检索结果-内蒙古大学图书馆

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

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

Video key concept extraction using Convolution Neural Network 3

Video key concept extraction using Convolution Neural Networ...

引用

3rd IEEE International Conference on AI in Cybersecurity, ICAIC 2024

作者： Sardar, Tanvir H Amin Hazarika, Ruhul Pandey, Bishwajeet Guru Prasad, M.S. Mahmudul Hassan, Sk Dodmane, Radhakrishna Gohel, Hardik Dept. of Computer Science & Engg Bengaluru India Manipal Institute of Technology Department of Information Technology Bengaluru India Astana It University Department of Intelligent System and Cyber Security Kazakhstan Dept. of Computer Science & Engg. Dehradun India VIT-AP School of Computer Science and Engineering India Nmam Institute of Technology Department of Computer Science & Engg. Nitte India University of Houston Department of Cse Victoria United States

ISBN: (纸本)9798350381856

Objectives: This work aims to develop an automated video summarising methodology and timestamping that uses natural language processing (NLP) tools to extract significant video ***: The methodology comprises extracting the audio from the video, splitting it into chunks by the size of the pauses, and transcribing the audio using Google's speech recognition. The transcribed text is tokenised to create a summary, sentence and word frequencies are calculated, and the most relevant sentences are selected. The summary quality is assessed using ROUGE criteria, and the most important keywords are extracted from the transcript using ***: Our proposed method successfully extracts key points from video lectures and creates text summaries. Timestamping these key points provides valuable context and facilitates navigation within the lecture. Our method combines video-to-text conversion and text summarisation with timestamping key concepts, offering a novel approach to video lecture analysis. Existing video analysis methods focus on keyword extraction or summarisation, while our method offers a more comprehensive approach. Our timestamped key points provide a unique feature compared to other methods. Our method enhances existing video reports by (i) providing concise summaries of key concepts and (ii) enabling quick access to specific information through timestamps. (iii) Facilitating information retrieval through a searchable index. Further research directions: (i) Improve the accuracy of the multi-stage processing pipeline. (ii) Develop techniques to handle diverse accents and pronunciations. (iii) Explore applications of the proposed method to other video genres and ***/Improvements: This approach is practical in giving accurate video summaries, saving viewers time and effort when comprehending the main concepts presented in a video. © 2024 IEEE.

关键词： Speech recognition

来源：评论

学校读者我要写书评

暂无评论

Parallelizing Exponential Search Algorithms with MPI and CUDA for High-Performance Computing

Parallelizing Exponential Search Algorithms with MPI and CUD...

引用

Next Generation Communication & Information Processing (INCIP), International Conference on

作者： Vedant Shreeyansh Abhay S. Gad B. Ashwath Rao N. Gopalakrishna Kini Dept. of Computer Science and Engineering Manipal Institute of Technology Manipal Acadmey of Higher Education Manipal India

ISBN: (数字)9798331528140

ISBN: (纸本)9798331528157

Exponential search is an algorithm for searching unbounded taken care of lists. The exponential seek approach can be used to find the vicinity of a specified value in a taken care of array. Parallel index lookups in Exponential seek can enhance their performance, specifically for massive lists. This work provides an example of the exponential seek set of rules, which employ CUDA to enforce GPU parallelism and MPI to achieve parallel memories. We've mentioned a method to evaluate exponential studies and exhibit development in performance. The effects show that we can acquire relatively quicker outcomes than sequential techniques, specifically for big arrays.

