检索结果-内蒙古大学图书馆

6th International Conference on Contemporary Computing and Informatics, IC3I 2023

作者： RukumaniKhandhan, C. Vijayakumar, P. Sri Sabari, C. Arun, G. Chandrasekaran, N. Rohith Bhat, C. Kongu Engineering College Department of Computer Technology - PG Erode Perundurai India Kongu Engineering College Department of Master of Computer Applications Tamil Nadu Perundurai India Kongu Engineering College Department of Computer Technology - PG Tamil Nadu Perundurai India Erode Sengunthar Engineering College Department of Artificial Intelligence and Data Science Thuduppathi India PSNA College of Engineering and Technology Department of Electrical and Electronics Engineering Dindigul India Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Department of Computer Science and Engineering Chennai India

ISBN: (纸本)9798350304480

Disabled people are of different kinds like physically challenged people, mentally challenged etc. To help the people who cannot convey their thoughts and who cannot hear others thoughts, sign language is being used to communicate with them. Sign language is something that is used to communicate through body movements mainly through hands and *** Sign Language(ASL) is an authorized sign language that is taught and used widely. ASL is difficult to teach and learn for them because it is completely new and they have no knowledge about it. In this research paper the ASL is recognized and converted into text through data mining techniques. The study uses a dataset of ASL alphabet images and applies various data mining techniques, including feature selection, classification, and clustering. The features extracted from the images include shape, size, color, and texture. The use of neural networks, decision trees, and support vector machines speeds up the data categorization process. Techniques such as k-means clustering and hierarchical grouping are used to facilitate entity grouping. The results show that the best performance is achieved using a combination of feature selection and classification techniques. The decision tree algorithm with the selected features achieves an accuracy of 96.5% on the test dataset. The system can accurately recognize all the ASL alphabets and convert them into text or speech. The system developed can be used to improve communication between deaf and hearing individuals and can be extended to recognize other ASL gestures and phrases. Future research can focus on real-time detection and recognition of ASL gestures using data mining techniques. CNN algorithm is used to recognize the image based on the images collected. The accuracy rate gets low and the detection is inaccurate. Therefore, VGG16 algorithm is used to recognize the images and it is unique in convolutional models. © 2023 IEEE.

关键词： ASL CNN Gestures VGG16

来源：评论

学校读者我要写书评

暂无评论

Siamese Network Based Anomaly Detection Framework for Robust Federated Learning

Siamese Network Based Anomaly Detection Framework for Robust...

引用

Intelligent Technologies (CONIT), International Conference on

作者： Karthik Shenoy K Manohara M. M. Pai Radhika M. Pai Department of Information and Communication Technology Manipal Institute of Technology Manipal India Department of Data Science and Computer Applications Manipal Institute of Technology Manipal India

Federated learning is a decentralized approach to machine learning that has increased in popularity in recent years. It enables several participants to train a common model without revealing their data. This strategy is, however, susceptible to attacks from malicious clients who can launch targeted model poisoning attacks and reduce learning performance by delivering false model updates to the server. It is necessary to identify and eliminate such fraudulent updates and the attackers behind them to preserve the robustness and security of the shared model. In this paper, a novel Siamese network-based architecture for robust federated learning is proposed. which can identify and eliminate harmful updates. Our method is assessed and compared with other approaches for adversarial detection in image classification tasks in a federated setting, using a CNN model. Experimental findings demonstrate that the system offers reliable federated learning that is resistant to both targeted model poisoning and untargeted Byzantine attacks. Overall, the study advances the development of secure federated learning systems, by suggesting a novel method for identifying and deleting fraudulent updates in federated learning,

关键词：

来源：评论

学校读者我要写书评

暂无评论

A comparative Analysis of ensemble methods and their efficiency in the classification of 'HIT AND RUN' cases in an imbalanced dataset (Traffic Crashes) with and without using "Synthetic minority oversampling technique" 33

A comparative Analysis of ensemble methods and their efficie...

