检索结果-内蒙古大学图书馆

arXiv 2025年

作者： Rehman, Abdul Heldal, Ilona Stilwell, Diana Lin, Jerry Chun-Wei Department of Computer Science Electrical Engineering and Mathematical Sciences Western Norway University of Applied Sciences Bergen Norway Faculty of Psychology Alameda da Universidade Lisbon1649-013 Portugal

This paper focuses on developing a framework for uncovering insights about NDD children’s performance (e.g., raw gaze cluster analysis, duration analysis & area of interest for sustained attention, stimuli expectancy, loss of focus/motivation, inhibitory control) and informing their teachers. The hypothesis behind this work is that self-adaptation of games can contribute to improving students’ well-being and performance by suggesting personalized activities (e.g., highlighting stimuli to increase attention or choosing a difficulty level that matches students’ abilities). The aim is to examine how AI can be used to help solve this problem. The results would not only contribute to a better understanding of the problems of NDD children and their teachers but also help psychologists to validate the results against their clinical knowledge, improve communication with patients and identify areas for further investigation, e.g., by explaining the decision made and preserving the children’s private data in the learning process. © 2025, CC BY.

关键词： Students

来源：评论

学校读者我要写书评

暂无评论

Exploring the Potential of the Machine Learning Techniques in the Water Quality Assessment: A Review of Applications and Performance

Exploring the Potential of the Machine Learning Techniques i...

引用

International Conference on Advanced Engineering, Technology and Applications, ICAETA 2024

作者： Márquez, Fausto Pedro García Al-taie, Ali Hussein Shuaa Zakur, Yahya Asmar Alsadoon, Abeer Flaih, Laith R. Zakoor, Yousif Asmar Ingenium Research Group Universidad Castilla-La Mancha Ciudad Real13071 Spain Department of Mathematics Faculty of Education for Pure Sciences Wasit University Wasit Iraq Department of Statistics Faculty of Mathematical Science University of Mazandaran Babolsar Iran Sydney Australia Sydney Australia Department of Computer Science College of Science Cihan University-Erbil Erbil Iraq Department of Civil Engineering College of Engineering Wasit University Wasit Iraq

ISBN: (纸本)9783031709234

In this review, the application of machine learning (ML) algorithms in water environment research is proficiently explored. The quick increase in data size related to the water environment has necessitated the use of ML for data analysis, classification, and forecasting. Unlike classical models, machine learning models excel in solving complex problems. They have been successfully applied to various aspects of water management and treatment systems, such as construction, simulation, evaluation, water pollution surveillance, controlling, water quality amelioration, and watershed environmental security management. The survey specifically focuses on the evaluation of water quality in diverse water environments, including surface water, drinking water, groundwater, sewage, and seawater. Moreover, potential future implementations of machine learning in water environments are proposed. ML facilitates the detection and prediction of water contamination events, as well as the provision of decision support systems for water resource management. Real-time monitoring of water quality, anomaly detection, and prediction of potential contamination events are among the specific applications of machine learning high-lighted. The review covers the advantages and disadvantages of generally used ML algorithms, with a particular emphasis on new ML techniques that surpass classical methods. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Sewage

来源：评论

学校读者我要写书评

暂无评论

Detection of Bacterial Leaf Blight Disease Using RGB-Based Vegetation Indices and Fuzzy Logic 19

Detection of Bacterial Leaf Blight Disease Using RGB-Based V...

引用

19th IEEE International Colloquium on Signal Processing and Its Applications, CSPA 2023

作者： Aziz, Nor Hafiza Narashid, Rohayu Haron Razak, Tajul Rosli Anshah, Siti Aminah Talib, Noorfatekah Latif, Zulkiflee Abd Hashim, Norhashila Zainuddin, Khairulazhar Universiti Teknologi MARA Centre of Studies Surveying Science and Geomatics Faculty of Architecture Planning and Surveying Arau Perlis02600 Malaysia Faculty of Computer and Mathematical Sciences Shah Alam Selangor40450 Malaysia Shah Alam Selangor40450 Malaysia Universiti Putra Malaysia Faculty of Engineering Johor Bahru Johor81310 Malaysia