关键词： Technological innovation Search methods Message passing High performance computing Graphics processing units Information processing Parallel processing data processing Computational efficiency Indexes

来源：评论

学校读者我要写书评

暂无评论

Deep Analysis for Speech Emotion Recognization 2

Deep Analysis for Speech Emotion Recognization

引用

2nd International Conference on computer science, Engineering and applications, ICCSEA 2022

作者： Bhattacharya, Sudipta Borah, Samarjeet Mishra, Brojo Kishor Das, Nabanita India Sikkim Manipal Institute of Technology Sikkim Manipal University Dept. of Computer Applications Sikkim India Maulana Abul Kalam Azad University of Technology Bengal Institute of Technology India

ISBN: (数字)9781665458344

ISBN: (纸本)9781665458344

Emotions play a vital part in human interactions and are important determinants of user happiness and consumer sentiment. The creation of human-computer interaction (HCI) systems depends on speech emotion recognition (SER) modules. Systems for analysing and classifying speech signals in order to identify the emotions they contain are known as speech emotion recognition (SER) systems. SER is a well-established and fast developing branch of signal processing. More data will be available to learn from as speech emotion detection systems become more popular, helping them to improve their performance. This study also includes a discussion of certain common machine learning approaches, such as ensemble methods, deep learning methods, and classifier enhancement methods. Attention-based deep neural networks (DNNs) are also highlighted in this paper, which is getting a lot of attention in this domain. The findings of this study show that this field of study is being investigated steadily. The scientific community in this area could benefit from this analysis's inspiration and motivation. © 2022 IEEE.

关键词： Emotion Recognition

来源：评论

学校读者我要写书评

暂无评论

Simplified Micropayment Mechanism to Eliminate the Risk of Double Payment in E-Commerce

Simplified Micropayment Mechanism to Eliminate the Risk of D...

引用

2023 International Conference on Advances in Intelligent Computing and applications, AICAPS 2023

作者： Chahar, Narendra Kumar Singh, Krishan Pal Hussain, Muzzammil Central University of Rajasthan Dept. of Data Science and Analytics Ajmer India Malaviya National Institute of Technology Dept. of Computer Science and Engineering Jaipur India Central University of Rajasthan Dept. of Computer Science and Engineering Ajmer India

ISBN: (纸本)9798350333817

In recent years, the emergence of the Internet and E-commerce has steered significant growth in digital transactions. Businesses today need mobile wallets, credit and debit cards, and e-cash to digitize payments. Digital payment systems are in transition and promise amazing advancements, but they also pose many risks and as the number of online transactions is increasing tremendously, we need a security system that follows all security norms. In this paper, we study digital transaction systems and evaluate various components of E-commerce plat-forms to address the security of these services. We evaluate the attributes that affect the security of digital payment processes and identify several barriers that hinder their performance to propose a simplified payment mechanism for micro-payments that eliminates the double payment problem. © 2023 IEEE.

关键词： Online systems

来源：评论

学校读者我要写书评

暂无评论

Predictive Analysis of Diabetes Mellitus Using Decision Tree Approach 2

Predictive Analysis of Diabetes Mellitus Using Decision Tree...

引用

2nd Asian Conference on Innovation in technology, ASIANCON 2022

作者： Thotad, Puneeth Bharamagoudar, Geeta R. Anami, Basavaraj S. Kle Institute of Technology Dept. of Master of Computer Applications Hubballi India Kle Institute of Technology Dept. of Computer Science & Engineering Hubballi India

ISBN: (数字)9781665468510

ISBN: (纸本)9781665468510

Diabetes Mellitus is one of the Non-Communicable Disease. It is characterized by hyperglycemia. It may be reason for numerous health difficulties. According to the statistics in coming years, in 2030, worldwide it reaches up to 643 million counts of diabetic patients. The various factors such as Bad Diet, High Blood Pressure, Obesity, Age, Lack of Exercise etc. can led to Diabetes Mellitus. The various diseases like nerve damage, heart problem, eye problem, kidney disease, stroke in many people caused by high risk of Diabetes Mellitus. Machine Learning plays vital role in healthcare sectors. Using various Machine Learning techniques, a study can be done on large datasets and discover unseen facts, unseen patterns to realize awareness from the data and predict results consequently. In this work, the PIMA Indian Diabetes dataset is considered for Predictive Analysis. The Decision Tree algorithm, namely ID3 (Iterative Dichotomize 3) is used for a predictive analysis. The major phases include preprocessing, feature extraction, classification, and prediction. The classification accuracies of 79.76% and 76.3% are obtained for balanced and unbalanced datasets respectively. The maximum specificity and sensitivity obtained are 79.75% and 79.78% respectively. The ROC curve gives 79.57% overall classification accuracy. The work assists physicians as a second opinion. It can help various health industries to predict the diabetes disease in a better way. © 2022 IEEE.

