检索结果-内蒙古大学图书馆

arXiv 2021年

作者： Altin, Mahsun Gürsoy, Furkan Xu, Lina Dept. of Computer Engineering Abdullah Gül University Kayseri Turkey Dept. of Management Information Systems Bogaziçi University Istanbul Turkey Dept. of Computer Science University College Dublin Dublin Ireland

Deep-learning based computer vision models have proved themselves to be ground-breaking approaches to human activity recognition (HAR). However, most existing works are dedicated to improve the prediction accuracy through either creating new model architectures, increasing model complexity, or refining model parameters by training on larger datasets. Here, we propose an alternative idea, differing from existing work, to increase model accuracy and also to shape model predictions to align with human understandings through automatically creating higher-level summarizing labels for similar groups of human activities. First, we argue the importance and feasibility of constructing a hierarchical labeling system for human activity recognition. Then, we utilize the predictions of a black box HAR model to identify similarities between different activities. Finally, we tailor hierarchical clustering methods to automatically generate hierarchical trees of activities and conduct experiments. In this system, the activity labels on the same level will have a designed magnitude of accuracy and reflect a specific amount of activity details. This strategy enables a trade-off between the extent of the details in the recognized activity and the user privacy by masking some sensitive predictions;and also provides possibilities for the use of formerly prohibited invasive models in privacy-concerned scenarios. Since the hierarchy is generated from the machine’s perspective, the predictions at the upper levels provide better accuracy, which is especially useful when there are too detailed labels in the training set that are rather trivial to the final prediction goal. Moreover, the analysis of the structure of these trees can reveal the biases in the prediction model and guide future data collection strategies. Copyright © 2021, The Authors. All rights reserved.

关键词： Video signal processing

来源：评论

学校读者我要写书评

暂无评论

Artificial Intelligence Oriented User Sentiment Evaluation System on Social Networks using Modified Deep Learning Principles

Artificial Intelligence Oriented User Sentiment Evaluation S...

引用

Mobile Computing and Sustainable Informatics (ICMCSI), International Conference on

作者： S. Thangamayan Sandip Nivrutti Jagdale T R.Kalai Lakshmi Jayendra Gopal Thatipudi Penyameen. K Bhola Khan Department of Research and Development Saveetha School of Law Saveetha Institute of Medical and Technical Sciences Chennai Yashwantrao Mohite Institute of Management Karad Bharati Vidyapeeth(Deemed to be University) School Of Management Studies Sathyabama Institute Of Science And Technology Chennai Dept. of Computer Science University of North Texas Velammal College Of Engineering And Technology Madurai Department of Regional Economics MJP Rohilkhand University Bareilly India

Sentiment analysis, a pivotal aspect of natural language processing, is vital for deciphering the emotional nuances embedded in textual data. This project introduces an innovative workflow that amalgamates various techniques to elevate sentiment analysis performance. The workflow encompasses Fuzzy C-means (FCM) clustering for pattern identification, Differential Multi-layer Whale Optimization (DWO) for feature extraction, and a classification phase utilizing diverse deep learning models, including Long Short-Term Memory (LSTM) and Convolutional Neural Networks (CNN). Additionally, Ant Lion Optimization (ALO) ensures system optimization, fostering robustness and adaptability. The proposed system is evaluated against eight distinct deep learning models, each offering unique architectures or configurations. Remarkably, the proposed workflow achieves an impressive accuracy of 96%, underscoring its efficacy in discerning complex sentiments. This high level of accuracy positions the system as a powerful tool for real-world applications where nuanced understanding of human sentiment is paramount. The project contributes to the evolving landscape of sentiment analysis, providing a comprehensive framework for extracting valuable insights from diverse textual datasets.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Predicting directional sound-localization of human listeners in both horizontal and vertical dimensions 148

Predicting directional sound-localization of human listeners...

