检索结果-内蒙古大学图书馆

23rd international conference on Extending database Technology, EDBT 2020

作者： Liu, Xiufeng Niu, Zhibin Yang, Yanyan Wu, Junqi Cheng, Dawei Wang, Xin Technical University of Denmark Lyngby Denmark School of Computing University of Portsmouth PortsmouthPO1 3HE United Kingdom Tianjin University Tianjin China Shanghai Jiaotong University Shanghai China Southwest Jiaotong University Chengdu China

ISBN: (纸本)9783893180837

In the context of urbanization and the rapid growth of energy demand, understanding the spatial and temporal dynamics of urban energy use is crucial for identifying energy-saving potentials. In this demo, we present a visual analysis tool, VAP, that allows users to explore the dynamics of urban energy use at different spatial and temporal scales. In contrast to traditional statistical and machine learning methods, the visual analysis based tool focuses on analytical thinking, user interactions and answering business questions by examining different visual analysis views. In the demonstration, conference attendees will interact with VAP and learn its capabilities in discovering typical consumption patterns and spatio-temporal shift patterns from a real-world case study of electricity. © 2020 Copyright held by the owner/author(s).

关键词： Energy utilization

来源：评论

学校读者我要写书评

暂无评论

Call for Papers The Third international conference on Rough Sets and Knowledge Technology (RSKT2008)

引用

计算机研究与发展 2007年第11期44卷 1872-1872页

Since the introduction of rough sets in 1982 by Professor Zdzisaw Pawlak, we have witnessed great advances in both theory and applications. Rough set theory is closely related to knowledge technology in a variety of forms such as knowledge discovery, approximate reasoning, intelligent and multiagent system design, knowledge intensive computations. The cutting-edge knowledge technologies have great impact on learning, pattern recognition, machine intelligence and automation of acquisition, transformation, communication, exploration and exploitation of knowledge. A principal thrust of such technologies is the utilization of methodologies that facilitate knowledge processing. To present the state-of-the-art scientific results, encourage academic and industrial interaction, and promote collaborative research in rough sets and knowledge technology worldwide, the 3rd international conference on Rough Sets and Knowledge Technology will be held in Chengdu, China, May 17～19, 2008. It will provide a forum for researchers to discuss new results and exchange ideas, following the successful RSKT'06 (Chongqing, China) and JRS'07 (RSKT'07 together with RSFDGrC'07) (Toronto, Canada).

关键词： Call for Papers The Third international conference on Rough Sets and Knowledge Technology RSKT2008

来源：评论

学校读者我要写书评

暂无评论

The Forecasting About Bitcoin and Other Digital Currency Markets: The Effects of data mining and Other Emerging Technologies

The Forecasting About Bitcoin and Other Digital Currency Mar...

引用

Advance Computing and Innovative Technologies in Engineering (ICACITE), international conference on

作者： Anil Kumar Bhuyan Darshana A. Naik Sachin Sharma Anita Gehlot A. Jafersadhiq Dhiraj Kapila Birla Global University Bhubaneswar Odisha Department of CSE Ramaiah Institute of Technology Bangalore Department of Computer Applications MRIIRS Faridabad Haryana Uttaranchal Institute of Technology Uttaranchal University India Department of Business Administration Kalasalingam Academy of Research and Education (Deemed to be University) Virudhunagar Department of Computer Science & Engineering Lovely Professional University Phagwara Punjab India

We examine the bitcoin currency's predictability over prediction timeframes of 1 to 15 minutes. As a result, we evaluate a variety of machine learning methods and discover that, although all models perform better than a random predictor, Bidirectional recurrent neural networks and extreme Gradient Boosting Classifier (XGB Classifier) are particularly effective for the investigated prediction tasks. We employ a wide range of features, including technological, asset-based, interest-based, and block chain technology characteristics. Our findings indicate that technical characteristics continue to be the most important for the majority of techniques, followed by a few blockchain- and interest-based features. Furthermore, we see that reliability rises with increasing prediction horizons. Although a quantile-based long-short trading strategy may provide market return of up to 34% before transaction costs, the very brief holding durations result in negative yields after transaction expenses are incurred.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Application of Artificial Intelligence Algorithms in Technology and Financial data Service Platform Systems

Application of Artificial Intelligence Algorithms in Technol...

