检索结果-内蒙古大学图书馆

4th international conference on Advanced Network Technologies and Intelligent computing, ANTIC 2024

作者： Barge, Abha Arora, Sandhya MKSSS’s Cummins College of Engineering for Women Pune India

ISBN: (纸本)9783031837920

This research paper examines the efficiency of Deep learning models of LSTM and N-BEATS, and the statistical methods of ARIMA and VAR alongside the impact of macroeconomic factors-specifically the Consumer Price Index (CPI) and Interest Rates-on Microsoft’s stock prices from August 2009 to June 2020. The paper also reviews a variety of sources that analyze the statistical relationships between macroeconomic factors and the stock market, highlighting these models’ advantages for time series forecasting. While ARIMA, N-BEATS, LSTM, and VAR are recognized as top models for time series predictions, their performance varies with data characteristics, model architecture, and tuning. This paper provides a detailed explanation of the concepts and mathematical formulations behind each implemented algorithm, making it a valuable resource. In examining univariate forecasting (ARIMA, LSTM, N-BEATS) and multivariate forecasting (VAR), it’s seen that incorporating macroeconomic indicators in multivariate forecasting resulted in lower MSE and MAPE. Specifically, VAR achieved the lowest MSE of 59.5901 and MAPE of 0.0476, proving it the most efficient model among those tested. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Prediction models

来源：评论

学校读者我要写书评

暂无评论

Two-server Password authenticated Key Exchange Protocol Based on MLWE 25

Two-server Password authenticated Key Exchange Protocol Base...

引用

Proceedings of the 2025 4th international conference on Cryptography, Network Security and Communication Technology

作者： Yeming Yang Shuaichao Song Songhui Guo Information Engineering University Zhengzhou Henan China

ISBN: (纸本)9798400712623

Currently, PAKE (Password Authenticated Key Exchange) protocols on lattice using a single-server architecture are widely applied. However, such protocols are vulnerable to server leakage attacks, dictionary attacks, and other threats. To address these issues, researchers have proposed multi-server and two-server architecture-based PAKE protocols. However, PAKE protocols in a multi-server architecture require the use of complex cryptographic primitives such as signatures, and zero-knowledge proofs to ensure security, which reduces the execution efficiency of the protocol. To solve these problems, we propose a two-server PAKE protocol on the lattice based on the MLWE (Module learning with errors) problem. The protocol is built using instances of the MLWE problem and utilizes the Peikert error coordination technique, which ensures both parties with similar values arrive at the same result through computation. Additionally, we introduce the error pairing hypothesis and demonstrates its security within the random oracle model. The protocol securely stores different shares of password information across various servers. This approach protects user password data, even if one of the servers is compromised. Compared to similar protocols, we avoid the use of numerous cryptographic primitives, and can better resist quantum computing attacks and server leakage. And we reduce computational and communication costs, and can better meet practical application needs.

关键词： MLWE

来源：评论

学校读者我要写书评

暂无评论

Smart Gas Monitoring System for Classroom Safety

Smart Gas Monitoring System for Classroom Safety

引用

5th international conference on Recent Trends in Machine learning, IoT, Smart Cities, and Applications, ICMISC 2024

作者： Chandra Karuturi, Prudhvi Sai Hothur, Sai Chandra Pavan Goli, Sai Sri Kadiyala, Karthik Sri Sai Ullas, S. Department of Computer Science and Engineering Amrita School of Computing Amrita Vishwa Vidyapeetham Bengaluru India

ISBN: (纸本)9789819788644

In the current educational landscape, ensuring the safety of students and educators is crucial. Our research introduces a smart gas monitoring system designed specifically for student safety. In today’s classrooms, potential gas leaks pose a safety risk. Our solution involves strategically placing sensors within classrooms to detect harmful gases. These sensors continuously monitor air quality and, in the presence of hazardous conditions, send instant alerts to users through a user-friendly Android app. The Android app provides real-time gas concentration levels, allowing users to stay informed about their environment. By combining accessible technology with a user-friendly interface, our Smart Gas Monitoring System offers a practical and scalable solution to enhance safety in classrooms. This research aligns with the growing need for modern, reliable safety measures in educational settings, making it a valuable addition to existing safety protocols. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2025.

