检索结果-内蒙古大学图书馆

3rd International Conference on Sentiment Analysis and Deep Learning, ICSADL 2024

作者： Abirami, R. Privadharshini, S. Aroul Canessane, R. Jany Shabu, S.L. Refonaa, J. Gayathri, S. Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350396157

Human sentiments are analyzed based on two prominent technologies, electroencephalography and image processing. Electroencephalography helps in detecting the brains activity by attaching the electrodes to the scalp. The neurons are charged with ions and constantly emit them. When charged ions repel and propagate this repulsion, a brain wave is produced at a unique frequency depending on the state of mind. Image processing helps in determining the characteristics of facial expression using mathematical operations and functions. This includes capturing image or more appropriately 20 signals. The output of image processing yields the characteristics of the image. The combined output of both Electroencephalography device and image processing are mapped together to genuinely analyze the human emotions. © 2024 IEEE.

关键词： Electroencephalography

来源：评论

学校读者我要写书评

暂无评论

Bi-SMOTE: a novel framework for handling imbalanced datasets using machine learning techniques

引用

International Journal of Information technology (Singapore) 2025年第1期17卷 431-445页

作者： Tigga, Onima Pal, Jaya Mustafi, Debjani Department of Computer Science & amp Engineering Birla Institute of Technology Jharkhand Mesra Ranchi India

Working with Imbalance data in real-world problems is not so easy due to the different cardinality of classes. Several machine learning Techniques have been used to overcome this kind of problem for 100% original data for classification. In this research work, the proposed Bi-SMOTE approach on the imbalanced Red wine and Glass datasets using machine learning techniques, Random Forest (RF), K Nearest Neighbor (KNN), Logistic Regression (LR), and Decision Tree (DT) have been used. Moreover, preprocessing steps are done by Binarization and standardization. The accuracy and F1-score are calculated of without SMOTE / with SMOTE / proposed Bi-SMOTE approaches with classifiers RF, KNN, LR, and DT for 95% & 100% of original datasets. Here the Bi-SMOTE approach gives better results up to 12%, and up to 22% for accuracy and up to 29% and up to 28% for F1-score for the Red wine and the Glass dataset respectively. Moreover, mean squared error (MSE) is continuously decreased in these machine learning techniques with original data with SMOTE and Bi-SMOTE. Thus, the proposed approach Bi-SMOTE yields the highest values in all performance measures, including accuracy, and F1-score for 95% data than 100% data. © Bharati Vidyapeeth's institute of computer Applications and Management 2024.

关键词： Accuracy Binarization Class Imbalance Machine learning (ML) SMOTE (Synthetic minority over-sampling technique)

来源：评论

学校读者我要写书评

暂无评论

Tracking A Student Using Face Recognition

Tracking A Student Using Face Recognition

引用

2024 International Conference on Intelligent Systems for Cybersecurity, ISCS 2024

作者： Tejas, V. Harsith Harshitha, S. Yogitha, R. Kalaiarasi, G. Selvi, M. Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350375237

The integration of advanced security technologies, particularly the widespread deployment of mobile cameras equipped with real-time face recognition capabilities, heralds a new era of surveillance capabilities. This paper presents a comprehensive overview of a cutting-edge surveillance system designed to enhance security measures in public and private spaces. Unlike traditional CCTV setups, this system leverages strategically positioned mobile cameras equipped with sophisticated face recognition algorithms such as YOLO, Haar featurebased cascade classifiers, OpenCV, and LBPH (Local Binary Pattern Histograms).Upon detection of a person of interest, the system swiftly matches the face against a pre-existing database, providing instantaneous identification. Moreover, the system concurrently displays the associated location information in real-time, facilitating swift and targeted response *** features of this system include its ability to send immediate notifications containing the individual's name and precise location details to specified recipients, typically via text messages to predetermined numbers. This functionality ensures that relevant authorities are promptly informed, enabling them to address potential concerns or threats *** amalgamating cutting-edge face recognition technology with mobile surveillance cameras, this system not only strengthens security efforts but also streamlines response mechanisms. © 2024 IEEE.