引用

Artificial Intelligence and Autonomous Robot Systems (AIARS), international conference on

作者： Jinjie Teng Changchun Humanities and Sciences College Changchun China

ISBN: (数字)9798350376173

ISBN: (纸本)9798350376180

The huge amount of data, complexity and changeability are difficulties that technological financial service platforms have always struggled to solve. Only by overcoming this difficulty can we carry out data analysis and decision support efficiently and accurately. This article solves this problem by introducing artificial intelligence algorithms. The article discusses the specific application methods of artificial intelligence algorithms in technology and financial data service platform systems. These methods include algorithm integration, model optimization, feature selection and extraction. Algorithm integration improves overall performance and stability by combining multiple models; model optimization improves the performance and generalization capabilities of the model by adjusting hyperparameters and optimization algorithms; feature selection and extraction reduces the complexity of the model and improves efficiency by selecting the most relevant and useful features. Experimental results show that the system response time of this algorithm is between 0.01-0.08 seconds, and it has achieved remarkable results in science and technology financial data analysis, prediction and decision support.

关键词： data analysis machine learning algorithms Feature extraction Prediction algorithms Stability analysis Complexity theory data mining Time factors Risk management Optimization

来源：评论

学校读者我要写书评

暂无评论

A Non-intrusive Load recognition Method Based on Convolutional Feature Fusion

A Non-intrusive Load Recognition Method Based on Convolution...

引用

Digital Society and Intelligent Systems (DSInS), international conference on

作者： Wenbo Zhu Weiyuan Huang Gaoyan Cai Jianwen Chen Zhongbo Zhang Haibing Li Wei Yu School of Mechatronic Engineering and Automation Foshan University Foshan China R&D Dept Hodi Technologies Co. Ltd Foshan China

ISBN: (数字)9798350331387

ISBN: (纸本)9798350331394

In non-intrusive load recognition, the aggregated load can lead to the feature information of individual target appliance being obscured, which then decreases the recognition accuracy. Although the existing methods can, to some extent, improve the accuracy of appliance identification under aggregated loads, most of them only work on identification under single modal information and do not focus on learning of information between different modalities of the load. Therefore, a cross-modal and multi-scale load convolution feature fusion recognition method was proposed in this paper. Firstly, the feature information at different scales among the three modalities of appliances was extracted by multi-layer convolution. Considering the differences in feature distributions between sequences and images, the use of traditional feature concatenation methods will lead to large deviations in feature ratio, thus reducing the ability of the model to learn the features of different modalities. To this end, a feature reconstruction scheme for balancing the feature information ratio among different modalities was proposed to improve this problem. Then, the multi-scale residuals were used to progressively fuse features at different scales among the modalities to achieve feature learning for the three modalities of appliances. After evaluation on a real datasets, the experimental results showed that the method proposed in this paper has a better performance. Compared with multiple neural network-based image classifier methods, this method has higher accuracy in recognition under aggregated load.

关键词： Time-frequency analysis Correlation Target recognition Convolution Feature extraction data models data mining

来源：评论

学校读者我要写书评

暂无评论

Tagging Units in the Text and the Bayes Algorithm

Tagging Units in the Text and the Bayes Algorithm

引用

Informatics, Electronics, and Radio Engineering (PIERE), international conference Problems of

