检索结果-内蒙古大学图书馆

32nd International Conference on Concurrency Theory, CONCUR 2021

作者： Shetty, Aneesh K. Krishna, S. Zetzsche, Georg Department of Computer Science and Engineering Iit Bombay India Max Planck Institute for Software Systems Kaiserslautern Germany

ISBN: (纸本)9783959772037

Multi-pushdown systems are a standard model for concurrent recursive programs, but they have an undecidable reachability problem. Therefore, there have been several proposals to underapproximate their sets of runs so that reachability in this underapproximation becomes decidable. One such underapproximation that covers a relatively high portion of runs is scope boundedness. In such a run, after each push to stack i, the corresponding pop operation must come within a bounded number of visits to stack i. In this work, we generalize this approach to a large class of infinite-state systems. For this, we consider the model of valence systems, which consist of a finite-state control and an infinitestate storage mechanism that is specified by a finite undirected graph. This framework captures pushdowns, vector addition systems, integer vector addition systems, and combinations thereof. For this framework, we propose a notion of scope boundedness that coincides with the classical notion when the storage mechanism happens to be a multi-pushdown. We show that with this notion, reachability can be decided in PSPACE for every storage mechanism in the framework. Moreover, we describe the full complexity landscape of this problem across all storage mechanisms, both in the case of (i) the scope bound being given as input and (ii) for fixed scope bounds. Finally, we provide an almost complete description of the complexity landscape if even a description of the storage mechanism is part of the input. © Aneesh K. Shetty, S. Krishna, and Georg Zetzsche;.

关键词： Vectors

来源：评论

学校读者我要写书评

暂无评论

COVID-19 Detection System: A Comparative Analysis of System Performance Based on Acoustic Features of Cough Audio Signals

COVID-19 Detection System: A Comparative Analysis of System ...

引用

IEEE International Conference on Trust, Security and Privacy in Computing and Communications (TrustCom)

作者： Asmaa Shati Ghulam Mubashar Hassan Amitava Datta Department of Computer Science and Software Engineering University of Western Australia Australia Department of Information Systems King Khalid University Saudi Arabia

ISBN: (数字)9798350381993

ISBN: (纸本)9798350382006

A wide range of respiratory diseases, such as cold and flu, asthma, and COVID-19, affect people’s daily lives worldwide. In medical practice, respiratory sounds are widely used in medical services to diagnose various respiratory illnesses and lung disorders. The traditional diagnosis of such sounds requires specialized knowledge, which can be costly and reliant on human expertise. Recently, cough audio recordings have been used to automate the process of detecting respiratory conditions. This research aims to examine various acoustic features that enhance the performance of machine learning (ML) models in detecting COVID-19 from cough signals. This study investigates the efficacy of three feature extraction techniques, including Mel Frequency Cepstral Coefficients (MFCC), Chroma, and Spectral Contrast features, on two ML algorithms, Support Vector Machine (SVM) and Multilayer Perceptron (MLP), and thus proposes an efficient COVID-19 detection system. The proposed system produces a practical solution and demonstrates higher state-of-the-art classification performance with an AUC of 0.843 on the COUGHVID dataset and 0.953 on the Virufy dataset for COVID-19 detection.

关键词： COVID-19 Support vector machines Training Computational modeling System performance Machine learning Feature extraction

来源：评论

学校读者我要写书评

暂无评论

Multi-Dataset Multi-Task Learning for COVID-19 Prognosis

arXiv

引用

arXiv 2024年

作者： Ruffini, Filippo Tronchin, Lorenzo Wu, Zhuoru Chen, Wenting Soda, Paolo Shen, Linlin Guarrasi, Valerio Unit of Computer Systems & Bioinformatics Department of Engineering Università Campus Bio-Medico di Roma Rome Italy College of Computer Science and Software Engineering Shenzhen University Shenzhen China Department of Electrical Engineering City University of Hong Kong Hong Kong

In the fight against the COVID-19 pandemic, leveraging artificial intelligence to predict disease outcomes from chest radiographic images represents a significant scientific aim. The challenge, however, lies in the scarcity of large, labeled datasets with compatible tasks for training deep learning models without leading to overfitting. Addressing this issue, we introduce a novel multi-dataset multi-task training framework that predicts COVID-19 prognostic outcomes from chest X-rays (CXR) by integrating correlated datasets from disparate sources, distant from conventional multi-task learning approaches, which rely on datasets with multiple and correlated labeling schemes. Our framework hypothesizes that assessing severity scores enhances the model's ability to classify prognostic severity groups, thereby improving its robustness and predictive power. The proposed architecture comprises a deep convolutional network that receives inputs from two publicly available CXR datasets, AIforCOVID for severity prognostic prediction and BRIXIA for severity score assessment, and branches into task-specific fully connected output networks. Moreover, we propose a multi-task loss function, incorporating an indicator function, to exploit multi-dataset integration. The effectiveness and robustness of the proposed approach are demonstrated through significant performance improvements in prognosis classification tasks across 18 different convolutional neural network backbones in different evaluation strategies. This improvement is evident over single-task baselines and standard transfer learning strategies, supported by extensive statistical analysis, showing great application potential. © 2024, CC BY-NC-SA.