关键词： Face recognition

来源：评论

学校读者我要写书评

暂无评论

Distributed field mapping for mobile sensor teams using a derivative‐free optimisation algorithm

引用

IET Cyber-Systems and Robotics 2024年第2期6卷 20-34页

作者： Tony X.Lin Jia Guo Said Al-Abri Fumin Zhang School of Electrical&Computer Engineering Georgia Institute of TechnologyAtlantaGeorgiaUSA College of Engineering Sultan Qaboos UniversityMuscatOman Department of Electronic&Computer Engineering Hong Kong University of Science and TechnologyHong KongChina

The authors propose a distributed field mapping algorithm that drives a team of robots to explore and learn an unknown scalar field using a Gaussian Process(GP).The authors’strategy arises by balancing exploration objectives between areas of high error and high *** computing high error regions is impossible since the scalar field is unknown,a bio-inspired approach known as Speeding-Up and Slowing-Down is leveraged to track the gradient of the GP *** approach achieves global field-learning convergence and is shown to be resistant to poor hyperparameter tuning of the *** approach is validated in simulations and experiments using 2D wheeled robots and 2D flying mini-ature autonomous blimps.

关键词： environment sensing multi-robot systems

来源：评论

学校读者我要写书评

暂无评论

Network Summarization Through the Lens of Latent Semantic Analysis and Fuzzy Techniques

Network Summarization Through the Lens of Latent Semantic An...

引用

International Conference on Internet of Everything and Quantum Information Processing, IEQIP 2023

作者： Vanathi, M. Lakshmanan, L. Department of Computer Science and Engineering Sathyabama Institute of Science and Technology Chennai India

ISBN: (纸本)9783031619281

Extracting text summarization involves the retention of only the most important sentences in a document. Finding the appropriate ranking order of the phrases in the document according to their relevance is a vital step in extractive text summarization. Singular value decomposition or SVD algorithm based on latent semantic analysis focuses on recognizing the sections in the document which are related in terms of their semantic nature. Fuzzy algorithms involve reasoning of the priority order of the sentences using fuzzy logic unlike the use of discrete values. While significant work has been done for extractive text summarization in English and other foreign languages, there is ample scope for improving the performance of systems when dealing with Marathi text. An analysis of the characteristics of both these techniques is conducted to compare their benefits and shortcomings. The performance of both the algorithms is evaluated on a document dataset using standard performance metrics including the ROUGE metric. Both of these approaches are objectively compared in order to determine their applicability, particularly when dealing with non-English text in general or Marathi in particular. © The Author(s), under exclusive license to Springer Nature Switzerland AG 2024.

关键词： Semantics

来源：评论

学校读者我要写书评

暂无评论

Securing FANET using federated learning through homomorphic matrix factorization

引用

International Journal of Information technology (Singapore) 2025年第1期17卷 17-36页

作者： Banerjee, Aiswaryya Mahato, Ganesh Kumar Chakraborty, Swarnendu Kumar Department of Computer Science and Engineering National Institute of Technology Arunachal Pradesh Jote 791113 India

As Flying Ad Hoc Networks (FANETs) continue to advance, ensuring robust security, privacy, and data reliability remains a significant challenge. This research presents a novel framework known as HE-FSMF-short for Homomorphic Encrypted Federated Secure Matrix Factorization-specifically designed to tackle these challenges. HE-FSMF integrates matrix factorization with federated learning and homomorphic encryption to enhance both security and efficiency in FANET environments. Matrix factorization, commonly used in recommendation systems, is adapted here to address the unique complexities of FANETs. By leveraging detailed feature extraction through the VGG-16 model, HE-FSMF ensures precise and secure data processing even in dynamic and high-mobility settings. The incorporation of homomorphic encryption protects data throughout cloud-based computations, maintaining privacy and integrity without compromising performance. Additionally, HE-FSMF features mechanisms to verify the accuracy and authenticity of results, which is crucial for establishing trust in distributed systems. This framework not only enhances learning efficiency and improves data transmission rates but also provides strong safeguards for sensitive information. HE-FSMF offers a robust solution for advancing FANET capabilities, making it a valuable tool for secure and efficient communication in the increasingly interconnected and rapidly evolving landscape of networked systems. © Bharati Vidyapeeth's institute of computer Applications and Management 2024.

关键词： FANET Federated learning Homomorphic encryption UAV

来源：评论

学校读者我要写书评

暂无评论

Detection Method for Software Defined Network Intrusion 5

Detection Method for Software Defined Network Intrusion

引用

5th International Conference on Intelligent Communication Technologies and Virtual Mobile Networks, ICICV 2024

作者： Jany Shabu, S.L. Nagarjuna, G.K. Satya Ram, Nandigam Kumar Refonaa, J. Joshila Grace, L.K. Sathyabama Institute of Science & Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350385649

There is a great deal of interest in using Intrusion Detection Systems (IDSs) as a key component of system defense at the moment. To secure a network IDS analyzing network traffic from a location on the network or computer system. It is very difficult and time-consuming to distinguish between network traffic that is intrusive and normal. An analyst must examine that much and such a wide range of data. It is necessary to determine the sequence in which intrusions have occurred on the network connection. Current network traffic activity must be reflected by a way to detect network intrusions. Using genetic algorithm and machine learning approaches, a novel approach was developed to uncover intrusion characteristics for intrusion detection systems. The rules are generated using a genetic algorithm for decision trees. Rules can be applied to determine intrusion characteristics, and then implemented into a genetic algorithm for protection. In this way, in addition to identifying the presence of an intrusion, one may stop the incursion by rejecting it. © 2024 IEEE.

