检索结果-内蒙古大学图书馆

4th International Conference on Recent Trends in Machine Learning, IoT, Smart Cities, and Applications, ICMISC 2023

作者： Gangone, Anjali Bharat Kumar, G.J. Gangone, Swapna Department of Computer Science and Engineering CMR Institute of Technology Telangana Hyderabad India Department of Computer Science Mattu University Mattu Ethiopia

ISBN: (纸本)9789819994410

This paper presents a comprehensive design and implementation of a Sunward Solar-Powered Wireless Soil Moisture Sensor, which combines cutting-edge technology to enable energy-efficient soil moisture measurement and wireless data transmission. The proposed sensor system employs capacitance-based soil moisture measurement principles and incorporates innovative design elements to reduce costs and simplify installation. It also integrates solar power technology to ensure autonomous and sustainable operation. The core components of the system include a microcontroller (MSP430F149), a Wireless Transceiver Unit (nRF905), a Soil Moisture Sensor Unit with annular and conical electrodes, and a servo motor-based solar panel module for optimal solar energy capture. The sensor's power consumption is meticulously analyzed, and its energy requirements are met by a combination of solar panels and rechargeable batteries. The design of the Sunward Solar Panel Module, featuring a spherical servo motor, is a highlight of this system. The servo motor ensures precise tracking of the sun's position, optimizing solar panel orientation for maximum energy generation. Four Light-Dependent Resistors (LDRs) strategically placed on the solar panel aid in this tracking process. Through this innovative system, real-time soil moisture data can be collected and wirelessly transmitted over long distances, making it a valuable tool for applications in agriculture and environmental monitoring. The paper also discusses the dimensions and efficiency of the solar panel, ensuring that it meets the energy needs of the sensor. It achieves the main objective of this research, that is, not only in day time when sun is with more intensity but also in the low-intensity times like morning and evenings, the proposed design exhibits better results. © The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd. 2024.

关键词： Solar energy

来源：评论

学校读者我要写书评

暂无评论

Exploring the Adoption and Innovation of Digital Twins in Healthcare 16

Exploring the Adoption and Innovation of Digital Twins in He...

引用

16th International Conference on Ambient Systems, Networks and Technologies Networks, ANT 2025 / 8th International Conference on Emerging Data and Industry 4.0, EDI40 2025

作者： John, Thomas Nath, Keshab Guravaiah, Koppala Department of Computer Science and Engineering Indian Institute of Information Technology Kerala Kottayam686635 India Department of Computer Science and Engineering Bhattadev University Assam India

Digital Twins replicate the real situations and the outcomes, helping organizations to make better decisions. Digital Twins find valuable in different domains such as manufacturing, automotive, healthcare, and etc. In healthcare, the report is transferred to a digital environment after the patient had a physical examination. This aids in a proper diagnosis and appropriate therapy for the patient, which is one of the most crucial aspects of medical care. Robots that assist in surgical decision-making have benefited from digital twins. There were different studies that have been made for the use of Digital Twins in the field of Healthcare. The surveys conducted in the subject of digital twins are identified in this research together with their benefits and limitations. In this paper, a comprehensive overview of the Literature reviews done on Digital Twins especially in healthcare space. This paper details about the different technologies as well as the operations using Digital Twins with respect to healthcare. The paper explains the different applications, challenges, and issues of Digital Twins. This study examines the real-world applications of digital twins in healthcare research. The overall goal of this paper is to look for the future of the field of Digital Twins and its possible setbacks and opportunities in the field of healthcare. © 2025 Elsevier B.V.. All rights reserved.

关键词： Surgery

来源：评论

学校读者我要写书评

暂无评论

Guarding Against IoT Threats: An Analysis of Intrusion Detection with the Kitsune Attack Dataset 4

Guarding Against IoT Threats: An Analysis of Intrusion Detec...