关键词： COVID-19

来源：评论

学校读者我要写书评

暂无评论

Multimodal Deep Neural Networks for Digitized Document Classification

引用

computer systems Science & engineering 2024年第3期48卷 793-811页

作者： Aigerim Baimakhanova Ainur Zhumadillayeva Bigul Mukhametzhanova Natalya Glazyrina Rozamgul Niyazova Nurseit Zhunissov Aizhan Sambetbayeva Department of Computer Engineering Khoja Akhmet Yassawi International Kazakh-Turkish UniversityTurkistanKazakhstan Department of Computer and Software Engineering L.N.Gumilyov Eurasian National UniversityAstanaKazakhstan Department of Information and Computing Systems Non-Profit Joint Stock Company Abylkas Saginov Karaganda Technical UniversityKaragandaKazakhstan Department of Information Systems Al-Farabi Kazakh National UniversityAlmatyKazakhstan

As digital technologies have advanced more rapidly,the number of paper documents recently converted into a digital format has exponentially *** respond to the urgent need to categorize the growing number of digitized documents,the classification of digitized documents in real time has been identified as the primary goal of our study.A paper classification is the first stage in automating document control and efficient knowledge discovery with no or little human *** intelligence methods such as Deep Learning are now combined with segmentation to study and interpret those traits,which were not conceivable ten years *** learning aids in comprehending input patterns so that object classes may be *** segmentation process divides the input image into separate segments for a more thorough image *** study proposes a deep learning-enabled framework for automated document classification,which can be implemented in higher *** further this goal,a dataset was developed that includes seven categories:Diplomas,Personal documents,Journal of Accounting of higher education diplomas,Service letters,Orders,Production orders,and Student ***,a deep learning model based on Conv2D layers is proposed for the document classification *** the final part of this research,the proposed model is evaluated and compared with other machine-learning *** results demonstrate that the proposed deep learning model shows high results in document categorization overtaking the other machine learning models by reaching 94.84%,94.79%,94.62%,94.43%,94.07%in accuracy,precision,recall,F-score,and AUC-ROC,*** achieved results prove that the proposed deep model is acceptable to use in practice as an assistant to an office worker.

关键词： Document categorization deep learning machine learning classification digitization

来源：评论

学校读者我要写书评

暂无评论

Energy Optimised Security against Wormhole Attack in IoT-Based Wireless Sensor Networks

引用

computers, Materials & Continua 2021年第8期68卷 1967-1981页

作者： Hafsa Shahid Humaira Ashraf Hafsa Javed Mamoona Humayun Nz Jhanjhi Mohammed A.AlZain Department of Computer Science and Software Engineering International Islamic University IslamabadIslamabadPakistan Department of Information Systems College of Computer and Information ScienceJouf UniversityAl-JoufSaudi Arabia School of Computer Science and Engineering(SCE) Taylor’s UniversitySelangorMalaysia Department of Information Technology College of Computers and Information TechnologyTaif UniversityTaif21944Saudi Arabia

An IoT-based wireless sensor network(WSN)comprises many small sensors to collect the data and share it with the central *** sensors are battery-driven and resource-restrained devices that consume most of the energy in sensing or collecting the data and transmitting *** data sharing,security is an important concern in such networks as they are prone to many threats,of which the deadliest is the wormhole *** attacks are launched without acquiring the vital information of the network and they highly compromise the communication,security,and performance of the *** the IoT-based network environment,its mitigation becomes more challenging because of the low resource availability in the sensing *** have performed an extensive literature study of the existing techniques against the wormhole attack and categorised them according to their *** analysis of literature has motivated our *** this paper,we developed the ESWI technique for detecting the wormhole attack while improving the performance and *** algorithm has been designed to be simple and less complicated to avoid the overheads and the drainage of energy in its *** simulation results of our technique show competitive results for the detection rate and packet delivery *** also gives an increased throughput,a decreased end-to-end delay,and a much-reduced consumption of energy.

关键词： IoT Internet of Things energy wormhole WSN wireless sensor networks

来源：评论

学校读者我要写书评

暂无评论

A Way to Protect the Surveillance Data Stored in the Cloud Using FC and SVM Methods 4

A Way to Protect the Surveillance Data Stored in the Cloud U...

