检索结果-内蒙古大学图书馆

Intelligent Algorithms for Computational Intelligence Systems (IACIS), International Conference on

作者： A. Beatrice Dorothy B. Madhavidevi Balusamy Nachiappan G. Manikandan Pramod Kumar Patjoshi M. Sindhuja Department of Data Science St. Joseph’s College (Autonomous) Tiruchirappalli India Department of Computer Science and Engineerin Institute of Aeronautical Engineering Hyderabad India Technical Lead Prologis Denver CO United States Department of ECE Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai India School of Management Centurion University of Technology and Management Bhubaneswar India Department of Computer Science and Engineering St. Martins Engineering College Secunderabad India

ISBN: (数字)9798350360660

ISBN: (纸本)9798350360677

This research work tackles flaws in typical cloud threat intelligence systems, which often depend on static rules and signature-based detection approaches that are unable to react to changing cyber threats. These constraints highlight the need for a more proactive approach, leading the development of a novel system that incorporates AI-driven approaches. The work goes beyond static rule-based models and proposes an AI-driven method to addressing inadequacies in current systems. Combining anomaly detection and machine learning (ML) techniques enables the system to adapt to changing security threats. The first phases involve gathering and analyzing data from numerous cloud sources to improve the system's capacity to spot problems. Supervised learning with Random Forest classifies known hazards, while unsupervised learning with Isolation Forest detects new abnormalities. Real-time monitoring and response considerably improve the system's threat detection rates (95%), anomaly detection (93%), and other performance indicators. The proposed system surpasses the existing system by 95% accuracy, 93% precision, and 96% recall. These findings demonstrate how effectively the framework enables cloud safety and its capacity to enhance overall digital safety and proactively prevent assaults.

关键词： Measurement Privacy Supervised learning Real-time systems Threat assessment Protection Anomaly detection Unsupervised learning Streams Random forests

来源：评论

学校读者我要写书评

暂无评论

data-Driven Computational Algorithms for Predicting Electricity Consumption Missing Values: A Comparative Study

Data-Driven Computational Algorithms for Predicting Electric...

引用

Australasian Universities Power engineering Conference, AUPEC

作者： Bavly Hanna Guandong Xu Xianzhi Wang Jahangir Hossain Department of Computer Science University of Technology Sydney Sydney Australia School of Electrical and Data Engineering University of Technology Sydney Sydney Australia

data availability is a significant issue and barrier for modeling and analyzing low voltage networks. This paper develops, implements, and compares several prediction algorithms for finding missing values in energy usage for commercial consumers. Four predictive machine learning models, such as random forest regression, linear regression, multi-layer perceptron, and decision trees, are utilized in this paper. Four commercial users from a regional city in Australia are selected as a dataset based on 30-minute intervals. Firstly, the obtained data is analyzed and pre-processed and then utilized for model training and testing. RMSE and MAE measures are used to compare the effectiveness of each machine learning model. This paper concludes that the multi-layer perceptron model provides better performance than that of random forest, decision tree, and linear regression. The RMSE and MAE of MLP model are 4.7472 and 4.2103, respectively, when using individual users as a training set.

关键词：

来源：评论

学校读者我要写书评

暂无评论

MacST: Multi-Accent Speech Synthesis via Text Transliteration for Accent Conversion

MacST: Multi-Accent Speech Synthesis via Text Transliteratio...

引用

International Conference on Acoustics, Speech, and Signal Processing (ICASSP)

作者： Sho Inoue Shuai Wang Wanxing Wang Pengcheng Zhu Mengxiao Bi Haizhou Li School of Data Science The Chinese University of Hong Kong Shenzhen (CUHK-Shenzhen) Shenzhen China Shenzhen Research Institute of Big Data The Chinese University of Hong Kong Shenzhen (CUHK-Shenzhen) Shenzhen China Fuxi AI Lab NetEase Inc. Hangzhou China Department of Electrical and Computer Engineering National University of Singapore Singapore

ISBN: (数字)9798350368741

ISBN: (纸本)9798350368758

In accented voice conversion or accent conversion, we seek to convert the accent in speech from one another while preserving speaker identity and semantic content. In this study, we formulate a novel method for creating multi-accented speech samples, thus pairs of accented speech samples by the same speaker, through text transliteration for training accent conversion systems. We begin by generating transliterated text with Large Language Models (LLMs), which is then fed into multilingual TTS models to synthesize accented English speech. As a reference system, we built a sequence-to-sequence model on the synthetic parallel corpus for accent conversion. We validated the proposed method for both native and non-native English speakers. Subjective and objective evaluations further validate our dataset’s effectiveness in accent conversion studies.

