检索结果-内蒙古大学图书馆

15th International Conference on Contemporary Computing, IC3 2023

作者： Asha, S. Vinod, P. Menon, Varun G. Department of Computer Science & Engineering SCMS School of Engineering & Technology APJ Abdul Kalam Technological University Trivandrum India Department of Computer Applications Cochin University of Science & Technology Cochin India Department of Computer Science & Engineering SCMS School of Engineering & Technology Ernakulam India

ISBN: (纸本)9798400700224

A multi-modal deepfake dataset is relevant in addressing the growing concern of deepfake misuse, which poses a significant security and privacy threat. Deepfakes are becoming increasingly sophisticated, and their potential to deceive individuals and organizations is a significant issue. The ability to generate synthesized human voices using deep learning models and inserting fake subtitles has added to this problem, making it more challenging to detect deepfakes accurately. A superior quality dataset is essential to developing a competent deepfake detector. However, existing datasets are limited and often biased, making it difficult to detect deepfakes accurately. A multi-modal deepfake dataset, such as the proposed multi-modal Audio-Video-Text Deepfake dataset (MMDFD) addresses this gap by providing a more realistic and unbiased dataset. Such a dataset helps develop more accurate and effective deepfake detection methods, which can detect audio, video, and textual deepfakes simultaneously. The proposed dataset is more reflective of situations in the real world since it contains actual YouTube recordings of celebrities from four different racial origins. This helps to avoid the creation of deepfake detectors that are biased toward certain racial or ethnic groups. Overall, a multi-modal deepfake dataset is essential in addressing the growing concerns of deepfake misuse and developing effective detection methods that can detect deepfakes accurately, regardless of the medium. © 2023 ACM.

关键词： Deep neural networks

来源：评论

学校读者我要写书评

暂无评论

IoT Smart Driving Protocol for Unmanned Ground Vehicles: A Comparative Study 5

IoT Smart Driving Protocol for Unmanned Ground Vehicles: A C...

引用

5th International Conference on IoT Based Control Networks and Intelligent Systems, ICICNIS 2024

作者： Seelam, Santhosh Kumar Nagakishorebhavanam, S. Midasala, Vasujadevi Reddy, Edara Sreenivasa University College of Engineering and Technology Department of Computer Science and Engineering Acharya Nagarjuna University Andhra Pradesh Guntur India Barela Department of Computer Science and Engineering Madhya Pradesh Jabalpur India VIT-AP University Department of Computer Science and Engineering Andhra Pradesh Amaravati India

ISBN: (纸本)9798331518097

UGVs are an emerging force of change in autonomous systems, ranging from logistics and agriculture to military applications. So far, there have been a wide number of applications of UGVs for military, civilian, and civil use. However, UGVs are also for use in both civilians and military servicemen. The paper aims to critically present a comparative review of the different protocols of IoT-based smart driving, including V2X, ITS, and DSRC, and intend to identify certain strengths and limitations of the same with respect to operations involving UGVs. In this regard, it proposes a new protocol design to contribute toward enhancing communication efficiency and reliability by reducing latency in real-time decision-making capabilities in various types of operational environments. © 2024 IEEE.

关键词： Smart agriculture

来源：评论

学校读者我要写书评

暂无评论

An enhanced approach for analyzing the performance of heart stroke prediction with machine learning techniques

引用

International Journal of Information technology (Singapore) 2023年第6期15卷 3257-3270页

作者： Mishra, Indrani Mohapatra, Subasish Department of Computer Science and Engineering Odisha University of Technology and Research Bhubaneswar India

The heart is one of the most vital organs in our body and crucial for proper bodily function, an unfit heart can seriously affect fitness, lifestyle and severely decrease the expected lifetime of an individual making a healthy heart necessary for survival. An early detection system for signs of a heart attack must be implemented in light of the alarming rise in the number of heart attacks in children and young adults. There has to be a method in place that is both convenient and accurate in forecasting the likelihood of a cardiac condition for the average person, such as the ECG. It has recently become easier to predict heart attacks due to machine learning (ML). Traditional prediction models and methodologies, on the other hand, are inadequate for gathering fundamental data because of their inability to imitate the high quality of mapping negative medical features. We forecast the survival of a cardiac patient using enhanced machine learning. Predicting a patient's risk of mortality from heart failure is based on information such as gender, age, blood pressure, kind of job, blood glucose, and body mass index. Support Vector Machine (SVM), Random Forest (RF), Navies Bayes (NB), Logistic Regression (LR), and Decision Tree (DT) are just a few of the machine learning-based classification algorithms that have been built and tested. The results of the experiments show that using 80% training and 20% testing, SVM can predict heart disease with an accuracy of 96.0%. © 2023, The Author(s), under exclusive licence to Bharati Vidyapeeth's Institute of computer Applications and Management.