作者： Elov Botir Boltayevich Bekmuradova Iroda Zokir qizi Israilova Saodat Turapovna Toirova Guli Ibragimovna Department of Computer Linguistics and Digital Technology Alisher Navo 'i Tashkent State University of Uzbek Language and Literature Tashkent Uzbekistan Department of computer linguistics and digital technologies Master student of Tashkent state university of Uzbek language and literature Tashkent Uzbekistan Senior teacher of UzNU candidate of philological sciences name of organization Uzbekistan National University Tashkent Uzbekistan Professor of the Department of Uzbek Linguistics and Journalism Doctor of Philology Bukhara State University Bukhara Uzbekistan

ISBN: (数字)9798331516321

ISBN: (纸本)9798331516338

This article presents an analysis of the methods employed for the tagging of units within textual data. The stages of automatic tagging of language units, in particular slangs, are covered in detail based on the working theory of the Bayesian algorithm. The factors that contribute to an increased accuracy of the calculated probability are outlined. And also this article analyzes the advantages and disadvantages of the Bayesian algorithm for text unit tagging. The steps of the algorithm are elucidated with the aid of illustrative examples. Describes the characteristics of the Bayesian algorithm as a computational method for estimating the probability of an object, its characteristics, and the group to which it belongs. This method has been shown to provide accurate results in data analysis using machine learning methods for automatic tagging of jargon, the necessity of distinguishing and automatic classification of lexical units in the language corpus, its importance in solving the problems related to the confusion in the analysis of the text containing such units.

关键词： machine learning algorithms Accuracy Translation Software algorithms machine learning Tagging Prediction algorithms Bayes methods Classification algorithms Object recognition

来源：评论

学校读者我要写书评

暂无评论

Chess Piece Image recognition Using Transfer learning, Simple Neural Network, and Convolutional Neural Network

Chess Piece Image Recognition Using Transfer Learning, Simpl...

引用

international conference on Artificial Intelligence and data Sciences (AiDAS)

作者： Gabriel Yohanes Mario Nursalim Nicholas Felix Indra Kurniadi Computer Science Department School of Computer Science Bina Nusantara University Jakarta Indonesia

Online chess has opened up a way for players to sharpen their skills through move analytics. Based on this feature, a support system called chess advisor can be utilized to assist players in a real-time match. However such system doesn't exist within the website itself, rather an involvement of 3rd party software is required. These kinds of software usually need assistance for input. This paper aims to create a system that is able to recognize chessboard state in real-time. We have proposed a chess piece image recognition system using transfer learning using ResNet50, a simple neural network, and a convolutional neural network (CNN). We collected our own 693 2D chess piece images dataset and performed data preprocessing to standardize the image dimensions. The proposed system detects and converts individual positions of each piece into a computer-readable output. This output can be used to facilitate the chess advisor in determining the best move. The transfer learning approach utilizing the ResNet50 model exhibited superior performance with an accuracy of 95.65%. This outperformed alternative methods such as the simple neural network and the CNN. The ResNet50 model's advantage stemmed from its pre-training on the ImageNet dataset, enabling effective pattern generalization. In contrast, the simple neural network and CNN achieved lower accuracies of 73.4% and 85%. These models encountered difficulties due to limited dataset quantity and quality, as well as the absence of regularization techniques. Nevertheless, the CNN displayed better consistency in generalizing patterns compared to the simple neural network.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Expression of Concern for: Coronary Artery Disease Prediction using data mining Techniques

Expression of Concern for: Coronary Artery Disease Predictio...

引用

international conference on Intelligent Sustainable Systems (ICISS)

作者： Santhosh Kumar K L Nida Kousar G Madhurya J A Department of CSE GITAM University Bengaluru India