引用

4th International Conference on Technological Advancements in Computational sciences, ICTACS 2024

作者： Sharma, Anshika Babbar, Himanshi Chitkara University Institute of Engineering and Technology Chitkara University Department of Computer Science Punjab India

ISBN: (纸本)9798350387490

The extensive adoption of Internet of Things (IoT) devices has resulted in previously unheard-of levels of connectedness and ease, but it has also created new cybersecurity challenges. Hackers are turning an increasing number of IoT devices into their targets. They take advantage of security flaws to execute a variety of attacks, from botnet malware attacks and distributed denial-of-service (DDoS) attacks to surveillance, reconnaissance (recon.) and man-in-the-middle(MITM) attacks. Innovative detection techniques are required because traditional security systems typically cannot keep up with the dynamic and varied nature of IoT environments. Using the Kitsune attack dataset, a large collection of network traffic captures that have been carefully chosen for use in network intrusion detection system (NIDS) research, the effectiveness of machine learning (ML)-based techniques have been examined for identifying IoT attacks in this study. Utilising characteristics taken from network traffic data, such as communication patterns, payload attributes, and packet headers, investigate how well-supervised learning algorithms like Support Vector Machines (SVM), Random Forest (RF), Logistic Regression (LR), and K-Nearest Neighbours (KNN) perform. Each algorithm's detection performance has been assessed using metrics including accuracy, precision, recall, and F1-score. Their respective advantages and disadvantages in terms of scalability, computational efficiency, and detection accuracy have also been compared. Additionally, the effects of feature selection and ensemble learning approaches have been evaluated on detection performance, offering recommendations for constructing durable and dependable IoT-IDS. The results show that, at 98.99%, the LR model has the highest accuracy. On the other side, the accuracy rates of the KNN, SVM and RF models are 79.42%, 92.75%, and 97.98%, respectively. © 2024 IEEE.

关键词： Network intrusion

来源：评论

学校读者我要写书评

暂无评论

Cracking Down on Digital Misogyny with MULTILATE a MULTImodaL hATE Detection System 25

Cracking Down on Digital Misogyny with MULTILATE a MULTImoda...

引用

25th Working Notes of the Conference and Labs of the Evaluation Forum, CLEF 2024

作者： Vetagiri, Advaitha Mogha, Prateek Pakray, Partha Department of Computer Science and Engineering National Institute of Technology Assam Silchar788010 India Department of Electrical Engineering National Institute of Technology Assam Silchar788010 India

Sexism in social networks manifests in various forms, from blatant misogyny to subtle, implicit biases, presenting a significant societal challenge that necessitates effective detection and mitigation strategies. Addressing this issue involves participation in the EXIST 2024 tasks, a competition designed to advance the identification of sexist content in social media. This year's contest includes both traditional text-based data from tweets and an innovative meme dataset, incorporating both images and text. The approach leverages sophisticated models to analyze these multimodal inputs. For textual modalities, a Convolutional Neural Network - Bidirectional Long Short-Term Memory model is employed to discern sexist language and tweet behaviours. For image modalities, a combination of Residual Network 50 and text-based analysis is utilized to detect and interpret sexist elements within memes. Both models undergo hyperparameter tuning and k-fold cross-validation to ensure robustness and accuracy. Preliminary results indicate that integrating these methods enhances the precision and effectiveness of sexism detection, providing a comprehensive tool for identifying and addressing sexist content in diverse social media formats. © 2024 Copyright for this paper by its authors.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Age Based Hybrid Recommendation System using Machine Learning 3

Age Based Hybrid Recommendation System using Machine Learnin...

引用

3rd International Conference on Innovative Sustainable Computational Technologies, CISCT 2023

作者： Karthikeya, Andhoju Kumar, Alle Aniesh Manicharan, Chennuri Hariharan, Shanmugasundaram Kukreja, Vinay Prasad, Andraju Bhanu Vardhaman College of Engineering Department of Computer Science and Engineering Hyderabad India Chitkara University Institute of Engineering and Technology Chitkara University Department of Computer Science and Engineering Punjab India

ISBN: (纸本)9798350303360

The recommendation system is one of the bigger developments brought about by machine learning in the machine-human interactions. In practically every area, including entertainment, e-commerce, farming, health, etc., recommendation systems are the primary players in delivering greater personalization. When it comes to content-based recommendation systems, there are many social platforms which uses recommendation system for providing improved personalization to their users and to access these social platforms the user need to have an account in that particular social platform. These platforms have different categories of content where not everyone is eligible to a particular content category. There are scenarios where different users may use the same account to access an entertainment application, or if a user inadvertently watched some inappropriate content, the recommendation system will make inappropriate recommendations, which can have an impact on the user's mental health-children. Therefore, after conducting research on the problem statement and reviewing various existing research works, machine learning model is proposed that offers recommendations to the user after determining the user's age and gender in order to deliver appropriate recommendations to the users. © 2023 IEEE.