引用

33rd International Conference on computer Theory and applications, ICCTA 2023

作者： Manjula Shenoy, K. Prabhu, R Srinivas Manipal Academy of Higher Education Manipal Institute of Technology Information and Communication Technology Department Manipal576104 India Manipal Academy of Higher Education Manipal Institute of Technology Data Science and Computer Applications Department Manipal576104 India

ISBN: (纸本)9798350309577

In some cases of developing a predictive model for a classification problem, the distribution of classes is skewed, meaning a majority of the training samples belong to a single class and a very small number of samples belong to a minority class. If Machine Learning techniques are applied directly to such data sets, it may result in a model which either ignores the minority class as a whole or gives less importance to the samples belonging to the minority class. Such datasets are often called imbalanced datasets. There are multiple ways to deal with these problems some include Random Over Sampling, Random Under Sampling, Threshold value tuning, one class classification to find the outlier, etc. One such technique is called the "Synthetic minority oversampling technique (SMOTE)". In this paper we are going to analyze the efficiency of ensemble methods for the classification of imbalanced datasets with and without using SMOTE. The dataset used for this purpose is an open-source Traffic crashes dataset available on the Chicago data portal. The target variable for our study is the "HIT-AND-RUN-I"column available in the dataset. This is a dichotomous variable that has 2 valid values. "Y"for the cases that are of positive outcomes as in "HIT-AND-RUN-I"= yes. "N"for the cases that are of negative outcomes as in "HIT-AND-RUN-I"= No. © 2023 IEEE.

关键词： Labeled data

来源：评论

学校读者我要写书评

暂无评论

Machine Learning for Real-Time Language Translation: A Server-Side Approach to Overcome Cross-Cultural Communication Challenges

Machine Learning for Real-Time Language Translation: A Serve...

引用

Soft Computing for Security applications (ICSCSA), International Conference on

作者： S. Elango Mohanaprakash T A D. Siva Gowtham A Sasikumar A N Sunitha T Department of Computer Science and Engineering SOET CMR University Bengaluru Department of Computer Science and Applications SRM Institute of Science and Technology Chennai Department of CSE (Cyber Security) Madanapalle Institute of Technology & Science AP India Department of Computer Science and Engineering Panimalar Engineering College Chennai India Department of Artificial Intelligence & Data Science Saveetha Engineering College Chennai India

ISBN: (数字)9798331515720

ISBN: (纸本)9798331515737

The evolution of human civilization has been intrinsically linked to advancements in technology, leading to the development of multiple languages as mediums of communication. However, this linguistic diversity poses significant challenges in cross-cultural communication. Despite numerous efforts and achieving near state-of-the-art results in language translation, a universal solution remains elusive. This research study proposes an advanced approach to machine translation by utilizing server-side machine learning to enable seamless communication across various languages. By sending GET or POST requests through JQuery, users can efficiently translate text. The process is structured into three key steps: speech recognition (conversion of spoken words to text), translation using machine learning algorithms, and speech synthesis (conversion of translated text to audio). This approach aims to enhance real-time translation capabilities, offering a more effective and user-friendly solution for overcoming language barriers.

关键词： Translation Machine learning algorithms Speech recognition Machine learning Speech enhancement Cross-cultural communication Real-time systems Speech synthesis Machine translation Security

来源：评论

学校读者我要写书评

暂无评论

An Optimal Power System Multi-objective Environmental-Economic Planning Based on Moth-Flame Optimization 1

引用

18th International Conference on Intelligent Information Hiding and Multimedia Signal Processing, IIH-MSP 2022

作者： Chu, Shu-Chuan Nguyen, Trong-The Nguyen, Vinh-Tiep Nguyen, Trinh-Dong Dao, Thi-Kien College of Computer Science and Engineering Shandong University of Science and Technology Qingdao266590 China University of Information Technology Ho Chi Minh City700000 Viet Nam Vietnam National University Ho Chi Minh City700000 Viet Nam Fujian Provincial Key Laboratory of Big Data Mining and Applications Fujian University of Technology Fuzhou350118 China

ISBN: (数字)9789819901050

ISBN: (纸本)9789819901043

A power system’s optimization under economic planning concerns scheduling sectors as a challenging reality task with its characteristics with non-convex, high-dimensional, nonlinear problems. This study introduces an optimal power system environmental and economic scheduling based on a multi-moth-flame optimizer (MMFO). A multi-objective programming mathematical model uses the Pareto optimal frontier to obtain the Pareto non-inferiority optimal solution, generate the optimal configuration scheme, and search for the optimal global solution in the feasible region. Calculation results of a power system with IEEE test case of 15 and 40 generator sets demonstrate the high convergence and strong adaptability of the algorithm suggested in addressing the environmental-economic dispatch of the power system. © 2023, The Author(s), under exclusive license to Springer Nature Singapore Pte Ltd.

关键词： Multiobjective optimization

来源：评论

学校读者我要写书评

暂无评论

Anomaly detection using Federated Learning: A Performance Based Parameter Aggregation Approach

Anomaly detection using Federated Learning: A Performance Ba...