关键词： Android app Gas monitoring Gaseous concentration in classroom Instant alerts Sensors Toxic gases

来源：评论

学校读者我要写书评

暂无评论

A Study on the Impact of Partitioning on Community Detection in Graph Networks 6th

A Study on the Impact of Partitioning on Community Detec...

引用

6th international conference on Computational Intelligence in Communications and Business Analytics, CICBA 2024

作者： Joseph, Neethu Vidhya, S. Department of Computer Science and Engineering Amrita School of Computing Coimbatore Amrita Vishwa Vidyapeetham Coimbatore India

ISBN: (纸本)9783031813382

The rapid growth of electronic data generation, processing and storage necessitates large-scale data processing in numerous domains like road networks, car ad hoc networks, bitcoin, pictures, brain networks, and citation networks. In these applications, Graph is a natural and potent tool for describing and capturing dependence relationships between items and it is important to detect the communities within these networks for meaningful interpretation, aiding in tasks such as identifying anomalies in road traffic systems or uncovering deceptive activities on social media. This paper delves into the exploration of graph partitioning approaches, employed to segment large graphs into subgraphs and subsequently identify communities within these partitioned graph networks. The investigation focuses on modularity-based algorithms, particularly the Louvain algorithm, and examines the effectiveness of pyMetis and Deep learning-based methods in enhancing the efficiency of graph partitioning to yield reliable community detection. The experiments showed that pyMetis outperformed the GCN Method in case of graph partitioning and also showed that the computation cost is reduced while doing graph partition and then proceeding with community detection as compared to usual community detection. Also, the non-distributed and distributed methods of community detection are evaluated and the distributed approach using Ray Framework produced better results than non-distributed community detection. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Data handling

来源：评论

学校读者我要写书评

暂无评论

Predicting Salinity Resistance of Rice at the Seedling Stage: An Evaluation of Transfer learning Methods 1st

Predicting Salinity Resistance of Rice at the Seedling Stage...

引用

1st international conference on Intelligent Systems in computing and Communications, ISCComm 2023

作者： Shiragudikar, Sharada K. Bharamagoudar, Geeta K., Manohara K. Y., Malathi S. G.Totad, Shashikumar School of Computer Science and Engineering KLE Technological University Karnataka Hubballi India CSE Department KLEIT Karnataka Hubballi India Central Coastal Agricultural Research Institute Old Goa India Department of Automation and Robotics KLE Technological University Hubballi India

ISBN: (纸本)9783031756047

Rice has become one of the largest and most widely cultivated food crops in the world. Nevertheless, there is a significant probability that high amounts of salt, especially at the stage of seedling development, would have a detrimental effect on rice output. As a result, it is critical to quickly discover and develop salinity-tolerant rice crop types, particularly at the stage of seedling development, to prevent a decrease in rice output. Expertise from humans is required for the categorization of visual signals and the conventional way of a standard assessment system for identifying rice crop salinity stress. It's time demanding and prone to mistakes, both of which may lead to inaccurate classification. Recent developments in deep learning and transfer training have opened the road for the automated categorization of a wide range of agricultural jobs, from the detection of plant diseases and pests to the identification of weeds and invasive species. The lack of plant-domain-specific pre-trained models and the limited number of available datasets remain significant obstacles to agricultural automation. We use the AgriNet dataset, a database of 850 image graphs of farms and agricultural settings. The work shows the need for a deep learning developed model over the conventional way of measuring rice crop sensitivity to salt stress throughout the seedling stage to detect and categorize stress caused by salinity in the seedling stage of rice using field images. Thus, we use one of the most advanced deep learning approaches, VGG 16, VGG 19, Resnet 50, Resnet 100, exception, Resnet 50V2, Inception V3, MobileNetV2, DenseNet121, and ResNet101V2 which was built in Python's Jupyter Notebook, to construct the classification model. To further demonstrate the need for a computer-based classification system for salinity estimation that could be used as a tool for automating the classification process for rice development to aid scientists and farmers in the rice crop management

关键词： Deep learning

来源：评论

学校读者我要写书评

暂无评论

Machine learning Algorithms for Identifying Spam Emails 1st

Machine Learning Algorithms for Identifying Spam Emails

引用

1st international conference on Artificial Intelligence and its Applications, ICAIA 2023