关键词： Feature selection Heart stroke Logistic regression Machine learning Risk level classification

来源：评论

学校读者我要写书评

暂无评论

LSTDA: Link Stability and Transmission Delay Aware Routing Mechanism for Flying Ad-Hoc Network (FANET)

引用

computers, Materials & Continua 2023年第10期77卷 963-981页

作者： Farman Ali Khalid Zaman Babar Shah Tariq Hussain Habib Ullah Altaf Hussain Daehan Kwak Department of Computer Science and Engineering Sungkyunkwan UniversitySeoul03063South Korea Information Engineering School Chang’an UniversityXi’an710061China College of Technological Innovation Zayed UniversityDubai19282United Arab Emirates School of Computer Science and Technology Zhejiang Gongshang UniversityHangzhou310018China Institute of Computer Science and IT The University of Agriculture PeshawarPeshawer25120Pakistan Department of Computer Science and Technology Kean UniversityUnionNew Jersey07083USA

The paper presents a new protocol called Link Stability and Transmission Delay Aware(LSTDA)for Flying Adhoc Network(FANET)with a focus on network corridors(NC).FANET consists of Unmanned Aerial Vehicles(UAVs)that face challenges in avoiding transmission loss and delay while ensuring stable *** proposed protocol introduces a novel link stability with network corridors priority node selection to check and ensure fair communication in the entire *** protocol uses a Red-Black(R-B)tree to achieve maximum channel utilization and an advanced relay *** paper evaluates LSTDA in terms of End-to-End Delay(E2ED),Packet Delivery Ratio(PDR),Network Lifetime(NLT),and Transmission Loss(TL),and compares it with existing methods such as Link Stability Estimation-based Routing(LEPR),Distributed Priority Tree-based Routing(DPTR),and Delay and Link Stability Aware(DLSA)using MATLAB *** results show that LSTDA outperforms the other protocols,with lower average delay,higher average PDR,longer average NLT,and comparable average TL.

关键词： LSTDA routing protocol Flying Ad-hoc Network link stability unmanned aerial vehicles maxim priority channel

来源：评论

学校读者我要写书评

暂无评论

Blockchain based Identity Generator and Authenticator 3

Blockchain based Identity Generator and Authenticator

引用

3rd International Conference on Intelligent and Innovative Technologies in Computing, Electrical and Electronics, IITCEE 2025

作者： Akhil, V. Hareesh, R. Yesudas, P.Y. Venugopalan, Anand Meera, K. Menon, Hema P. Sreepathy Institute of Management and Technology Department of Computer Science and Engineering Vavannor Kerala Palakkad India

ISBN: (纸本)9798331515911

The market today is flooded with the counterfeit branded products and there is currently no reliable solution to prevent the widespread flow of duplicates. However, blockchain technology offers a potential solution to stabilize the inflow of these counterfeits. As a decentralized and secure system, blockchain can assign a permanent, unique identity to each product, which can be accessed by anyone but cannot be altered, not even by the owner. This paper proposes the development of a blockchain-based system to assign a unique identity to every product, serving as a tag to distinguish between original and counterfeit items. This identity can also act as an ownership ID, enabling ownership transfer and helping to prevent the illegal trade of stolen or counterfeit products. © 2025 IEEE.

关键词： Blockchain

来源：评论

学校读者我要写书评

暂无评论

Organ Donation and Transplantation Framework using Blockchain

Organ Donation and Transplantation Framework using Blockchai...

