检索结果-内蒙古大学图书馆

Classifying extended,localized and critical states in quasiperiodic lattices via unsupervised learning

Chinese Physics B 2025年第1期34卷 422-427页

作者： Bohan Zheng Siyu Zhu Xingping Zhou Tong Liu School of Computer Science and Technology School of SoftwareNanjing University of Posts and TelecommunicationsNanjing 210023China Institute of Quantum Information and Technology Nanjing University of Posts and TelecommunicationsNanjing 210003China Department of Applied Physics School of ScienceNanjing University of Posts and TelecommunicationsNanjing 210003China

Classification of quantum phases is one of the most important areas of research in condensed matter *** this work,we obtain the phase diagram of one-dimensional quasiperiodic models via unsupervised ***,we choose two advanced unsupervised learning algorithms,namely,density-based spatial clustering of applications with noise(DBSCAN)and ordering points to identify the clustering structure(OPTICS),to explore the distinct phases of the Aubry–André–Harper model and the quasiperiodic p-wave *** unsupervised learning results match well with those obtained through traditional numerical ***,we assess similarity across different algorithms and find that the highest degree of similarity between the results of unsupervised learning algorithms and those of traditional algorithms exceeds 98%.Our work sheds light on applications of unsupervised learning for phase classification.

关键词： quantum phase quasiperiodic machine learning

来源：评论

学校读者我要写书评

暂无评论

Improving Sentiment Analysis in Election-Based Conversations on Twitter with ElecBERT Language Model

引用

computers, Materials & Continua 2023年第9期76卷 3345-3361页

作者： Asif Khan Huaping Zhang Nada Boudjellal Arshad Ahmad Maqbool Khan School of Computer Science and Technology Beijing Institute of TechnologyBeijing100081China The Faculty of New Information and Communication Technologies University Abdel-Hamid Mehri Constantine 2Constantine25000Algeria Department of IT and Computer Science Pak-Austria Fachhochschule:Institute of Applied Sciences and TechnologyHaripur22620Pakistan

Sentiment analysis plays a vital role in understanding public opinions and sentiments toward various *** recent years,the rise of social media platforms(SMPs)has provided a rich source of data for analyzing public opinions,particularly in the context of election-related ***,sentiment analysis of electionrelated tweets presents unique challenges due to the complex language used,including figurative expressions,sarcasm,and the spread of *** address these challenges,this paper proposes Election-focused Bidirectional Encoder Representations from Transformers(ElecBERT),a new model for sentiment analysis in the context of election-related ***-related tweets pose unique challenges for sentiment analysis due to their complex language,sarcasm,*** is based on the Bidirectional Encoder Representations from Transformers(BERT)language model and is fine-tuned on two datasets:Election-Related Sentiment-Annotated Tweets(ElecSent)-Multi-Languages,containing 5.31 million labeled tweets in multiple languages,and ElecSent-English,containing 4.75million labeled tweets in *** outperforms othermachine learning models such as Support Vector Machines(SVM),Na飗e Bayes(NB),and eXtreme Gradient Boosting(XGBoost),with an accuracy of 0.9905 and F1-score of 0.9816 on ElecSent-Multi-Languages,and an accuracy of 0.9930 and F1-score of 0.9899 on *** performance of differentmodels was compared using the 2020 United States(US)Presidential Election as a case *** ElecBERT-English and ElecBERT-Multi-Languages models outperformed BERTweet,with the ElecBERT-English model achieving aMean Absolute Error(MAE)of *** paper presents a valuable contribution to sentiment analysis in the context of election-related tweets,with potential applications in political analysis,social media management,and policymaking.

关键词： Sentiment analysis social media election prediction machine learning transformers

来源：评论

学校读者我要写书评

暂无评论

Automatic Modulation Recognition with Breast Cancer Classification for Medical Internet of Things Applications 1

Automatic Modulation Recognition with Breast Cancer Classifi...

引用

1st IEEE International Conference on Emerging Research in Computational science, ICERCS 2023

作者： Nirmalrani, V. Poornima, D. Gowri, S. Chandrasekaran, Kumaresan Sathyabama Institute of Science & Technology Department of Computer Science and Engineering Chennai India University of Technology and Applied Sciences Department of Computer Science and Engineering Oman