关键词： Training Large language models Semantics Signal processing Acoustics Text to speech Multilingual

来源：评论

学校读者我要写书评

暂无评论

TransformerFusionNet: A Real-Time Multimodal Framework for ICU Heart Failure Mortality Prediction Using Big data Streaming

TransformerFusionNet: A Real-Time Multimodal Framework for I...

引用

2024 International Conference on computer and Applications, ICCA 2024

作者： Saleh, Hager McCann, Michael El-Sappagh, Shaker Breslin, John G. Hurghada University Faculty of Computers and Artificial Intelligence Hurghada Egypt University of Galway Insight Research Ireland Centre for Data Analytics GalwayH91 TK33 Ireland Atlantic Technological University Letterkenny Ireland Atlantic Technological University Department of Computing Letterkenny Ireland Galala University Faculty of Computer Science and Engineering Suez Egypt Benha University Faculty of Computers and Artificial Intelligence Benha Egypt School of Engineering University of Galway GalwayH91 TK33 Ireland

ISBN: (纸本)9798350367560

This paper presents a real-time multimodal frame-work to enhance ICU mortality prediction for heart disease patients by integrating structured data, clinical notes, and big data streaming platforms. The proposed framework comprises two components: an offline multimodal model and a real-time pipeline. In the offline component, we proposed the Transformer-FusionNet model leverages BioBERT-Transformer for clinical notes and a Recurrent Neural Network (RNN) for structured data. The model integrates outputs through a concatenation layer to make predictions and is rigorously evaluated using the MIMIC-III dataset. It demonstrates superior performance across evaluation metrics and achieves an accuracy of 91.720%, precision of 91.85%, recall of 91.720%, and F1-score of 91.693%, outperforming other single and multimodal models. The real-time pipeline component incorporates Apache Spark and Apache Kafka for ingesting, preprocessing, and streaming structured data and clinical notes. This integration enables real-time mor-tality prediction with TransformerFusionNet, addressing critical gaps in the utilization of clinical notes in healthcare analytics. The framework significantly advances multimodal deep learning applications in healthcare by combining state-of-the-art models with scalable streaming technologies, offering a practical solution for improving clinical decision support systems and patient outcomes in real-time, especially in intensive care unit settings. © 2024 IEEE.

关键词： Recurrent neural networks

来源：评论

学校读者我要写书评

暂无评论

Protecting Deep Neural Networks in Cloud-Based Environments Towards Backdoor Assaults

Protecting Deep Neural Networks in Cloud-Based Environments ...

引用

Sustainable Computing and Integrated Communication in Changing Landscape of AI (ICSCAI), International Conference on

作者： Manjunatha R Naresh Kaushik Yaduvir Singh Department of Data analytics and Mathematical Sciences School of Sciences JAIN (Deemed to be University) Bangalore Karnataka India Department of uGDX ATLAS SkillTech University Mumbai Maharashtra India Department of Computer Science and Engineering (AI) Noida Institute of Engineering & Technology Greater Noida Uttar Pradesh India

ISBN: (数字)9798350355338

ISBN: (纸本)9798350355345

When it comes to training deep neural networks, especially those with complicated architectures, the accompanying financial and temporal costs often force resource-constrained customers to outsource their learning process via cloud service providers. But there's a risk that dishonest cloud providers may include backdoors and jeopardise the security of the overall model. Users may examine the model closely and utilise state-of-the-art defence techniques to reduce this danger. The goal of this research is to create a robust backdoor attack technique called RobNet that can circumvent current defences from the perspective of malevolent cloud providers. Furthermore, multi-trigger backdoor assaults are introduced, which enlarge the attack area by misclassifying inputs with different triggers into target labels that are either identical or dissimilar. RobNet is tested against four popular defence techniques (Pruning, NeuralCleanse, Strip, and ABS) using datasets from MNIST, GTSRB, and CIFAR-10. RobNet has a higher attack success rate and more robustness against possible defensive measures when compared to two state-of-the-art baselines: Hidden Backdoors and BadNets.