关键词： Recommender systems

来源：评论

学校读者我要写书评

暂无评论

DPT‐tracker:Dual pooling transformer for efficient visual tracking

引用

CAAI Transactions on Intelligence technology 2024年第4期9卷 948-959页

作者： Yang Fang Bailian Xie Uswah Khairuddin Zijian Min Bingbing Jiang Weisheng Li Key Laboratory of Data Engineering and Visual Computing Chongqing University of Posts and TelecommunicationsChongqingChina Department of Mechanical Precision Engineering Malaysia‐Japan International Institute of TechnologyUniversity of Technology MalaysiaKuala LumpurMalaysia Department of Electrical and Computer Engineering Inha UniversityIncheonRepublic of Korea School of Information Science and Technology Hangzhou Normal UniversityHangzhouChina

Transformer tracking always takes paired template and search images as encoder input and conduct feature extraction and target‐search feature correlation by self and/or cross attention operations,thus the model complexity will grow quadratically with the number of input *** alleviate the burden of this tracking paradigm and facilitate practical deployment of Transformer‐based trackers,we propose a dual pooling transformer tracking framework,dubbed as DPT,which consists of three components:a simple yet efficient spatiotemporal attention model(SAM),a mutual correlation pooling Trans-former(MCPT)and a multiscale aggregation pooling Transformer(MAPT).SAM is designed to gracefully aggregates temporal dynamics and spatial appearance information of multi‐frame templates along space‐time *** aims to capture multi‐scale pooled and correlated contextual features,which is followed by MAPT that aggregates multi‐scale features into a unified feature representation for tracking *** tracker achieves AUC score of 69.5 on LaSOT and precision score of 82.8 on Track-ingNet while maintaining a shorter sequence length of attention tokens,fewer parameters and FLOPs compared to existing state‐of‐the‐art(SOTA)Transformer tracking *** experiments demonstrate that DPT tracker yields a strong real‐time tracking baseline with a good trade‐off between tracking performance and inference efficiency.

关键词： human‐computer interfacing image motion analysis pattern recognition signal processing tracking

来源：评论

学校读者我要写书评

暂无评论

Influence of Opinion Formation on Polarization in Social Networks 14

Influence of Opinion Formation on Polarization in Social Net...

引用

14th International Conference on Computing Communication and Networking Technologies, ICCCNT 2023

作者： Das, Susmita Dutta, Sangita Chakraborty, Susanta Biswas, Samit Indian Institute of Engineering Science and Technology Department of Computer Science and Technology Shibpur711103 India

ISBN: (纸本)9798350335095

Online social networks have introduced diverse discussions regarding different topics. At the same time, these platforms have also garnered the idea of shaping opinions. The increase in user engagement in case of arguments has led to the issue of polarization in online social media platforms. In this paper, we have studied the influence of opinion change on homophily in social networks and the variation in polarization. Our own new method has been proposed for analysing the modification of user opinions dynamically in different timestamps. The probability of information sharing varies depending on the opinion similarity and homophily in social networks alters accordingly. Our approach portrays the opinion modification dynamics for different network features using complex networks concepts. We have observed that on social interaction networks like Twitter, opinion, information sharing and homophily perform a significant role in the determination of online polarization. Our approach has been compared with an established approach over external datasets and the results obtained are promising. © 2023 IEEE.