作者： Kiran, Ajmeera Khan, Mudassir Babu, J. Chinna Kumar, B. P. Santosh Department of Computer Science and Engineering MLR Institute of Technology Telangana Hyderabad500043 India Department of Computer Science College of Science and Arts Tanumah King Khalid University Abha Saudi Arabia Department of ECE Annamacharya Institute of Technology and Sciences AP Rajampet India Department of ECE YSR Engineering College YV University AP Proddatur India

ISBN: (纸本)9783031843938

Emails are utilised in practically all spheres of today's society, from the professional world to the academic sphere. Ham and spam are the two subcategories that may be found within emails. Email spam, also known as junk email or unwelcome email, is a sort of email that may be used to cause harm to any user by wasting his or her time, using an excessive amount of computing resources, and stealing important information. The proportion of unsolicited emails is rising at an alarming rate day by day. Predicting the value of a company's stock is difficult for academics, investors, and analysts. The majority of people are interested in learning about stock prices in order to enhance their own finances. Long-Short-Term Memory (LSTM) is the abbreviation for the time series notation. In today's market, a stock trading system needs to adhere to this paradigm and combine KNN and LSTM in order to achieve higher levels of accuracy in its models. The majority of people in today's world improve their financial situations by trading on the stock market. When this doesn't work, individuals’ resort to criminal behaviour. The two equities are compared using this procedure. In order to solve the problems that the pure KNN method was having with distance metrics, the suggested model uses an optimised version of the KNN technique. The fact that the majority of test data in the present KNN is focused on focal points has no impact on the stock prediction because all of the qualities are connected. The Programme places a greater emphasis on data points that are favorable rather than ones that are centered. The KNN distance probability is determined by an optimization procedure. The present iteration of the KNN model demands a significant amount of memory in addition to other resources so that it can compute the distance between each data point and the test point. By removing duplicates, the procedure eliminates the need to double-check the records. The procedure is sped up by reducing the

关键词： Financial markets

来源：评论

学校读者我要写书评

暂无评论

The state-of-the-art in cardiac MRI reconstruction: Results of the CMRxRecon challenge in MICCAI 2023

引用

MEDICAL IMAGE ANALYSIS 2025年 101卷 103485页

作者： Lyu, Jun Qin, Chen Wang, Shuo Wang, Fanwen Li, Yan Wang, Zi Guo, Kunyuan Ouyang, Cheng Taenzer, Michael Liu, Meng Sun, Longyu Sun, Mengting Li, Qing Shi, Zhang Hua, Sha Li, Hao Chen, Zhensen Zhang, Zhenlin Xin, Bingyu Metaxas, Dimitris N. Yiasemis, George Teuwen, Jonas Zhang, Liping Chen, Weitian Zhao, Yidong Tao, Qian Pang, Yanwei Liu, Xiaohan Razumov, Artem V. Dylov, Dmitry Dou, Quan Yan, Kang Xue, Yuyang Du, Yuning Dietlmeier, Julia Garcia-Cabrera, Carles Hemidi, Ziad Al-Haj Vogt, Nora Xu, Ziqiang Zhang, Yajing Chu, Ying-Hua Chen, Weibo Bai, Wenjia Zhuang, Xiahai Qin, Jing Wu, Lianming Yang, Guang Qu, Xiaobo Wang, He Wang, Chengyan Yantai Univ Sch Comp & Control Engn Yantai Peoples R China Imperial Coll London Dept Elect & Elect Engn & I X London England Fudan Univ Digital Med Res Ctr Sch Basic Med Sci Shanghai Peoples R China Imperial Coll London Bioengn Dept & Imperial X London W12 7SL England Royal Brompton Hosp Cardiovasc Magnet Resonance Unit London SW3 6NP England Kings Coll London Sch Biomed Engn & Imaging Sci London WC2R 2LS England Shanghai Jiao Tong Univ Sch Med Ruijin Hosp Dept Radiol Shanghai Peoples R China Xiamen Univ Natl Inst Data Sci Hlth & Med Dept Elect Sci Fujian Prov Key Lab Plasma & Magnet Resonance Xiamen Peoples R China Imperial Coll London Dept Comp London SW7 2AZ England Imperial Coll London Dept Brain Sci London SW7 2AZ England Fudan Univ Shanghai Pudong Hosp Shanghai Peoples R China Fudan Univ Human Phenome Inst 825 Zhangheng Rd Shanghai 201203 Peoples R China Int Human Phenome Inst Shanghai Shanghai Peoples R China Fudan Univ Zhongshan Hosp Dept Radiol Shanghai Peoples R China Shanghai Jiao Tong Univ RuiJin Hosp Lu Wan Branch Dept Urol Sch Med Shanghai Peoples R China Fudan Univ Inst Sci & Technol Brain Inspired Intelligence Shanghai 200433 Peoples R China Rutgers State Univ Dept Comp Sci New Brunswick NJ 08901 USA Netherlands Canc Inst Dept Immunol Plesmanlaan 121 NL-1066 CX Amsterdam Netherlands Chinese Univ Hong Kong Dept Imaging & Intervent Radiol CUHK Lab AI Radiol CLAIR Shatin Hong Kong Peoples R China Delft Univ Technol Dept Imaging Phys Lorentzweg 1 NL-2628 CJ Delft Netherlands Tianjin Univ Sch Elect & Informat Engn TJK BIIT Lab Tianjin 300072 Peoples R China Inst Appl Phys & Computat Math Beijing 100094 Peoples R China Skolkovo Inst Sci & Technol Ctr Artificial Intelligence Technol Bolshoy Blvd 30Bld 1 Moscow 121205 Russia Univ Virginia Dept Biomed Engn 415 Lane Rd Charlottesville VA 22903 USA Univ Edinburgh Inst Imaging Data & Commun IDCOM Edinburgh EH9 3FG Scotland Dublin City Univ Insight SFI Res Ctr Data Analy