ISBN: (纸本)9798350359756

Medical Internet of Things (MIoT) and healthcare have lately converged, which has led to novel techniques to identifying and treating medical troubles. This research gives a completely unique method that utilizes the Internet of Things (IoT) to combine Automatic Modulation Recognition (AMR) with Breast Cancer (BC) categorization. The loss of included answers arises from the reality that most current research ignores BC type in desire for both AMR or BC type. A unique Medical Internet of Things-based totally Breast Cancer (MIoT-BC) category method addresses the project. In order to facilitate automatic modulation identity, the proposed gadget first statistics indicators from clinical gadget and wireless verbal exchange channels. After that, it uses DBNs (deep belief networks) to categorize BCs. The MIoT-primarily based strategy ensures the secure transmission and instantaneous analysis of scientific facts, which improves the precision and timeliness of diagnosis. There are some of blessings to the use of MIoT for BC categorization, such as less difficult get entry to to health information, faster diagnostic instances, and the option for faraway monitoring. In addition, the potential for misclassification and human errors is reduced, making this a useful tool inside the realm of medical diagnostics. DBNs are used to give a dependable and correct type version for BC categorization. Several healthcare packages have found achievement with DBNs due to their suitability for processing excessive-dimensional, complicated scientific facts. Differentiating benign from malignant breast lesions is an area where their capability to extract sizeable facts from enter facts robotically shines. MIoT-primarily based processes the usage of DBNs enhance BC classification accuracy in comparison to traditional techniques, consistent with this paper. Evaluation criteria, such as sensitivity, specificity, accuracy, overall performance and F1 rating, measure the effectiveness of the suggeste

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

Optimization of Vehicular Congestion Control in Traffic Signals using YOLO algorithm

Optimization of Vehicular Congestion Control in Traffic Sign...

引用

2024 International Conference on Smart Systems for Electrical, Electronics, Communication and computer Engineering, ICSSEEC 2024

作者： Sivaganesan, D. Kumar, S. Barath Krishnadharani, S. Rashmitha, G. PSG Institute of Technology and Applied Research Dept. of Computer Science and Engg Coimbatore India

ISBN: (纸本)9798350378177

The increase in the volume of vehicles utilizing our roads has highlighted the seriousness of the ongoing problem of traffic congestion. This problem is even worse at intersections, where a line of cars waits patiently for their turn to move forward. The traditional traffic light systems, which were originally intended to handle a less intense traffic load, are now having difficulty keeping up with the increasing number of vehicles, which further complicates the situation. We have adopted cutting-edge technologies, particularly those found in the fields of computer vision and machine learning, to tackle this modern dilemma. Our methodology is based on the application of a state-of-the-art system powered by a deep Convolutional Neural Network, which we call You Only Look Once (YOLO). With the help of this cutting-edge technology, we can quickly and thoroughly examine real-time data at signalized road crossings to gain a sophisticated understanding of the constantly changing traffic environment. Once we have a thorough understanding of the complex traffic dynamics thanks to YOLO's capabilities, we use this knowledge to make the most out of traffic light phases. We focus on closely examining important data elements, like the average wait time for a car and the number of cars in the line. The main goal is to create a coordinated and efficient traffic flow. This reduces the amount of time that drivers must wait in traffic overall and gives priority to safe and effective vehicle movement through intersections, resulting in a more responsive and fluid urban mobility experience. © 2024 IEEE.

关键词： Traffic congestion

来源：评论

学校读者我要写书评

暂无评论

High Resolution Solar Image Generation Using Generative Adversarial Networks

引用

Annals of Data science 2024年第5期11卷 1545-1561页

作者： Dash, Ankan Ye, Junyi Wang, Guiling Jin, Huiran Department of Computer Science New Jersey Institute of Technology NewarkNJ07102 United States School of Applied Engineering and Technology New Jersey Institute of Technology NewarkNJ07102 United States

We applied Deep Learning algorithm known as Generative Adversarial Networks (GANs) to perform solar image-to-image translation. That is, from Solar Dynamics Observatory (SDO)/Helioseismic and Magnetic Imager (HMI) line of sight magnetogram images to SDO/Atmospheric Imaging Assembly (AIA) 0304-Å images. The Ultraviolet (UV)/Extreme Ultraviolet observations like the SDO/AIA 0304-Å images were only made available to scientists in the late 1990s even though the magnetic field observations like the SDO/HMI have been available since the 1970s. Therefore, by leveraging Deep Learning algorithms like GANs we can give scientists access to complete datasets for analysis. For generating high resolution solar images, we use the Pix2PixHD and Pix2Pix algorithms. The Pix2PixHD algorithm was specifically designed for high resolution image generation tasks, and the Pix2Pix algorithm is by far the most widely used image to image translation algorithm. For training and testing we used the data for the year 2012, 2013 and 2014. After model training, we evaluated the model on the test data. The results show that our deep learning models are capable of generating high resolution (1024 × 1024 pixels) SDO/AIA0304 images from SDO/HMI line of sight magnetograms. Specifically, the pixel-to-pixel Pearson Correlation Coefficient of the images generated by Pix2PixHD and original images is as high as 0.99. The number is 0.962 if Pix2Pix is used to generate images. The results we get for our Pix2PixHD model is better than the results obtained by previous works done by others to generate SDO/AIA 0304 images. Thus, we can use these models to generate AIA0304 images when the AIA0304 data is not available which can be used for understanding space weather and giving researchers the capability to predict solar events such as Solar Flares and Coronal Mass Ejections. As far as we know, our work is the first attempt to leverage Pix2PixHD algorithm for SDO/HMI to SDO/AIA0304 image-to-image translation. © Th

关键词： Generative adversarial networks

来源：评论

学校读者我要写书评

暂无评论

Employee Fingerprint Identification Management System Based on Bidirectional ResNext Network with Triplet Loss 8

Employee Fingerprint Identification Management System Based ...