关键词： Training Technological innovation Strips Neurons Artificial neural networks Robustness Service-oriented architecture Security Biological neural networks Resilience

来源：评论

学校读者我要写书评

暂无评论

data Processing Technology for Network Abnormal Traffic Detection

引用

Procedia computer Science 2024年 243卷 610-618页

作者： Kun Wang Yu Fu Xueyuan Duan Jianqiao Xu Taotao Liu Department of Information Security Naval University of Engineering Wuhan 430033 China School of Mathematics and Information Engineering Xinyang Vocational and Technical College Xinyang 464000 China College of Computer and Information Technology Xinyang Normal University Xinyang 464000 China Henan Key Laboratory of Analysis and Applications of Education Big Data Xinyang Normal University Xinyang 464000 China

At present, the threats to network security are also increasing, among which abnormal traffic detection is the key link to ensure network security. Traditional detection methods based on signature or threshold are often difficult to adapt to the increasingly complex network environment and new attack methods. Therefore, this paper optimizes and improves the data processing technology, proposes a network ATD method based on particle swarm optimization (PSO) algorithm, and explores in detail the traffic data collection and pre-processing, the feature recognition of abnormal traffic, the application of PSO algorithm, real-time monitoring and response mechanism. The results of two sets of simulation experiments are as follows: compared with the traditional model, the accuracy rate of ATD of the improved algorithm is increased by 7.2% on average, and the detection time is reduced by 7.35s on average. This method not only enhances the adaptability of the model to new attacks, but also improves the degree of automation of detection.

关键词： Network Anomaly Traffic Detection data Processing Technology particle swarm optimization

来源：评论

学校读者我要写书评

暂无评论

AI-Enhanced Public Safety Lighting for Smart Sustainable Cities Using Cloud Computing

AI-Enhanced Public Safety Lighting for Smart Sustainable Cit...

引用

Multi-Agent Systems for Collaborative Intelligence (ICMSCI), International Conference on

作者： Bharat Tidke S. Pragadeeswaran R. Poornima Lakshmi G Bhuvaneswari G Manikandan S. Murugan Symbiosis Institute of Technology Nagpur Campus Symbiosis international (Deemed) University Pune India Department of Computer Science and Engineering School of Computing Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Chennai Tamil Nadu India Department of Computer Science and Engineering Chennai Institute of Technology Chennai India Department of Computer Science and Engineering Saveetha Engineering college Saveetha Nagar Thandalam Chennai Tamil Nadu India Department of Artificial Intelligence and Data Science RMK Engineering College Kavaraipettai Chennai Tamil Nadu India Department of Biomedical Engineering Saveetha School of Engineering Saveetha Institute of Medical and Technical Sciences Saveetha University Chennai Tamil Nadu India

ISBN: (数字)9798331509828

ISBN: (纸本)9798331509835

This paper presents a novel method that combines cloud computing infrastructure and Reinforcement Learning (RL) algorithms to improve public safety lighting in smart cities. By dynamically adjusting lighting levels in response to real-time sensor inputs, the proposed system aims to maximize visibility while minimizing energy consumption. The cloud-based framework's RL agents continuously interact with the environment and human activity patterns to learn the best lighting policies. The system utilizes data from multiple sensors, including ambient light and motion detectors, to adjust real-time to daylight levels, weather, and pedestrian traffic variations. By integrating RL, the lighting system can adapt to changing urban dynamics and safety requirements over time, all while reducing energy waste. Compared to conventional static lighting systems, case studies and simulations show how the system can significantly improve visibility and response times while enhancing safety in various urban settings. RL algorithms can be easily deployed and managed throughout extensive smart city networks due to cloud computing network scalability and adaptability. This study advances sustainable urban infrastructure by showcasing the effectiveness of RL-based artificial intelligence (AI) solutions in public safety lighting optimization, thereby laying the groundwork for future smarter and safer cities.

关键词： Cloud computing Pedestrians Smart cities Scalability Lighting Public security Real-time systems Artificial intelligence Standards Meteorology

来源：评论

学校读者我要写书评

暂无评论

The Two Fundamental Shapes of Sleep Heart Rate Dynamics and Their Connection to Mental Health in College Students

引用

Digital Biomarkers 2024年第1期8卷 120-131页

作者： Fudolig, Mikaela Irene Bloomfield, Laura S.P. Price, Matthew Bird, Yoshi M. Hidalgo, Johanna E. Kim, Julia N. Llorin, Jordan Lovato, Juniper McGinnis, Ellen W. McGinnis, Ryan S. Ricketts, Taylor Stanton, Kathryn Dodds, Peter Sheridan Danforth, Christopher M. Vermont Complex Systems Center MassMutual Center of Excellence for Complex Systems and Data Science University of Vermont BurlingtonVT United States Department of Mathematics and Statistics University of Vermont BurlingtonVT United States Computational Story Lab MassMutual Center of Excellence for Complex Systems and Data Science University of Vermont BurlingtonVT United States Gund Institute for Environment University of Vermont BurlingtonVT United States Department of Psychological Science University of Vermont BurlingtonVT United States Project Lemurs University of Vermont BurlingtonVT United States Department of Electrical and Biomedical Engineering University of Vermont BurlingtonVT United States Department of Computer Science University of Vermont BurlingtonVT United States Wake Forest University School of Medicine Winston-SalemNC United States Rubenstein School of Environment and Natural Resources University of Vermont BurlingtonVT United States Santa Fe Institute Santa FeNM United States