Cardiac magnetic resonance imaging (MRI) provides detailed and quantitative evaluation of the heart's structure, function, and tissue characteristics with high-resolution spatial-temporal imaging. However, its slow imaging speed and motion artifacts are notable limitations. Undersampling reconstruction, especially data- driven algorithms, has emerged as a promising solution to accelerate scans and enhance imaging performance using highly under-sampled data. Nevertheless, the scarcity of publicly available cardiac k-space datasets and evaluation platform hinder the development of data-driven reconstruction algorithms. To address this issue, we organized the Cardiac MRI Reconstruction Challenge (CMRxRecon) in 2023, in collaboration with the 26th international conference on Medical Image computing and Computer-Assisted Intervention (MICCAI). CMRxRecon presented an extensive k-space dataset comprising cine and mapping raw data, accompanied by detailed annotations of cardiac anatomical structures. With overwhelming participation, the challenge attracted more than 285 teams and over 600 participants. Among them, 22 teams successfully submitted Docker containers for the testing phase, with 7 teams submitted for both cine and mapping tasks. All teams use deep learning based approaches, indicating that deep learning has predominately become a promising solution for the problem. The first-place winner of both tasks utilizes the E2E-VarNet architecture as backbones. In contrast, U-Net is still the most popular backbone for both multi-coil and single-coil reconstructions. This paper provides a comprehensive overview of the challenge design, presents a summary of the submitted results, reviews the employed methods, and offers an in-depth discussion that aims to inspire future advancements in cardiac MRI reconstruction models. The summary emphasizes the effective strategies observed in Cardiac MRI reconstruction, including backbone architecture, loss function, pre-processing tech

关键词： Reconstruction Cardiac imaging Fast imaging Under-sampling K-space

来源：评论

学校读者我要写书评

暂无评论

Advanced Threat Intelligence Systems for Early Warning of Cyber Hacking 3rd

Advanced Threat Intelligence Systems for Early Warning of Cy...