引用

148th Audio engineering Society International Convention 2020

作者： Barumerli, Roberto Majdak, Piotr Reijniers, Jonas Baumgartner, Robert Geronazzo, Michele Avanzini, Federico Dept. of Information Engineering University of Padova Italy Acoustics Research Institute Austrian Academy of Sciences Austria Dept. of Engineering Management University of Antwerp Belgium Dept. of Architecture Design and Media Technology Aalborg University Denmark Dept. of Computer Science University of Milano Italy

Measuring and understanding spatial hearing is a fundamental step to create effective virtual auditory displays (VADs). The evaluation of such auralization systems often requires psychoacoustic experiments. This process can be time consuming and error prone, resulting in a bottleneck for the evaluation complexity. In this work we evaluated a probabilistic auditory model for sound localization intended as a tool to assess VAD's abilities to provide static sound-localization cues to listeners. The outcome of the model, compared with actual results of psychoacoustic experiments, shows the advantages and limitations of this systematic evaluation. © 2020 148th Audio engineering Society International Convention. All rights reserved.

关键词： Audition

来源：评论

学校读者我要写书评

暂无评论

Pairs in Nested Steiner Quadruple Systems

arXiv

引用

arXiv 2024年

作者： Chee, Yeow Meng Dau, Son Hoang Etzion, Tuvi Kiah, Han Mao Zhang, Wenqin Dept. of Industrial Systems Engineering and Management National University of Singapore Singapore School of Computing Technologies RMIT University MelbourneVIC3000 Australia Computer Science Faculty TechnionIsrael Institute of Technology Haifa3200003 Israel School of Physical and Mathematical Sciences Nanyang Technological University Singapore School of Electronic Information and Engineering Shanghai Jiao tong University China

Motivated by a repair problem for fractional repetition codes in distributed storage, each block of any Steiner quadruple system (SQS) of order v is partitioned into two pairs. Each pair in such a partition is called a nested design pair and its multiplicity is the number of times it is a pair in this partition. Such a partition of each block is considered as a new block design called a nested Steiner quadruple system. Several related questions on this type of design are considered in this paper: What is the maximum multiplicity of the nested design pair with minimum multiplicity? What is the minimum multiplicity of the nested design pair with maximum multiplicity? Are there nested quadruple systems in which all the nested design pairs have the same multiplicity? Of special interest are nested quadruple systems in which all the (v2) pairs are nested design pairs with the same multiplicity. Several constructions of nested quadruple systems are considered and in particular classic constructions of SQS are examined. © 2024, CC BY.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Convex neural network synthesis for robustness in the 1-norm

arXiv

引用

arXiv 2024年

作者： Drummond, Ross Guiver, Chris Turner, Matthew C. Dept. of Automatic Control and Systems Engineering University of Sheffield SheffieldS1 3JD United Kingdom School of Computing Engineering & the Built Environment Edinburgh Napier University EdinburghEH10 5DT United Kingdom School of Electronics and Computer Science University of Southampton SouthamptonSO17 1BJ United Kingdom

With neural networks being used to control safety-critical systems, they increasingly have to be both accurate (in the sense of matching inputs to outputs) and robust. However, these two properties are often at odds with each other and a trade-off has to be navigated. To address this issue, this paper proposes a method to generate an approximation of a neural network which is certifiably more robust. Crucially, the method is fully convex and posed as a semi-definite programme. An application to robustifying model predictive control is used to demonstrate the results. The aim of this work is to introduce a method to navigate the neural network robustness/accuracy trade-off. © 2024, CC BY.

关键词： Model predictive control

来源：评论

学校读者我要写书评

暂无评论

MORIX: Machine learning-aided framework for lethality detection and MORtality inference with eXplainable artificial intelligence in MAFLD subjects

Computer Methods and Programs in Biomedicine Update

引用

computer Methods and Programs in Biomedicine Update 2025年 7卷

作者： Lofù, Domenico Sorino, Paolo Colafiglio, Tommaso Bonfiglio, Caterina Donghia, Rossella Giannelli, Gianluigi Lombardi, Angela Di Noia, Tommaso Di Sciascio, Eugenio Narducci, Fedelucio Dept. of Electrical and Information Engineering (DEI) Politecnico di Bari BA Bari 70125 Italy Dept. of Computer Automatic and Management Engineering (DIAG) Sapienza Università di Roma RM Roma 00185 Italy Unit of Data Science National Institute of Gastroenterology ”Saverio de Bellis” IRCCS Hospital BA Castellana Grotte 70013 Italy Scientific Direction National Institute of Gastroenterology ”Saverio de Bellis” IRCCS Hospital BA Castellana Grotte 70013 Italy