引用

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

作者： Shrihari, M.R. Singh, Gaurav Reddy, Keerthi Ajay, N. S J C Institute of Technology Department of Computer Science and Engineering Chikkaballapur India

ISBN: (纸本)9798350359688

The act of organ transplantation is a crucial and life-saving medical procedure, yet it is often faced with obstacles like a limited supply of organs, ineffective management practices, and a lack of openness in the distribution of organs. To tackle these challenges head-on, we put forth an innovative solution: a blockchain-based system for managing organ donation and transplantation. By harnessing the unique features of blockchain, such as decentralisation, immutability, and transparency, our system offers a secure and transparent environment for all participants in the organ donation and transplantation journey. Our system utilises advanced smart contracts and distributed ledger technology to ensure seamless traceability of organ transactions. This not only streamlines the process of matching donors with recipients but also increases transparency and integrity within the organ allocation process. In this paper, we delve into the intricacies of our proposed system, including its architecture, components, and functionalities. We also explore the potential impact of our system on improving efficiency, fairness, and trust in organ donation and transplantation management. These findings demonstrate the immense potential of blockchain technology in transforming the organ transplantation ecosystem, ultimately paving the way for a more equitable and efficient allocation of life-saving organs. © 2024 IEEE.

关键词： Distributed ledger

来源：评论

学校读者我要写书评

暂无评论

Optimization of Path Planning for Automated Vehicles Using SLAM Algorithm 1st

Optimization of Path Planning for Automated Vehicles Using S...

引用

1st International Conference on Data engineering and Machine Intelligence, ICDEMI 2023

作者： Prinslin, L. Selvi, R. Revathi, B. Yuvabharathi, E. Sharmila, L. Department of Computer Science and Engineering Agni College of Technology Chennai India Department of Artificial Intelligence and Data Science Dhanalakshmi College of Engineering Chennai India Department of Information Technology Jeppiaar Institute of Technology Chennai India Department of Computer Science and Engineering Vel Tech Rangarajan Dr.Sagunthala R&D Institute of Science and Technology Chennai India

ISBN: (纸本)9789819776153

SLAM (simultaneous localization and mapping) is a technique for automated vehicles that enables simultaneous map building and vehicle localization. The vehicle is able to map out uncharted terrain owing to SLAM algorithms. Engineers use the map information to carry out tasks such as path planning and obstacle avoidance. An autonomous machine needs the ability to plan the motion of a high-level command. For example, if a task is given to explore a particular area, the bot has to plan accordingly to complete the required task. To achieve this level of accomplishment, the path works on an algorithm that solves SLAM and path planning problems. The machine is designed in such a way that it will work as a grass cutter will complete the task in the given frame. The grass-cutting machine creates its own path in the frame and detects obstacle coming in the path. In this way, the SLAM robot is utilized in the application of agricultural field. In the current work, we have designed a 3-D model of a SLAM robot and its various components like the LIDAR Camera, Jetson Nano, Lithium-Ion Battery, Motor, and Body design machine. This model is capable of performing grass-cutting operations using a cutting blade and collection of waste in a sack attached to the machine. This machine works on automation based on path planning algorithms using ROS, this eliminates human interference. Various kinds of research papers were reviewed to compare different kinds of mechanisms and various components were analyzed for the final model *** check and verify that the author names are correctly recognized and presented in the correct sequence order, which is [given name, middle name/initial, family name] for the author(s). In addition, please verify that the name(s) and respective affiliation(s) shown on the metadata page are valid and make any necessary amendments if ***, have edited the affiliation of the last author. © The Author(s), under exclusive license to Springer Nat

关键词： SLAM robotics

来源：评论

学校读者我要写书评

暂无评论

OPTIMISING FUEL EFFICIENCY OF VEHICLE USING MACHINE LEARNING ALGORITHM 6

OPTIMISING FUEL EFFICIENCY OF VEHICLE USING MACHINE LEARNING...

引用

6th International Conference on Computational Intelligence and Communication Technologies, CCICT 2024

作者： Gupta, Kapil Raj, Aditya Gupta, Keshav Department of Computer Science and Engineering Sharda School of Engineering & Technology Sharda University Greater Noida India

ISBN: (纸本)9798350374629

Because of the negative effects fuel consumption has on the environment and the economy, car owners and operators are quite concerned about it. By anticipating fuel usage and understanding the variables that influence it, machine learning (ML) algorithms can beused to maximize fuel economy. This paper examines the optimization of fuel efficiency through the application of machine learning methods such as Random-Forest, Decision-trees and linear regression. An algorithm to manage the efficiency of fuel used by a vehicle by using multiple machine learning model such as Linear Regression, Decision-Tree, Random-Forest, XG-Boost for predicting the fuel consumption of the vehicles based on thegiven set of input values and predicting the output value which is the fuel consumption in Litre/100 km. For example, this paper used linear regression model, random forest regression model, decision tree regression model, and xg-boost model for predicting the fuel consumption of the Light Motor Vehicles (LMV) with an accuracy of 90.5%,99.97%, 99.96%, and 99.96% respectively. All things considered, ML algorithms might drastically increase fuel economy. To create and test different machine learning models for optimizing fuel efficiency in various car types and operating environments, further study is nonetheless required. ©2024 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Exploring Sleep Paralysis Phenomenon Through Machine Learning: An Analytical Study

Exploring Sleep Paralysis Phenomenon Through Machine Learnin...