引用

8th International Conference on Management Engineering, Software Engineering and Service sciences, ICMSS 2024

作者： Yang, Yuezhi Yang, Qian Su, Zhihao Wu, Wenlong Computer Science College Guangzhou College of Applied Science and Technology Guangzhou China La Consolacion University Philippines

ISBN: (纸本)9798350393705

With the increasing digitization and modernization of enterprise management, employee fingerprint identification management systems have become a key tool to ensure the safety and efficiency of the office space. Such a system not only accurately verifies the identity of employees but can also be used for attendance, access control and other related applications. However, improving the accuracy of fingerprint recognition remains a challenge. In this paper, we propose a fingerprint identification method based on a bidirectional ResNext network and combined with triplet loss. Compared with the traditional ResNext network, our method captures richer fingerprint features through bidirectional structure and triplet loss, thereby achieving higher matching accuracy. We conducted extensive experiments on the public FVC (Fingerprint Verification Competition) dataset and our own collected dataset CSFI (Company staff fingerprint identification). Experimental results show that compared with the original ResNext network, our method achieves approximately 3% and 5% performance improvements on the two data sets respectively. These results verify the effectiveness of our proposed method on fingerprint identification tasks and provide strong technical support for the further development of employee fingerprint identification management systems. © 2024 IEEE.

关键词： Access control

来源：评论

学校读者我要写书评

暂无评论

Boosted Spider Wasp Optimizer for High-dimensional Feature Selection

引用

Journal of Bionic Engineering 2024年第5期21卷 2424-2459页

作者： Elfadil A.Mohamed Malik Sh.Braik Mohammed Azmi Al-Betar Mohammed A.Awadallah Artificial Intelligence Research Center(AIRC) College of Engineering and Information TechnologyAjman University346AjmanUnited Arab Emirates Department of Computer Science Al-Balqa Applied UniversityAl-Salt19117Jordan Department of Information Technology Al-Balqa Applied UniversityIrbid21510Jordan Department of Computer Science Al-Aqsa UniversityGaza4051Palestine Artificial Intelligence Research Center(AIRC) Ajman University346AjmanUnited Arab Emirates

With the increasing dimensionality of the data,High-dimensional Feature Selection(HFS)becomes an increasingly dif-ficult *** is not simple to find the best subset of features due to the breadth of the search space and the intricacy of the interactions between *** of the Feature Selection(FS)approaches now in use for these problems perform sig-nificantly less well when faced with such intricate situations involving high-dimensional search *** is demonstrated that meta-heuristic algorithms can provide sub-optimal results in an acceptable amount of *** paper presents a new binary Boosted version of the Spider Wasp Optimizer(BSWO)called Binary Boosted SWO(BBSWO),which combines a number of successful and promising strategies,in order to deal with *** shortcomings of the original BSWO,including early convergence,settling into local optimums,limited exploration and exploitation,and lack of population diversity,were addressed by the proposal of this new variant of *** concept of chaos optimization is introduced in BSWO,where initialization is consistently produced by utilizing the properties of sine chaos mapping.A new convergence parameter was then incorporated into BSWO to achieve a promising balance between exploration and *** exploration mechanisms were then applied in conjunction with several exploitation strategies to effectively enrich the search process of BSWO within the search ***,quantum-based optimization was added to enhance the diversity of the search agents in *** proposed BBSWO not only offers the most suitable subset of features located,but it also lessens the data's redundancy *** was evaluated using the k-Nearest Neighbor(k-NN)classifier on 23 HFS problems from the biomedical domain taken from the UCI *** results were compared with those of traditional BSWO and other well-known meta-heuristics-based *** findings indicate that,in comparison to other competing techn

关键词： High-dimensional features SWO algorithm Feature selection Optimization Machine learning

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Enabled Future Wireless Electric Vehicles with Multi-Model Learning and Decision Making Models

引用

Tsinghua science and technology 2024年第6期29卷 1776-1784页

作者： Gajula Ramesh Anil Kumar Budati Shayla Islam Louai A.Maghrabi Abdullah Al-Atwai Department of Computer Science and Engineering Gokaraju Rangaraju Institute of Engineering&TechnologyHyderabad 500090India Institute of Computer Science and Digital Innovation(ICSDI) UCSI UniversityKuala Lumpur 56000Malaysia also with Department of ECE KoneruLakshmaiah Education FoundationHyderabad 500090India ICSDI UCSI UniversityKuala Lumpur 56000Malaysia Department of Software Engineering College of EngineeringUniversity of Business and TechnologyJeddah 21448Kingdom of Saudi Arabia Department of Computer Science Applied CollegeUniversity of TabukTabuk 47512Kingdom of Saudi Arabia