ISBN: (纸本)9781665476928

Paddy planting becomes the primary source of income and livelihood for paddy farmers, especially small-scale farmers and landless laborers. Unfortunately, rice production has been threatened by paddy disease. The bacteria leaf blight disease (BLB) is one of Malaysia's most significant paddy diseases, causing substantial harm to rice production. This study aims to determine the bacteria leaf blight (BLB) disease from the utilized techniques of RGB-Based Vegetation Indices and Fuzzy Logic on the Unmanned Aerial Vehicle (UAV) images during the first paddy season 2022 in Perlis. In this study, the RGB-based indices of Normalized Green Red Different Index (NGRDI) and Green Leaf Index (GLI) were applied to the UAV Images captured at 20m altitudes. Then the fuzzy logic classification technique was applied to identify the BLB disease severity which consists of healthy and infected paddy leaves with the acceptable accuracy of 90.16%. Based on the classified BLB severeness with fuzzy logic, the result shows that the NGRDI was more significant to identify paddy disease in the area. In contrast, the GLI index is more significant to identify the non-paddy area. The NGRDI and GLI index ranges for BLB were found between -0.054 to 0.092 and 0.005 to 0.222. For more improvement of the study, the multispectral UAV Image should be applied to increase the accuracy of paddy disease detection like BLB and the images will also be taken and verified in other paddy plots with the aid of a spectroradiometer. © 2023 IEEE.

关键词： Bacteria

来源：评论

学校读者我要写书评

暂无评论

Efficiently stable presentations from error-correcting codes

arXiv

引用

arXiv 2023年

作者： Chapman, Michael Vidick, Thomas Yuen, Henry Courant Institute of Mathematical Sciences New York University United States Faculty of Mathematics and Computer Science Weizmann Institute of Science Israel Department of Computer Science Columbia University United States

We introduce a notion of efficient stability for finite presentations of groups. Informally, a finite presentation using generators S and relations R is stable if any map from S to unitaries that approximately satisfies the relations (in the tracial norm) is close to the restriction of a representation of G to the subset S. This notion and variants thereof have been extensively studied in recent years, in part motivated by connections to property testing in computer science. The novelty in our work is the focus on efficiency, which, informally, places an onus on small presentations - in the sense of encoding length. The goal in this setup is to achieve non-trivial tradeoffs between the presentation length and its modulus of stability. With this goal in mind we analyze various natural examples of presentations. We provide a general method for constructing presentations of Z2k from linear error-correcting codes. We observe that the resulting presentation has a weak form of stability exactly when the code is testable. This raises the question of whether testable codes give rise to genuinely stable presentations using this method. While we cannot show that this is the case in general, we leverage recent results in the study of non-local games in quantum information theory (Ji et al., Discrete Analysis 2021) to show that a specific instantiation of our construction, based on the Reed-Muller family of codes, leads to a stable presentation of Z2k of size poly log(k) only. As an application, we combine this result with recent work of de la Salle (arXiv:2204.07084) to re-derive the quantum low-degree test of Natarajan and Vidick (IEEE FOCS'18), which is a key building block in the recent refutation of Connes' Embedding Problem via complexity theory (Ji et al., arXiv:2001.04383). © 2023, CC BY-SA.

关键词： Quantum optics

来源：评论

学校读者我要写书评

暂无评论

AUGMENTING VISION-BASED HUMAN POSE ESTIMATION WITH ROTATION MATRIX

arXiv

引用

arXiv 2023年

作者： Vazan, Milad Masoumi, Fatemeh Sadat Ou, Ruizhi Rawassizadeh, Reza Department of Computer and Data Science Faculty of Mathematical Science Shahid Beheshti University Tehran Iran Department of Computer Science Faculty of Mathematics Statistics and Computer Science University of Allameh Tabataba’i Tehran Iran Department of Computer Science College of Art and Sciences Boston University United States Department of Computer Science Metropolitan College Boston University United States

Fitness applications are commonly used to monitor activities within the gym, but they often fail to automatically track indoor activities inside the gym. This study proposes a model that utilizes pose estimation combined with a novel data augmentation method, i.e., rotation matrix. We aim to enhance the classification accuracy of activity recognition based on pose estimation data. Through our experiments, we experiment with different classification algorithms along with image augmentation approaches. Our findings demonstrate that the SVM with SGD optimization, using data augmentation with the Rotation Matrix, yields the most accurate results, achieving a 96% accuracy rate in classifying five physical activities. Conversely, without implementing the data augmentation techniques, the baseline accuracy remains at a modest 64%. © 2023, CC BY-NC-ND.

关键词： Matrix algebra

来源：评论

学校读者我要写书评

暂无评论

Recognition of Colon Neoplasm using Contrast-Aware Capsule Network

Recognition of Colon Neoplasm using Contrast-Aware Capsule N...