引用

3rd international conference on Advancements in Smart computing and Information Security, ASCIS 2024

作者： Sharath, T. Muthukumaravel, A. Chennai India Chennai India

ISBN: (纸本)9783031863042

As we continue to deploy state-of-the-art cybersecurity measures, targeted cyber-attacks have increased in scale and frequency. A Research on a New Advanced Threat Intelligence System for Early Warning in Cyber Attack based on Realtime Monitoring, Machine learning and Big data Analytics The system combines, tidies and synthesizes data across disparate sources. It uses supervised and unsupervised machine learning models to assess the risks in that case. ATIS have introduced big data tools to conduct fast large-scale data analysis to predict threats online and activate alerts;In a controlled evaluation of ATIS, there was seen to be an improvement in the accuracy and reduction in false positives associated with threat detection. This new method gives an end-to-end cybersecurity solution for proactive security services, which allows organizations to gather such required data on a timely basis and respond when the attack takes place. The main objective of this research is to predict the cyber attack in the field of data engineering. Here the proposed algorithm Random Forest (RF) gave best accuracy of 95.154%, precision of 92%, recall of 94%, f1 score of 93% and AUC-ROC of 0.97 which is high compared to other existing algorithms. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Unsupervised learning

来源：评论

学校读者我要写书评

暂无评论

Simulation and Operation of 6DoF Robotic Arms: a Microservices Approach 16th

Simulation and Operation of 6DoF Robotic Arms: a Microser...

引用

16th EAI international conference on Simulation Tools and Techniques, SIMUTools 2024

作者： Munoz-Gonzalez, Tomas Farias, Adalberto Piñero-Fuentes, Enrique Rios-Navarro, Antonio Segura-Ramos, Sergio Linares-Barranco, Alejandro Smart Computer Engineering Research Lab I3US Universidad de Sevilla Seville Spain Systems and Computing Department Federal University of Campina Grande Campina Grande Brazil

ISBN: (纸本)9783031873447

The use of robotic arms in industrial and academic settings has grown exponentially, however, the process of simulating and operating these systems continues to be a significant challenge, particularly for users without prior experience. The learning curve is steep due to the technical complexity associated with programming, calibrating and controlling precise movements, which can be daunting. Robotic devices are usually controlled using proprietary software or ad-hoc low-level programs, hindering their shared use and integration with other applications. This work presents a software application for robotic arm trajectory simulation, with a remote service for allowing access control and arbitration in the use of robots as a shared service. This software allows the design of trajectories in robot and Cartesian coordinate spaces in a simple and convenient way for the user. The service allows the execution of said trajectories whenever the robot is available. Robotic arms ED-RobotAnno and ROS-RobotAnno are presented as use cases for this service. Concepts such as closed-loop motor control or direct robot kinematics are abstracted from the user, allowing the creation of unsupervised learning iterations of closed-loop trajectories or the creation of datasets for supervised training. Moreover, the servitization is based on a heterogeneous ecosystem composed of microservices that use different platforms/languages to provide a novel Web experience to users, while still being flexible to allow easy addition of new robotic arms. © ICST Institute for Computer Sciences, Social Informatics and Telecommunications engineering 2025.

关键词： Robotic arms

来源：评论

学校读者我要写书评

暂无评论

An Ensemble Method for Insider Threat Detection Based on User Activities Analysis Using Bi-LSTM and GA Optimization 3rd

An Ensemble Method for Insider Threat Detection Based on Use...

引用

3rd international conference on Advancements in Smart computing and Information Security, ASCIS 2024

作者： Anju, A. Freeda, Adline Venket, Krithika Kurian, Babymol Sudha, D. Mercy, W. Department of Information Technology KCG College of Technology Chennai India Department of Artificial Intelligence KCG College of Technology Chennai India Department of CSE KCG College of Technology Chennai India

ISBN: (纸本)9783031863042

One of the main reasons why firms experience security breaches is insider threats. They are users or workers of an organization who carry out any malicious conduct with the intention of harming others. The majority of insider threat detection techniques currently in use depend on deep learning and machine learning techniques and have the following drawbacks: they need obvious feature engineering, which increases the number of false positives;they rely on established criteria or maintained patterns and fail to detect novel or unidentified threats they are highly computational and need a large amount of training data. For an improved client behavior-based insider threat identification system, this study proposes an integrated learning strategy to overcome the aforementioned limitations. An ensemble model Bidirectional long-short-term memory and uses a CNN, ANN with GA and Meta Learner also used to find the best solution by combining all models predictions. The first kernel selection for CNN is done using the fast global search method of the genetic algorithm. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2025.

关键词： Deep learning

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：