ISBN: (数字)9781728170893

ISBN: (纸本)9781728170909

The health industry produces a gigantic amount of data and by using this huge data many diseases can be detected and predicted at early stage and can be even cured. Diseases like coronary artery, cancer, and tumour disease cause a big threat to human. In this regard, the proposed research work has been carried out to predict coronary disease and it has also been outlined below. The cardiac illness is often identified by using AI strategies. The medical statistics are taken as input and then those capabilities are modelled for prediction. This model can then be used to envision subsequent medical data. The three different data mining techniques are used in our proposed model. The accuracy of the model using each of the algorithms is intended. Then the one with adequate accuracy is taken as the model for predicting the coronary *** this new-fangled era in healthcare domains, generally the statistics mining techniques are used for prediction of diseases. It is very challenging task for the researchers to predict the medical diseases using gigantic medical databases. To overcome from this issue the researchers use various statistics mining techniques for the disease prediction. In our paper, the main intention of the research work is to predict coronary diseases using machine learning algorithms. In this paper, SVM, Naïve Bayes and Random Forest model have been used to predict the heart diseases which will be helpful for the medical sector. Early prediction of coronary illness is very vital to save human life and take proper steps to control the disorder. The main aim fo the proposed research work is to explore the new methods for early prediction of coronary disease by using statistic mining techniques.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Transfer learning for Breast Cancer Classification using Small dataset of Ultrasound Images

Transfer Learning for Breast Cancer Classification using Sma...

引用

international conference on Intelligent Sustainable Systems (ICISS)

作者： Manpreet Kaur Vikas Khullar Harjit Pal Singh CT Institute of Engineering Management and Technology Jalandhar India Institute of Engineering and Technology Chitkara University Rajpura India CT Institute of Engineering Management and Technology Jalandhar India

ISBN: (数字)9781728170893

ISBN: (纸本)9781728170909

Globally, breast cancer has been identified as probably the most deadly type of cancer among women. This proposed work implements a sophisticated Breast Cancer Prognosis from Ultrasound dataset using Transfer learning. The two great challenges for the Researchers are Breast cancer analysis and the Prognosis. Malignancy patients are influenced by many aspects. All these factors and the outward symptoms in the individual are recorded making use of scanning devices such as Ultrasound pictures, histopathology, cytology, mammogram, etc. After that this data has been used for the medical diagnosis of cancer utilizing the Transfer learning method. This paper aims to compare & analyze our suggested model Transfer learning and deep learning techniques for Breast cancer recognition from Ultrasound images predicated on parameters viz. Accuracy, Precision, Losses, Recall, and Area under Curve (AUC). The outcome of the proposed method results in best accuracy and obtains minimum losses when dealing with machine learning and deep learning approaches for the diagnosis of breast cancer in Ultrasound Images.

关键词： Feature extraction Breast cancer Tumors Convolution Ultrasonic imaging Breast Computer architecture

来源：评论

学校读者我要写书评

暂无评论

An Approach to Ensemble Simplified ResNet Models-Using Egyptian Hieroglyphs data Set

An Approach to Ensemble Simplified ResNet Models-Using Egypt...

引用

Electronic Information Engineering and Computer Science (EIECS), 2021 international conference on

作者： Zixiang Yan Kecheng Jin Jingkun Hou Pu Zhang College of Computer and Information Engineering (College of Artificial Intelligence) Nanjing Tech University Nanjing China Nanjing Hankai Academy Nanjing China School of Inteligence Science and Technology University of Science and Technology Beijing Beijing China Austin Friars St Monica's School Etterby Scaur Carlisle Cumbria UK

Since the inception of computer vision, recognizing text, including both printed and handwritten characters, has posed a significant challenge for traditional machine learning models. However, only a handful of these models have focused on ideographical scripts. Similarly, while mathematical solutions to common neural network problems such as degradation and computational complexity have been studied, possible shortcuts are often overlooked. This paper presents an innovative approach by introducing a novel ensemble network called "SparrowNet" and compares it to ResNet18 and GoogLeNet V2. Using an open-source Egyptian hieroglyph dataset, the paper focuses on evaluating the efficiency and accuracy of different networks using various performance metrics. Additionally, the paper discusses the advantages of the two existing models and explains the reasons behind the modifications made to SparrowNet. Through this research, it has been demonstrated that the use of 1x1 convolutions can significantly improve speed and reduce computational complexity, while a voting mechanism can be a novel solution to prevent degradation, and the modified network is capable to solve this particular character recognition task.

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：