引用

International Conference on Adaptive science & Technology (ICAST)

作者： Mavis Serwaa Yeboah Patrick Kwabena Mensah Adebayo Felix Adekoya Mighty Abra Ayidzoe Department of Computer Science and Informatics University of Energy and Natural Resources Sunyani Ghana Department of Computer Science Sunyani Technical University Sunyani Ghana Faculty of Computing Engineering and Mathematical Sciences Catholic University of Ghana Sunyani Ghana

ISBN: (数字)9798350385403

ISBN: (纸本)9798350385410

Colon neoplasms are the second leading cause of mortality worldwide, and despite advances in endoscopy, even experienced endoscopists miss 22-28% of cases. Intelligent systems can bridge this gap, but current approaches face significant challenges. For instance, Convolutional Neural Networks (CNNs) excel in image recognition but require large datasets, which are often scarce in healthcare. On the other hand, Capsule Networks, suitable for smaller datasets, struggle with complex images. To address these limitations, we propose a novel contrast-aware Capsule Network for colon neoplasm recognition. By incorporating a novel contrast-aware feature transformation algorithm, our proposed model enhances extracted features and focuses on processing relevant features, achieving remarkable recognition accuracies of 96.70%, 93.68%, and 99.99% on PolyGen, ETIS-Larib, and CVC-ClinicDB datasets, respectively. Our approach outperforms state-of-the-art Capsule Network algorithms and offers a promising solution to support endoscopists in accurate colon neoplasm detection, reducing the burden of image analysis and improving patient outcomes.

关键词： Uncertainty Accuracy Neural networks Estimation Training data Mortality Medical services Feature extraction Colon Neoplasms

来源：评论

学校读者我要写书评

暂无评论

MELex: The Construction of Malay-English Sentiment Lexicon

引用

computers, Materials & Continua 2022年第4期71卷 1789-1805页

作者： Nurul Husna Mahadzir Mohd Faizal Omar Mohd Nasrun Mohd Nawi Anas ASalameh Kasmaruddin Che Hussin Abid Sohail Faculty of Computer and Mathematical Sciences Universiti Teknologi MARA(UiTM)Kedah08400MerbokKedahMalaysia Department of Decision Sciences School of Quantitative SciencesUniversiti Utara Malaysia06010KedahMalaysia Disaster Management of Institute School of Technology Management and LogisticUniversiti Utara Malaysia06010KedahMalaysia Department of Management Information System College of Business AdministrationPrince Sattam Bin Abdulaziz University165Al-KharjSaudi Arabia Faculty of Entrepreneurship and Business Universiti Malaysia KelantanMalaysia Department of Computer Science COMSATS University IslamabadLahorePakistan

Currently,the sentiment analysis research in the Malaysian context lacks in terms of the availability of the sentiment ***,this issue is addressed in this paper in order to enhance the accuracy of sentiment *** this study,a new lexicon for sentiment analysis is constructed.A detailed review of existing approaches has been conducted,and a new bilingual sentiment lexicon known as MELex(Malay-English Lexicon)has been *** MELex involves three activities:seed words selection,polarity assignment,and synonym *** approach differs from previous works in that MELex can analyze text for the two most widely used languages in Malaysia,Malay,and English,with the accuracy achieved,is 90%.It is evaluated based on the experimentation and case study approaches where the affordable housing projects in Malaysia are selected as case *** finding has given an implication on the ability of MELex to analyze public sentiments in the Malaysian *** novel aspects of this paper are ***,it introduces the new technique in assigning the polarity score,and second,it improves the performance over the classification of mixed language content.

关键词： Machine learning data sciences artificial intelligence opinion mining sentiment analysis sentiment lexicon lexicon-based bilingual lexicon

来源：评论

学校读者我要写书评

暂无评论

Low-Cost Green Computing-as-a-Service Testbed for SMEs: Leveraging AI and 6G for Enhanced Productivity 17

Low-Cost Green Computing-as-a-Service Testbed for SMEs: Leve...