Metabolic dysfunction-associated fatty liver disease (MAFLD) introduces new diagnostic criteria for fatty liver disease that are independent of alcohol consumption and viral hepatitis infection. Therefore, investigating how biochemical and anthropometric factors influence mortality in MAFLD subjects is of significant interest. In this work, we propose MORIX, an Artificial Intelligence-based framework capable of predicting fatal mortality outcomes in subjects with MAFLD. MORIX utilizes data from epidemiological datasets containing carefully selected anthropometric and biochemical information. This selection is achieved through Recursive Feature Elimination (RFE) using a Random Forest (RF) to train Machine Learning (ML) algorithms and provide a mortality risk (Yes/No) output. To provide physicians with a valuable tool, MORIX was trained and tested on a dataset of MAFLD subjects, comparing five different models: Random Forest (RF), eXtreme Gradient Boosting (XGB), Support Vector Machine (SVM), Multilayer Perceptron (MLP), and Light Gradient Boosting Model (LGBM) in a 5-fold cross-validation training strategy. Experimental results identified the RF as the best model, achieving a high accuracy for both mortality risks predicted. Additionally, an eXplainable Artificial Intelligence (XAI) analysis was conducted to clarify the diagnostic logic of the RF model and to assess the impact of each feature to the prediction. Moreover, a web application was developed to predict mortality risk and provide explanations of how the input features influenced the final prediction. In conclusion, the MORIX framework is easy to apply, and the required parameters are readily available in healthcare datasets, making it a practical tool for medical professionals. © 2025 The Authors

关键词： Epidemiology Interpretability Machine learning techniques MAFLD Mortality

来源：评论

学校读者我要写书评

暂无评论

ELCCFD: An Efficient and Enhanced Credit Card Fraud Detection using Enhanced Deep Learning Principle

ELCCFD: An Efficient and Enhanced Credit Card Fraud Detectio...

引用

Image Processing and Capsule Networks (ICIPCN), International Conference on

作者： Pandarinath Potluri Sajja Suneel B. Chandra D. Muthukumaran Makarand Upadhyaya R Rajesh Kanna department of CSE Swarnandhra college of engineering and technology Sitarampuram Narsapuram West Godavari district Department of CSE(Data Science) Institute of Aeronautical Engineering Hyderabad Telangana India Department of Management Studies Vignan's Institute of Information Technology(A) AP India Vel Tech Rangarajan Dr. Sagunthala R&D Institute of Science and Technology Dept. of Management & Marketing College of Business Administration University of Bahrain Department of Computer Science CHRIST (Deemed to be University)

ISBN: (数字)9798350367171

ISBN: (纸本)9798350367188

Credit card fraud poses a serious threat to financial institutions and their customers; hence, stringent detection protocols are necessary. This study introduces an approach known as Enhanced Learning for Credit Card Fraud Detection (ELCCFD) to enhance the accuracy of credit card fraud detection. To improve the fraud detection process, the proposed method combines the strengths of Convolutional Neural Networks (CNNs), AlexNet architecture, and Gradient Boosting Machines (GBM). The proposed approach begins with cleaning up the credit card data to get useful features, then trains a Convolutional Neural Network (CNN) using AlexNet to figure out complex patterns and representations on its own. This study generates a complete set of features by merging the CNN’s output with features generated using GBM. The final model is trained by using a combination of deep learning and other conventional machine learning techniques to achieve the best results. Experimental findings on benchmark datasets demonstrate the effectiveness of the ELCCFD methodology, achieving an accuracy rate of 98%. This study combines AlexNet with GBM to get a model to capture the complex patterns and is easier to understand with the feature importance analysis. With its strong accuracy and reliability, the proposed methodology offers a strong option to fight credit card fraud, and it shows the potential for actual use in financial systems.

关键词： Deep learning Accuracy Protocols Image processing Merging Credit cards Cleaning

来源：评论

学校读者我要写书评

暂无评论

Performance Enhancement and Secrecy Analysis of Hybrid RF/FSO Communication Links Under Combined κ-μ Fading and Exponential Turbulence Conditions

Performance Enhancement and Secrecy Analysis of Hybrid RF/FS...