引用

2024 International Conference on engineering and Computing, ICECT 2024

作者： Ishaq, Samra Rehman, Attique Ur Ali, Tahir Muhammad Javaid, Sabeen Mir, Azka University of Sialkot Department of Software Engineering Sialkot Pakistan Gulf University for Science and Technology Department of Computer Science Kuwait

ISBN: (纸本)9798350349719

Sleep paralysis is when you're awake but powerless to move. Although the majority of occurrences are linked to extreme terror and some potentially clinically significant sufferings are connected with the case;little is known about it. The present state of research on the connection between sleep paralysis and overall sleep will be examined in this study. Several studies have linked an increased risk of sleep paralysis to low-quality sleep. This could occur in between sleeping and waking. The issue is tackled in the context of sleep paralysis prediction using machine learning. There are multiple attributes in the dataset (label Data). Every exam has a unique set of characteristics and expected results. We carried out an accuracy test of posture recognition by the system to evaluate its validity. Predicting sleep paralysis has been done using machine learning techniques. A comparison of sleeping positions with the findings indicated a correlation between paralysis and poor quality of sleep. Poor sleep quality is correlated with sleep paralysis. In the provided dataset, the Random Forest model predicts sleep paralysis with the highest accuracy 92.3%, K-nearest neighbors' classifier has an accuracy rate of 91.0% 91.9%, and 90.4% using Decision Tree and naïve Bayes. © 2024 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Experimental Evaluation of Remote Sensing–Based Climate Change Prediction Using Enhanced Deep Learning Strategy

引用

Remote Sensing in Earth Systems sciences 2024年第4期7卷 642-656页

作者： Madhavi, Macharapu Kolikipogu, Ramakrishna Prabakar, S. Banerjee, Sudipta Maguluri, Lakshmana Phaneendra Raj, G. Bhupal Balaram, Allam Department of Computer Science and Engineering Velagapudi Ramakrishna Siddhartha Engineering College Andhra Pradesh Vijayawada India Department of Information Technology Chaitanya Bharathi Institute of Technology Hyderabad India School of Commerce and Management Studies Dayananda Sagar University Bangalore India Department of Computer Science and Engineering Symbiosis Institute of Technology Symbiosis International (Deemed University) (SIU) Pune Campus Maharashtra Pune India Department of Computer Science and Engineering Koneru Lakshmaiah Education Foundation AP Vaddeswaram Guntur India School of Agriculture SR University Warangal India Department of Computer Science and Engineering MLR Institute of Technology Hyderabad India

Climate change is one of the most pressing global challenges of our time, with far-reaching impacts on ecosystems, economies, and human societies. Accurate prediction of climate change patterns is crucial for developing effective mitigation and adaptation strategies. Remote sensing data, with its ability to provide comprehensive and continuous observations of the Earth’s surface, plays a vital role in monitoring and predicting these changes. However, the complexity and high dimensionality of remote sensing data present significant challenges for traditional predictive models. In this study, we present an Enhanced Deep Learning Strategy for climate change prediction using remote sensing data, integrating a Cascaded Inception-LGBM model. The proposed model combines the feature extraction capabilities of the Inception module with the predictive power of the Light Gradient Boosting Machine (LGBM). The methodology was evaluated on various climate variables, including temperature, precipitation, and CO₂ levels, achieving an accuracy of 97.22%. Comparative analysis with state-of-the-art models demonstrated the superior performance of our approach, particularly in terms of RMSE, MAE, and R² metrics. Robustness tests further confirmed the model’s generalization capabilities under different data conditions. This study underscores the potential of advanced deep learning techniques in enhancing climate change prediction accuracy and offers insights into the key drivers of climate variability. © The Author(s), under exclusive licence to Springer Nature Switzerland AG 2024.

关键词： Climate change prediction Deep learning Environmental monitoring Feature extraction Inception module Light Gradient Boosting Machine Model accuracy NDVI Remote sensing Spectral indices

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：