, High, Low, Last (Close) and Volume. Our objective is to predict the price change for the next day using 6 technical indicators as features which include RSI, Williams%R, etc. For building machine learning Models, we have used the R Library caret. The primary methods which are used are KNN, Classification Regression Trees, Naive Bayes, SVM with Radial Basis Function and DNN. For k-nearest neighbors, we are able to achieve an accuracy of 72.78%, for DNN 72.533%, for CART 72.36%, for NB 70.08%, and for SVM 72.69% for the prediction accuracy of the next day. © 2023 IEEE.

关键词： data acquisition

来源：评论

学校读者我要写书评

暂无评论

Fog and Edge Computing-Based Smart Health Care System Using machine learning 7th

Fog and Edge Computing-Based Smart Health Care System Using ...

引用

7th international conference on Advanced Computing and Intelligent engineering, ICACIE 2022

作者： Tripathy, Subhranshu Sekhar Tripathy, Niva Rath, Mamata Hu, Yu-Chen Pattanaik, Swarupa Samantaray, Swarnakanti Department of Computer Science and Engineering DRIEMS Autonomous College Odisha Cuttack India Department of Computer Science and Information Management Providence University Taichung City Taiwan GIET Khurdha Odisha Baniatangi India Nalanda Institute of Technology Odisha Bhubaneswar India School of Computer Engineering KIIT Deemed to be University Bhubaneswar India Department of Computer Science and Engineering SOET Centurion University of Technology and Management Bhubaneswar India

ISBN: (纸本)9789819950140

data in the medical field include varying degrees of ambiguity and imprecision, which makes it difficult for doctors to improve the health of patients with a group of related suggestive disorders. As a result, doctors use data stored in networks and computing systems to identify a variety of illnesses in patients. The proposed strategy boosts the system’s effectiveness and makes accurate diagnoses and suggestions for treating life-threatening diseases easier. The adaptive prediction systems are assessed, and a machine learning-based model for heart disease detection is trained and compared to the relevant traditional approaches. When compared to other sophisticated classification methods, the cloud-fog-fog architecture was shown to be the most accurate. As a result, the suggested strategy is more accurate in identifying different cardiac issues and suggesting effective treatment options. The performance of the proposed system warrants its application in automated cardiac patient diagnostic and recommendation systems. The Heart Failure Clinical Records repository at UCI provided the dataset for this study, which has 13 characteristics. The experimental findings showed that the CNN model performs better than other deep learning and machine learning models which are proposed by eminent researchers. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Deep learning Methods for Predicting Severity for Diabetic Retinopathy on Retinal Fundus Images 1

引用

2nd international conference on Computational Intelligence in machine learning, ICCIML 2022

作者： Chandankhede, Minakshee Zade, Amol G H Raisoni University Amravati Amravati India

ISBN: (数字)9789819979547

ISBN: (纸本)9789819979530

A thorough investigation is conducted in this work to identify diabetic retinopathy using retinal fundus images. Diabetes affects the retinal blood vessels in the interior of the eye, causing diabetic retinopathy, an eye disorder. In working population, diabetic retinopathy is very common major root of sight loss or blindness. If this illness is not identified in its early stages, it may cause permanent eyesight loss. The rate of damage can be reduced or avoided if it is predicted in advance. Utilising deep learning approaches for the automatic detection and prediction of diabetic retinopathy, recent developments in AI-assisted disease diagnosis have yielded positive and reliable results. By using deep learning algorithms, we can increase accuracy compared to prior machine learning methods. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Diagnosis

来源：评论

学校读者我要写书评

暂无评论

On the Capabilities of Quantum machine learning 7

On the Capabilities of Quantum Machine Learning

引用

7th international conference on data Science and machine learning Applications (CDMA)

作者： Alghamdi, Sarah Almuhammadi, Sultan King Fahd Univ Petr & Minerals Coll Comp Sci & Math Dhahran Saudi Arabia

ISBN: (纸本)9781665410144

machine learning techniques give impressive results in many areas. However, due to the physical limitation of integrated circuits which restricts their computational power growth, and the rapid advances in quantum computing, lots of research studies on quantum machine learning (QML) have been done recently. QML is a technique that uses quantum algorithms as parts of the implementation. Quantum algorithms use quantum mechanics and have the potential to outperform classical algorithms for a given problem. In this paper, three widely used machine learning algorithms are discussed and their quantum versions are presented, namely: quantum neural network, quantum autoencoder, and quantum kernel method. In addition, we discuss the potential capabilities of these QML algorithms and review recent work employing them. Moreover, a quantum neural network prototype is implemented using Qiskit as a proof of concept and tested on a real quantum computer. Empirical results show that quantum neural networks can be trained efficiently.

关键词： Quantum machine learning Near-term Quantum Computers Neural Network Autoencoder Kernel Method

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：