引用

IEEE Congress on Cybermatics: 17th IEEE International Conference on Internet of Things, iThings 2024, 20th IEEE International Conference on Green Computing and Communications, GreenCom 2024, 17th IEEE International Conference on Cyber, Physical and Social Computing, CPSCom 2024, 10th IEEE International Conference on Smart Data, SmartData 2024

作者： Patwary, Mohammad N. Khan, Samiya Nawaz, Syed Junaid University of Wolverhampton Faculty of Science and Engineering WolverhamptonWV1 1LY United Kingdom University of Greenwich School of Computing and Mathematical Sciences LondonSE10 9LS United Kingdom Comsats University Islamabad Department of Electrical & Computer Engineering Islamabad Pakistan

ISBN: (纸本)9798350351637

The exponential growth in computing devices and the emergence of high-computing-dependent applications have led to a significant increase in energy demand. In response, this paper proposes the development of a novel green computing testbed aimed at addressing energy efficiency and sustainability in computing infrastructure. The testbed integrates highly energy-efficient computing infrastructure, a virtual machine-driven on-demand computing ecosystem, and Green AI model development as a service. The state-of-the-art 5G/6G infrastructure and services, such as ultra-low-latency communications, are investigated and identified as suitable for connecting the zero clients (with minimal capabilities) to remote computing and other facilities. Through a comprehensive measurement campaign, the testbed's energy efficiency and sustainability have been evaluated. This research presents a pioneering effort towards achieving sustainability in computing to support Small and Medium-sized Enterprises (SMEs) to enhance productivity with AI, with reduced cost, energy, and minimizing e-waste. © 2024 IEEE.

关键词： Green development

来源：评论

学校读者我要写书评

暂无评论

A graph-based CNN-LSTM stock price prediction algorithm with leading indicators

A graph-based CNN-LSTM stock price prediction algorithm with...

引用

作者： Wu, Jimmy Ming-Tai Li, Zhongcui Herencsar, Norbert Vo, Bay Lin, Jerry Chun-Wei Shandong University of Science and Technology Qingdao China Department of Telecommunications Faculty of Electrical Engineering and Communication Brno University of Technology Brno Czech Republic Faculty of Information Technology Ho Chi Minh City University of Technology Ho Chi Minh Viet Nam Department of Computer Science Electrical Engineering and Mathematical Sciences Western Norway University of Applied Sciences Bergen Norway

In today’s society, investment wealth management has become a mainstream of the contemporary era. Investment wealth management refers to the use of funds by investors to arrange funds reasonably, for example, savings, bank financial products, bonds, stocks, commodity spots, real estate, gold, art, and many others. Wealth management tools manage and assign families, individuals, enterprises, and institutions to achieve the purpose of increasing and maintaining value to accelerate asset growth. Among them, in investment and financial management, people’s favorite product of investment often stocks, because the stock market has great advantages and charm, especially compared with other investment methods. More and more scholars have developed methods of prediction from multiple angles for the stock market. According to the feature of financial time series and the task of price prediction, this article proposes a new framework structure to achieve a more accurate prediction of the stock price, which combines Convolution Neural Network (CNN) and Long–Short-Term Memory Neural Network (LSTM). This new method is aptly named stock sequence array convolutional LSTM (SACLSTM). It constructs a sequence array of historical data and its leading indicators (options and futures), and uses the array as the input image of the CNN framework, and extracts certain feature vectors through the convolutional layer and the layer of pooling, and as the input vector of LSTM, and takes ten stocks in U.S.A and Taiwan as the experimental data. Compared with previous methods, the prediction performance of the proposed algorithm in this article leads to better results when compared directly. © 2021, The Author(s).

关键词： Long short-term memory

来源：评论

学校读者我要写书评

暂无评论

ISPREC: Integrated Scientific Paper Recommendation using heterogeneous information network 12

ISPREC: Integrated Scientific Paper Recommendation using het...

引用

12th International Conference on Information and Knowledge Technology, IKT 2021

作者： Jafari, Elaheh Shams, Bita Haratizadeh, Saman University of Tehran Faculty of new sciences and technologies Tehran Iran Alzahra University Faculty of Mathematical Sciences Department of Computer Science Tehran Iran

ISBN: (纸本)9781665408493

Due to the rapid expansion of online scientific articles, researchers have got into trouble finding reliable articles that are relevant to their research interests. Recently, a group of scientific paper recommendation algorithms has been proposed to solve this issue. But, they have two main shortcomings. First, they can only recommend papers to experienced researchers who have published some papers and not amateur ones. Second, they ignore some valuable sources of information in scientific article libraries. This paper presents a novel Integrated Scientific Paper RECommendation approach, called ISPREC, which integrates different pieces of information as a novel heterogeneous network structure, called SPIN. Thereafter, exploits a limited random-walk algorithm for a Top-N recommendation. Extensive experiments on a real-world dataset demonstrate a significant improvement of the proposed framework of ISPREC compared to the state-of-the-art scientific paper recommendation algorithms. © 2021 IEEE.

关键词： Information services

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：