关键词： Genetic algorithms

来源：评论

学校读者我要写书评

暂无评论

Planetary Defense Using Machine Learning Early Warning Systems for Hazardous Asteroids

Planetary Defense Using Machine Learning Early Warning Syste...

引用

2024 International Conference on Advances in Data engineering and Intelligent Computing Systems, ADICS 2024

作者： Sandeep, Avala Reddy, Panta Jeevan Perkin, T. Madhu Hindustan Institute Of Technology And Science Department Of Computer Science & Engineering Chennai India

ISBN: (纸本)9798350364828

Within the dynamic field of planetary defence, machine learning has emerged as a key component that is essential to early warning systems that are tasked with forecasting the orbits and trajectories of potentially dangerous asteroids. Through the application of a broad range of sophisticated algorithms, such as logistic regression, XGBoost, decision trees, k-nearest neighbours (KNN), and multi-layer perceptron (MLP), a group of committed scientists are hard at work developing reliable models that will be crucial in classifying asteroids into different orbit classes. These classifications, particularly the potentially dangerous asteroids and Near-Earth Objects (NEOs), provide us with important information that helps us determine risk levels and develop practical mitigation plans. Thus, the combination of astronomy and artificial intelligence has enabled a significant advancement in our ability to examine the data and features of these celestial planets, providing insight into their mysterious motions and any possible risks. With this innovative method, we may both advance our knowledge of the dynamic universe and improve our capacity to protect Earth from the impending threat of asteroidal collisions. In a time when space travel and the secrets of the cosmos entice us with both wonder and danger, this marriage of science and technology serves as a symbol of human ingenuity and our commitment to safeguarding our home planet. © 2024 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

AI-Powered Disease Diagnosis from Medical Image Reports 4

AI-Powered Disease Diagnosis from Medical Image Reports

引用

4th IEEE International Conference on Advance Computing and Innovative Technologies in engineering, ICACITE 2024

作者： Kaviraj, L.R. Rajalakshmi, R. Joshua, S. Sathyabama Institute of Science and Technology Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350360165

The use of data science and technology in healthcare has completely changed how diseases are predicted and diagnosed. Through the integration of two state-of-the-art deep learning architectures - InceptionV3, VGG 19 and sequential CNN within a Flask-based API framework, this research offers a novel method for multi-disease prediction. Kidney stones, kidney cysts, kidney tumors, Lung cancer, and brain tumors are among the disorders that are being targeted. The project progresses through a number of crucial phases. first, a wide-ranging and extensive dataset made up of image data that was rigorously preprocessed. This includes data augmentation, variable normalization, and handling missing data. Modern deep learning architectures, such as Transfer learning models like InceptionV3 and EfficientNet-B7, are chosen and optimized for each disease in order to extract complex patterns from the medical imaging data. intricate connections among high-dimensional data, improving the precision of predictions. These structures are well known for improving prediction accuracy by capturing intricate linkages within high-dimensional data. The performance of the model is evaluated by calculating accuracy and loss after training. © 2024 IEEE.

关键词： Lung cancer

来源：评论

学校读者我要写书评

暂无评论

Exhaustive Analysis and Time Complexity Evaluation of Sorting Algorithms 2

Exhaustive Analysis and Time Complexity Evaluation of Sortin...

引用

2nd International Conference on computer, Communication and Control, IC4 2024

作者： Kalmodiya, Tanay Dixit, Manish Madhav Institute of Technology & Science Department of Computer Science and Engineering Gwalior India

ISBN: (纸本)9798350387933

This paper compares the time complexity of various sorting algorithms for the logic, code and time complexity of each algorithm. The sorting algorithms that this paper discusses are Selection sort, Bubble sort, Insertion sort, Quick sort and Merge sort. The algorithms execution times are calculated using the C++ chrono library. Each algorithms have different formats and their own pros and cons. This paper presents a study of how these different algorithms work and compares them on the basis of their execution time in different input size to reach a conclusion. © 2024 IEEE.

关键词： Computational complexity

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：