Introduction: Wearable devices are rapidly improving our ability to observe health-related processes for extended durations in an unintrusive manner. In this study, we use wearable devices to understand how the shape of the heart rate curve during sleep relates to mental health. Methods: As part of the Lived Experiences Measured Using Rings Study (LEMURS), we collected heart rate measurements using the Oura ring (Gen3) for over 25,000 sleep periods and self-reported mental health indicators from roughly 600 first-year university students in the USA during the fall semester of 2022. Using clustering techniques, we find that the sleeping heart rate curves can be broadly separated into two categories that are mainly differentiated by how far along the sleep period the lowest heart rate is reached. Results: Sleep periods characterized by reaching the lowest heart rate later during sleep are also associated with shorter deep and REM sleep and longer light sleep, but not a difference in total sleep duration. Aggregating sleep periods at the individual level, we find that consistently reaching the lowest heart rate later during sleep is a significant predictor of (1) self-reported impairment due to anxiety or depression, (2) a prior mental health diagnosis, and (3) firsthand experience in traumatic events. This association is more pronounced among females. Conclusion: Our results show that the shape of the sleeping heart rate curve, which is only weakly correlated with descriptive statistics such as the average or the minimum heart rate, is a viable but mostly overlooked metric that can help quantify the relationship between sleep and mental health. © 2024 The Author(s). Published by S. Karger AG, Basel.

关键词： Wearable technology

来源：评论

学校读者我要写书评

暂无评论

Proposing Machine Learning as the technology to Deal with the Liver Disease

Proposing Machine Learning as the technology to Deal with th...

引用

Emerging Trends in Industry 4.0 (ETI 4.0)

作者： Nageshwar Dev Yadav Vaibhav Kant Singh Master Data Management Cloud Product Research & Development Product Specialist at Informatica Bengaluru Karnataka India Department of Computer Science & Engineering School of Studies of Engineering and Technology Guru Ghasidas Vishwavidyalaya A Central University Bilaspur Chhattisgarh India

In this work the Authors majorly focuses on the Disease that is Liver Disease and tried to work out a Strategy that could be handy to Deal with the Problem under Question. The implementation of the Work is solely in Python. The Major Python Libraries are used to come up with a Solution. There are various ML approaches Available to Handle the Problem. In our Implementation we made a Utilization of the data-Set received from Kaggle Repository. The Implementation makes usage of the Technology that is Support Vector Machine. We in our work made utilization of the Four Kernels Available for Implementation in Python Programming. In the Implementation Section we will observe the Classification Report Generated in the Coding done by the Authors. SVM is a very nice approach to take care of the Medical Issues.

关键词： Support vector machines Liver diseases Machine learning Programming Libraries Encoding Kernel

来源：评论

学校读者我要写书评

暂无评论

TRACKING OBJECTS AND ACTIVITIES WITH ATTENTION FOR TEMPORAL SENTENCE GROUNDING

arXiv

引用

arXiv 2023年

作者： Xiong, Zeyu Liu, Daizong Zhou, Pan Zhu, Jiahao Hubei Key Laboratory of Distributed System Security Hubei Engineering Research Center on Big Data Security School of Cyber Science and Engineering Huazhong University of Science and Technology China Wangxuan Institute of Computer Technology Peking University China

Temporal sentence grounding (TSG) aims to localize the temporal segment which is semantically aligned with a natural language query in an untrimmed video. Most existing methods extract frame-grained features or object-grained features by 3D ConvNet or detection network under a conventional TSG framework, failing to capture the subtle differences between frames or to model the spatio-temporal behavior of core persons/objects. In this paper, we introduce a new perspective to address the TSG task by tracking pivotal objects and activities to learn more fine-grained spatio-temporal behaviors. Specifically, we propose a novel Temporal Sentence Tracking Network (TSTNet), which contains (A) a Cross-modal Targets Generator to generate multi-modal templates and search space, filtering objects and activities, and (B) a Temporal Sentence Tracker to track multi-modal targets for modeling the targets' behavior and to predict query-related segment. Extensive experiments and comparisons with state-of-the-arts are conducted on challenging benchmarks: Charades-STA and TACoS. And our TSTNet achieves the leading performance with a considerable real-time speed. Copyright © 2023, The Authors. All rights reserved.

关键词： Arts computing

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：