引用

Intelligent Technologies (CONIT), International Conference on

作者： Pushkar Bhat Manohara Pai M M Radhika M Pai Department of Information and Communication Technology Manipal Institute of Technology Manipal India Department of Data Science and Computer Applications Manipal Institute of Technology Manipal India

Anomaly detection is a significant challenge that exists in multiple industries, including healthcare, finance, and manufacturing. Machine Learning techniques are extensively being used to solve these problems. However, data privacy concerns and regulations are making acquiring the necessary data for model training increasingly challenging, particularly in sensitive sectors. Federated learning has emerged as a promising solution, allowing local models to be trained on edge devices using local datasets and model parameters to be shared with a central server for aggregation. This allows the models to reap the benefits of the distributed data without actually sharing any data. However, the current aggregation method used in federated learning is susceptible to models trained on bad data, which can impact the accuracy and reliability of the resulting model. To address this issue, the study proposes a new filtered aggregation algorithm that greatly mitigates the effect of models trained on bad data. The proposed algorithm accounts for models that cannot detect anomalous patterns and gives them much less representation in the final model, resulting in improved accuracy and reliability.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Resting-State Network Transitions in Temporal Lobe Epilepsy: Insights from MEG Based Dynamic Functional Connectivity

引用

IEEE Transactions on Neural Systems and Rehabilitation Engineering 2025年 33卷 2286-2298页

作者： Suhas, M.V. Sinha, Sanjib Kotegar, Karunakar Ravindranadh Chowdary, M. Raghavendra, K. Asranna, Ajay Viswanathan, L.G. Mariyappa, N. Anitha, H. Manipal Academy of Higher Education Manipal Institute of Technology Department of Electronics and Communication Engineering Karnataka Manipal 576104 India National Institute of Mental Health and Neurosciences (NIMHANS) Department of Neurology Karnataka Bangalore 560029 India Manipal Academy of Higher Education Manipal Institute of Technology Department of Data Science and Computer Applications Karnataka Manipal 576104 India National Institute of Mental Health and Neurosciences (NIMHANS) MEG Research Centre Department of Neurology Karnataka Bangalore 560029 India Manipal Academy of Higher Education Manipal Institute of Technology Department of Computer Science and Engineering Karnataka Manipal 576104 India

Temporal Lobe Epilepsy (TLE), a common form of focal epilepsy, is associated with recurrent seizures originating in the temporal lobe, often leading to cognitive and psychological impairments. This study explores dynamic functional connectivity (dFC) patterns in TLE patients compared to Healthy Controls (HC) using resting-state Magnetoencephalography (MEG) data. dFC, which captures the temporal variability of brain networks, was analyzed across eight frequency bands (delta, theta, alpha, beta, low gamma, mid gamma, high gamma, and broadband) in 21 TLE patients and 21 HC. Nine dFC metrics, including state transitions, connectivity strength, network stability, and overall network movement, were derived using amplitude envelope correlations between 68 brain regions mapped to resting-state networks. Results reveal heightened variability in beta band transitions and increased entropy in delta band transitions, indicating unstable and diverse network configurations. TLE patients showed reduced dwell time in visual networks and increased dwell time in the dorsal attention network, suggesting compensatory mechanisms. Reduced connectivity in alpha and beta bands, coupled with increased variability in theta and low gamma bands, highlights widespread network instability. These findings emphasize dFC metrics as potential biomarkers for TLE, offering insights for targeted therapeutic interventions to stabilize brain dynamics. © 2001-2011 IEEE.

关键词： Dynamic functional connectivity magnetoencephalography resting state network temporal lobe epilepsy

来源：评论

学校读者我要写书评

暂无评论

data Analytics for Core Temperature Estimation in Battery Management System for Electric and Hybrid Vehicles 5

Data Analytics for Core Temperature Estimation in Battery Ma...

引用

5th International Conference on Energy, Power, and Environment, ICEPE 2023

作者： Chhetri, Ahilya Surya, Sumukh Mohan Krishna, S. Rao, Vidya Cactus Communications Engineering and Technology Mumbai India Bosch Global Software Technologies Pvt. Limited Bengaluru India Aced Alliance University Department of Electrical and Electronics Engineering Bengaluru India Manipal Institute of Technology Manipal Academy of Higher Education Department of Data Science and Computer Applications Manipal India

ISBN: (纸本)9798350313123

Compared to conventional means of transport thatuse fossil fuels, electric vehicles are known to reduce pollution levels as they take power from renewable sources of energy stored in energy storage devices like batteries and fuel cells. Core temperature estimation of batteriesis extremely important inbattery management systems for preventing thermal runaway and ensuring safe operation. In this study, core temperature is estimated using a Kalman filter for two different battery chemistries viz;lithium polymer and lithium iron phosphate using a second-order thermal model. Further, a linear regression model is applied to verify the prediction over the trained and tested dataset. The lithium iron phosphate prediction curvehad a fit of approximately 82-83%, whilelithium polymerhad a fit of 72-82% during the charging and discharging of OCV-SOC variation. © 2023 IEEE.