引用

Computational Intelligence, Communication Technology and Networking (CICTN), International Conference on

作者： Deepak Upadhyay Prakhar Prakhar Rashmy Moray Rashmi Sharma Nookala Venu Shipra Shukla Dept. of Computer Science and Engineering Graphic Era Hill University Dehradun India Department of CSE Roorkee Institute of Technology Pune India Symbiosis Institute of Management Studies (SIMS) A Constituent of Symbiosis International Deemed University Department of CSE Symbiosis Institute of Technology Nagpur Campus Symbiosis International (Deemed University) Pune India Centre for Internet of Things Madhav Institute of Technology & Science Deemed University Gwalior India Dept. of CSE (Data Science) G. L. Bajaj Institute of Technology and Management Greater Noida India

ISBN: (数字)9798331530389

ISBN: (纸本)9798331530396

In this study, the secrecy performance evaluation of hybrid RF/FSO communication systems over κ-μ fading and exponential turbulence channels are conducted. We analyse the secure information rate and evaluate the throughput and secrecy capacity of the system through simulations. The results indicate that the proposed hybrid system improves reliability and security by combining adaptive modulation, beamforming, and encryption to combat interference and secure data transmission. Geographical heat maps help to visualize the influence of environmental factors on system performance. Federated learning in hybrid RF/FSO systems have been investigated in detail through simulations and numerical results to show the considerable improvements in communication reliability and performance that the increased redundancy and robustness of the hybrid scheme provides. This helps gain valuable insights into a better design of wireless networks in the future by highlighting the benefits of hybrid communication techniques and simulation-driven design to enhance performance and security across diverse complex environments and conditions.

关键词： Fading channels Analytical models Adaptation models Array signal processing Atmospheric modeling Computational modeling Modulation Throughput Encryption Security

来源：评论

学校读者我要写书评

暂无评论

Numerical approach to design of low frequency magnetic field irradiation system for lab on chip experiments

Numerical approach to design of low frequency magnetic field...

引用

ELEKTRO

作者： Roman Radil Marek Bajtoš Lucia Č arnecká Klaudia Hargaš ová Patrik Kamencay Department of Electromagnetic and Biomedical Engineering University of Zilina Zilina Slovakia Department of Systems Biology and Engineering Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Gliwice Poland Dept. of Electromagnetic and Biomedical Engineering Organization University of Zilina Zilina Slovakia

ISBN: (数字)9781665467261

ISBN: (纸本)9781665467278

The article is focused on design of specific electromagnetic coil system using numerical modelling and simulation methods. The proposed solution would be capable of delivering magnetic field of desired strength/ flux density and homogeneity within the specific area to affect the cultivation process of single cells in lab on chip experiments.

关键词： Radiation effects Numerical models Magnetic fields Electromagnetics

来源：评论

学校读者我要写书评

暂无评论

Database Reconstruction Is Not So Easy and Is Different from Reidentification

arXiv

引用

arXiv 2023年

作者： Muralidhar, Krishnamurty Domingo-Ferrer, Josep University of Oklahoma Price College of Business Dept. of Marketing and Supply Chain Management 307 West Brooks Adams Hall Room 10 NormanOK73019 United States Universitat Rovira i Virgili Dept. of Computer Engineering and Mathematics CYBERCAT-Center for Cybersecurity Research of Catalonia Av. Països Catalans Catalonia Tarragona26 43007 Spain

In recent years, it has been claimed that releasing accurate statistical information on a database is likely to allow its complete reconstruction. Differential privacy has been suggested as the appropriate methodology to prevent these attacks. These claims have recently been taken very seriously by the U.S. Census Bureau and led them to adopt differential privacy for releasing U.S. Census data. This in turn has caused consternation among users of the Census data due to the lack of accuracy of the protected outputs. It has also brought legal action against the U.S. Department of Commerce. In this paper, we trace the origins of the claim that releasing information on a database automatically makes it vulnerable to being exposed by reconstruction attacks and we show that this claim is, in fact, incorrect. We also show that reconstruction can be averted by properly using traditional statistical disclosure control (SDC) techniques. We further show that the geographic level at which exact counts are released is even more relevant to protection than the actual SDC method employed. Finally, we caution against confusing reconstruction and reidentification: using the quality of reconstruction as a metric of reidentification results in exaggerated reidentification risk *** Codes 68P27 Privacy of data © 2023, CC BY-NC-ND.

关键词： Database systems

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：