In the contemporary era,driverless vehicles are a reality due to the proliferation of distributed technologies,sensing technologies,and Machine to Machine(M2M)***,the emergence of deep learning techniques provides more scope in controlling and making such vehicles energy *** existing methods,it is understood that there have been many approaches found to automate safe driving in autonomous and electric vehicles and also their energy ***,the models focus on different aspects *** is need for a comprehensive framework that exploits multiple deep learning models in order to have better control using Artificial Intelligence(AI)on autonomous driving and energy *** this end,we propose an AI-based framework for autonomous electric vehicles with multi-model learning and decision *** focuses on both safe driving in highway scenarios and energy *** deep learning based framework is realized with many models used for localization,path planning at high level,path planning at low level,reinforcement learning,transfer learning,power control,and speed *** reinforcement learning,state-action-feedback play important role in decision *** simulation implementation reveals that the efficiency of the AI-based approach towards safe driving of autonomous electric vehicle gives better performance than that of the normal electric vehicles.

关键词： wireless vehicles deep learning multi-model learning reinforcement learning Artificial Intelligence(Al)

来源：评论

学校读者我要写书评

暂无评论

A survey on textual emotion cause extraction in social networks

引用

Digital Communications and Networks 2025年第2期11卷 524-536页

作者： Sancheng Peng Lihong Cao Guojun Wang Zhouhao Ouyang Yongmei Zhou Shui Yu Laboratory of Language Engineering and Computing Center for Linguistics and Applied LinguisticsGuangdong University of Foreign StudiesGuangzhou510006China School of English Education Guangdong University of Foreign StudiesGuangzhou510006China School of Computer Science and Cyber Engineering Guangzhou UniversityGuangzhou510006China South China University of Technology Guangzhou510006China School of Information Science and Technology Guangdong University of Foreign StudiesGuangzhou510006China School of Computer Science University of Technology SydneySydneyNSW 2007Australia

With the rapid development of web technology,Social Networks(SNs)have become one of the most popular platforms for users to exchange views and to express their *** and more people are used to commenting on a certain hot spot in SNs,resulting in a large amount of texts containing *** Emotion Cause Extraction(TECE)aims to automatically extract causes for a certain emotion in texts,which is an important research issue in natural language *** is different from the previous tasks of emotion recognition and emotion *** addition,it is not limited to the shallow-level emotion classification of text,but to trace the emotion *** this paper,we provide a survey for ***,we introduce the development process and classification of ***,we discuss the existing methods and key factors for ***,we enumerate the challenges and developing trend for TECE.

关键词： Text Emotion Emotion cause Machine learning Deep learning

来源：评论

学校读者我要写书评

暂无评论

On picking sequences for chores 23

On picking sequences for chores

引用

24th ACM Conference on Economics and Computation, EC 2023

作者： Feige, Uriel Huang, Xin Computer Science and Applied Mathematics Weizmann Institute of Science Rehovot Israel Computer Science Technion - Israel Institute of Technology Haifa Israel

ISBN: (纸本)9798400701047

We consider the problem of allocating m indivisible chores to n agents with additive disvaluation (cost) functions. It is easy to show that there are picking sequences that give every agent (that uses the greedy picking strategy) a bundle of chores of disvalue at most twice her share value (maximin share, MMS, for agents of equal entitlement, and anyprice share, APS, for agents of arbitrary entitlement). Aziz, Li and Wu (2022) designed picking sequences that improve this ratio to 5/3 for the case of equal entitlement. We design picking sequences that improve the ratio to 1.733 for the case of arbitrary entitlement, and to 8/5 for the case of equal entitlement. (In fact, computer assisted analysis suggests that the ratio is smaller than 1.543 in the equal entitlement case.) We also prove a lower bound of 3/2 on the obtainable ratio when n is sufficiently *** results trivially imply that (for additive valuation over chores) in the arbitrary entitlement case, there always is an allocation that gives every agent at most 1.733APS, and in the equal entitlement case, there always is a distribution over allocations that gives every agent at most 1.6MMS ex-post, and at most the proportional share ex-ante. Neither of these implications were previously known to *** contributions of our work include improved guarantees in the equal entitlement case when n is small;introduction of the chore share as a convenient proxy to other share notions for chores;introduction of ex-ante notions of envy for risk averse agents, and enhancements to our picking sequences that eliminate such envy. © 2023 Owner/Author(s).

关键词： Additives

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：