关键词： Simulink

来源：评论

学校读者我要写书评

暂无评论

Immersive Viewing of Dento-facial Medical data in Virtual Reality 14

Immersive Viewing of Dento-facial Medical Data in Virtual Re...

引用

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

作者： Bhat, Shreenidhi H. Hareesh, K.S. Kamath, Abhay T. Kudva, Adarsh Manipal Institute of Technology Manipal Academy of Higher Education Dept. Data Science and Computer Applications Manipal India Consultant-Oral and Maxillofacial Surgery Kmc Hospitals Mangaluru India Manipal College of Dental Sciences Manipal Academy of Higher Education Dept. Oral and Maxillofacial Surgery Manipal India

ISBN: (纸本)9798350335095

Virtual reality (VR) requires dynamic and responsive rendering technologies to offer an immersive user experience. Failing, users may experience motion sickness due to motion lag in virtual space. This work aims to create a framework with a higher framerate to decrease the motion sickness in turn increasing the virtual world viewing quality. Essentially, an interactive environment is developed between existing volume rendering engines OpenGL and GPU-based ray casting techniques for rendering the dentofacial data volume. The developed visualization methods are incorporated into Head Mount Device(HMD) to offer immersive effects. The performance of the VR rendering application measured in terms of framerate was observed to be 125 frames per second, significantly higher than the current HMDs framerate. In addition, the adaptation of rendered image quality is activated by adjusting the sampling distance and jitter to complete the rendering process in the allotted time. The achieved result is expected to offer satisfactory comfort to the viewer with reduced motion sickness, particularly in pre-surgical planning for dentofacial surgery. © 2023 IEEE.

关键词： Virtual reality

来源：评论

学校读者我要写书评

暂无评论

A Study on AI applications for Orthodontics and Malocclusion Detection Approaches

A Study on AI Applications for Orthodontics and Malocclusion...

引用

IEEE Distributed Computing, VLSI, Electrical Circuits and Robotics (DISCOVER)

作者： Ankitha A Nayak Venugopala P S Ashwini B Padmashree G Department of Computer Science and Engineering Nitte NITTE (Deemed to be University) NMAM Institute of Technology Udupi India Dept. of Artificial Intelligence and Data Science NMAM Institute of Technology NITTE (Deemed to be University) Udupi India Department of Computer Science and Engineering NMAM Institute of Technology NITTE (Deemed to be University) Udupi India Department of Data Science and Computer Applications Manipal Academy of Higher Education Manipal Institute of Technology Manipal India

ISBN: (数字)9798350350593

ISBN: (纸本)9798350350609

Orthodontics is a dental specialty focused on treating, diagnosing, and preventing malocclusion and other dental irregularities. In a complex human digestive system, the anatomy of teeth has a significant role. Moreover, maintaining a healthy dental anatomy is essential to ensure a vibrant lifestyle. Orthodontics plays a vital role in the health of teeth structure by providing solutions for crooked teeth, tooth decay, periodontal disease, TMJ syndrome, neck shoulder pain, headaches, and pleasing facial appearance. This paper showcases a comprehensive review of the background and evolution of the orthodontics area through the years, emphasizing more methodologies for fixing malocclusion. The field of orthodontics needs significant manual intervention throughout the entire process, starting from the initial detection of the problem to the final stage of rectifying the fault. This paper presents a fair comparative visualization of manual work cut down with technical advancements in orthodontics and malocclusion detection techniques, spanning from the Bio-mechanical to Artificial Intelligent era. For a better descriptive analysis, we have analyzed the various existing works in orthodontics and malocclusion detection connecting to a set of well-defined research questions. The study of available algorithms, technologies data sets, and gaps for orthodontics and malocclusion detection technique is outlined concerning observed results in the survey.

关键词： Surveys Reviews Pain Teeth Manuals Very large scale integration Dentistry Artificial intelligence Robots Periodic structures

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：