关键词： Decision trees

来源：评论

学校读者我要写书评

暂无评论

Mental Health Tracker Using Machine Learning Approaches 4

Mental Health Tracker Using Machine Learning Approaches

引用

4th IEEE Global Conference for Advancement in technology, GCAT 2023

作者： Thotad, Puneeth N. Kallur, Shanta Mundaragi, Laxmi Kadam, Swati H. Dept. of Master of Computer Applications K.L.E. Institute of Technology Hubballi580 027 India Dept. of Computer Science and Engineering K.L.E. Institute of Technology Hubballi580 027 India

ISBN: (纸本)9798350305258

Mental illness is a common condition in the 21st century. Despite the significant number of people who experience mental illness, many continue to experience stress without comprehending its damaging effects on their brain. Python and machine learning tools are adopted to create the mental health tracker system. According to the experimentation, the work focuses on developing a psychological well-being tracker. The prediction uses various models such as logistic regression, random forest, decision tree, and k-nearest neighbor. In the proposed system, the patient must answer the questions to predict their mental illness condition. Based on the responses given by the patient, the system will predict whether they need treatment or not. The system will attempt to gain an understanding of a user's mental state, determine whether they are suffering, and then suggest steps they can take to improve their mental health situation. Mental health prediction might benefit psychological departments looking to enhance their counseling and diagnosis abilities. The model was developed by collecting the question-answer set as options related to mental health by consulting specialized doctors in the hospital. The model is trained using different ML algorithms, finding their accuracy and predicting the results. The analysis was made by considering the raw data and normalized data. Models performance was improved with normalization with the following accuracies. 71.4%, 73.5%, 80.6%, and 81.2% accuracies are obtained for Logistic regression, K-Nearest Neighbor, Decision Tree, and Random Forest, respectively. © 2023 IEEE.

关键词： Decision Tree Digital Mental Health K-Nearest Neighbor Logistic Regression Machine Learning Random Forests

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

Etiseg-Net: Edge-Aware Self Attention to Enhance Tissue Segmentation in Histopathological Images

SSRN

引用

SSRN 2023年

作者： Rashmi, R. Girisha, S. Manipal India Department of Data Science and Computer Applications Manipal Institute of Technology Manipal Academy of Higher Education Manipal India

Digital pathology employing Whole Slide Images (WSIs) plays a pivotal role in cancer detection. Nevertheless, the manual examination of WSIs for the identification of various tissue regions presents formidable challenges due to its labor-intensive nature and subjective interpretation. Convolutional Neural Network (CNN) based semantic segmentation algorithms have emerged as valuable tools for assisting in this task by automating ROI delineation. The incorporation of attention modules and carefully designed loss functions has shown promise in further augmenting the performance of these algorithms. However, there exists a notable gap in research regarding the utilization of attention modules specifically for tissue segmentation, thereby constraining our comprehension and application of these modules in this *** study introduces ETiSeg-Net (Edge-aware self attention to enhance Tissue Segmentation), a CNN-based semantic segmentation model that uses a novel edge-based attention module to achieve effective delineation of class boundaries. In addition, an innovative iterative training strategy is devised to efficiently optimize the model parameters. The study also conducts a comprehensive investigation into the impact of attention modules and loss functions on the efficacy of semantic segmentation models. Qualitative and quantitative evaluations of these semantic segmentation models are conducted using publicly available datasets. The findings underscore the potential of attention modules in enhancing the accuracy and effectiveness of tissue semantic segmentation. © 2023, The Authors. All rights reserved.

关键词： Semantic Segmentation

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：