关键词： Polarization

来源：评论

学校读者我要写书评

暂无评论

From Ranch to Worldwide:Observing Soil Welbeing Patterns

From Ranch to Worldwide:Observing Soil Welbeing Patterns

引用

2024 International Conference on Knowledge engineering and Communication Systems, ICKECS 2024

作者： Divakar, K.M. Ankith Gowrishankar Esturi, R. Anil, P.S. Namith, D. Chethan, A. S J C Institute of Technology Dept. of Computer Science Engineering Chikkaballapur India

ISBN: (纸本)9798350359688

Declining soil wellbeing represents a huge danger to worldwide food security and rural maintainability. Precisely checking soil wellbeing patterns and anticipating future land appropriateness at nearby and worldwide scales are essential for illuminating feasible administration practices and strategy intercessions. This paper proposes a clever structure that use the force of large information investigation to address this test. We expect to overcome any issues between ranch level checking and worldwide experiences, engaging partners at each level to come to informed conclusions about land use and management. Our structure depends on the mix of assorted information sources. High-goal remote detecting information, including satellite symbolism and aeronautical photography, will give basic experiences into soil properties, crop conditions, and land the board rehearses. We will additionally improve the examination by consolidating promptly accessible open-access datasets on environment, soil overviews, and financial data. This exhaustive information combination approach permits us to catch the diverse idea of soil wellbeing and land reasonableness dynamics. Extracting significant experiences from these tremendous datasets requires clever examination devices. We will use a setup of AI procedures, including regulated and solo learning calculations, to reveal stowed away examples and connections inside the information. Directed learning will empower us to foster prescient models for soil wellbeing appraisal and land appropriateness planning, while solo learning will assist with recognizing remarkable attributes and likely peculiarities in various farming *** system will create constant soil wellbeing maps, featuring areas of corruption, supplement lacks, and potential improvement open doors. This enables ranchers to come to informed conclusions about manure application, water the board, and harvest choice, advancing their activities for expanded yield and long ha

关键词： Fertilizers

来源：评论

学校读者我要写书评

暂无评论

An Optimized TF-IDF Features based Deep Learning Enabled Automated Fake News Detection Scheme

An Optimized TF-IDF Features based Deep Learning Enabled Aut...

引用

2024 Asia Pacific Conference on Innovation in technology, APCIT 2024

作者： Aggarwal, Nikhil Kumar, Siddharth Chandigarh University Apex Institute of Technology Department of Computer Science and Engineering Punjab Mohali India

ISBN: (纸本)9798350361537

People are exposed to a variety of false news and disinformation because of the continuously changing social media landscape and the various sources of information used by news organizations and production companies. We are now conducting research to find useful techniques to detect this false news, and the designed system is known as deep learning enabled an automated Fake News Detection (FND) system. The categorization or identification of fake news in online social media platforms has drawn more interest from the machine learning community. Misleading news refers to news stories that purposefully mislead readers by disseminating false information. In this post, we suggest a solution for social media platforms that automatically detects bogus news. Pre-processing, extraction of features, feature optimization, and classification were the four processes employed by the suggested system. Here, the concept of Term Frequency-Inverted Document Frequency (TF-IDF)-based approach is used as the feature extraction scheme and the extracted features are optimized using the concept of swarm-based Artificial Bee Colony (ABC) by designing an appropriate and novel fitness/objective function. ABC creates two categories of news, first as Fake and second as Real. Based on these categories, further Convolutional Neural Network (CNN) is used to train the FND model. To verify the effectiveness of the suggested FND model, parameters like Precision, Recall, and F-measure (PRF) with Accuracy are computed. Finally, I assess how the suggested FND system performs in comparison to current models. to validate the performance in terms of PRF and we observed that the FND system got better results with accuracy of 99% for most of the cases. © 2024 IEEE.

关键词： Convolutional neural networks

来源：评论

学校读者我要写书评

暂无评论

Breast Cancer Detection in Image Processing

Breast Cancer Detection in Image Processing

引用

2024 International Conference on Innovations and Challenges in Emerging Technologies, ICICET 2024

作者： Ramesh, Sai Adhithya, G. Charithra, E. St.Joseph's Institute of Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350319019

One in eight women are diagnosed with breast cancer and thirty percent of women not up to date screening recommandations, if diagnosed early effects can be reduced. Breast Cancer is becoming less uncommon. As a result, identifying BC and determining the affected region of the breast is more essential. Images from Screening for a Mammography. The two perspectives, CC and MLO, are often used in the diagnosis process. This paper describes a method for detecting cancer regions and classifying patients as normal or cancerous. The preliminary processing involves taking the input mammogram image, removing any unwanted parts, segmenting the tumor region using morphological operations, and highlighting the relevant area on the original image. If the mammogram image is normal, it indicates that the patient is normal. © 2024 IEEE.

关键词： Mammography

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：