引用

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

作者： Suganthi, D. Raju, M. Mahesh Kumar, N.B. Vasavi, M. Washeel, Oday Faris Abdtawfeeq, Tareq Hafdhi Saveetha College of Liberal Arts and Sciences Simats Department of Computer Science Chennai Tamilnadu Thandalam602105 India Sri Krishna Arts and Science College Department of Software Systems Coimbatore India Tamil Nadu Coimbatore641 032 India Cvr College of Engineering Et Department Hyderabad India National University of Science and Technology Collage of Nursing Dhi Qar64001 Iraq

ISBN: (纸本)9798350360165

Building trust between consumers and service providers is critical to the functioning of cloud computing, a technology that offers a range of services over the Internet. When consumers choose which cloud services to utilise for processing and storing sensitive data, trust values are a major factor. In addition, service providers can employ trust values as a means of granting access to resources, protecting against malevolent users. The subjective trust model category, which evaluates trust based on user and service provider behaviour, is the one that this research suggests for trust models. Because trust is intrinsically ambiguous in our method, trust levels for cloud consumers and service providers are calculated using fuzzy logic and support vector machines. Using triangle membership functions for defuzzification and Gauss membership functions for fuzzification, we use the Mamdani fuzzy approach. In order to determine how trustworthy a resource is, our paradigm for evaluating trust takes performance and flexibility into account. Performance evaluation includes measurements related to workload and reaction time, whereas elasticity evaluation takes into account elements like scalability, availability, security, and usability. We apply fuzzy C-means clustering on pertinent criteria to establish trust levels for users, including faulty requests, fake requests, unauthorised requests, and total requests. © 2024 IEEE.

关键词： Cloud platforms

来源：评论

学校读者我要写书评

暂无评论

Cooperative Learning-Based Framework for VNF Caching and Placement Optimization over Low Earth Orbit Satellite Networks

arXiv

引用

arXiv 2024年

作者： Doan, Khai Avgeris, Marios Leivadeas, Aris Lambadaris, Ioannis Shin, Wonjae Korea University School of Electrical Engineering Seoul Korea Republic of Carleton University Department of Systems and Computer Engineering OttawaON Canada École de Technologie Supérieure Department of Software and IT Engineering MontrealQC Canada

Low Earth Orbit Satellite Networks (LSNs) are integral to supporting a broad range of modern applications, which are typically modeled as Service Function Chains (SFCs). Each SFC is composed of Virtual Network Functions (VNFs), where each VNF performs a specific task. In this work, we tackle two key challenges in deploying SFCs across an LSN. Firstly, we aim to optimize the long-term system performance by minimizing the average end-to-end SFC execution delay, given that each satellite comes with a pre-installed/cached subset of VNFs. To achieve optimal SFC placement, we formulate an offline Dynamic Programming (DP) equation. To overcome the challenges associated with DP, such as its complexity, the need for probability knowledge, and centralized decision-making, we put forth an online Multi-Agent Q-Learning (MAQL) solution. Our MAQL approach addresses convergence issues in the non-stationary LSN environment by enabling satellites to share learning parameters and update their Q-tables based on distinct rules for their selected actions. Secondly, to determine the optimal VNF subsets for satellite caching, we develop a Bayesian Optimization (BO)-based learning mechanism that operates both offline and continuously in the background during runtime. Extensive experiments demonstrate that our MAQL approach achieves near-optimal performance comparable to the DP model and significantly outperforms existing baselines. Moreover, the BO-based approach effectively enhances the request serving rate over time. © 2024, CC BY.

关键词： Dynamic programming

来源：评论

学校读者我要写书评

暂无评论

KRATT: QBF-Assisted Removal and Structural Analysis Attack Against Logic Locking

arXiv

引用

arXiv 2023年

作者： Aksoy, Levent Yasin, Muhammad Pagliarini, Samuel Department of Computer Systems Tallinn University of Technology Tallinn Estonia Department of Computer and Software Engineering National University of Sciences and Technology Islamabad Pakistan Department of Electrical and Computer Engineering Carnegie Mellon University Pittsburgh United States

This paper introduces KRATT, a removal and structural analysis attack against state-of-the-art logic locking techniques, such as single and double flip locking techniques (SFLTs and DFLTs). KRATT utilizes powerful quantified Boolean formulas (QBFs), which have not found widespread use in hardware security, to find the secret key of SFLTs for the first time. It can handle locked circuits under both oracle-less (OL) and oracle-guided (OG) threat models. It modifies the locked circuit and uses a prominent OL attack to make a strong guess under the OL threat model. It uses a structural analysis technique to identify promising protected input patterns and explores them using the oracle under the OG model. Experimental results on ISCAS’85, ITC’99, and HeLLO: CTF’22 benchmarks show that KRATT can break SFLTs using a QBF formulation in less than a minute, can decipher a large number of key inputs of SFLTs and DFLTs with high accuracy under the OL threat model, and can easily find the secret key of DFLTs under the OG threat model. It is shown that KRATT outperforms publicly available OL and OG attacks in terms of solution quality and run-time. © 2023, CC BY.

关键词： Structural analysis

来源：评论

学校读者我要写书评

暂无评论

Product Recommendation System using Deep Learning based Recurrent Neural Network

Product Recommendation System using Deep Learning based Recu...

引用

International Conference on computer Communication and Informatics (ICCCI)

作者： S. Shanthi K. Nirmaladevi N. Mathiarasi As. Krithika Tharani A. Monisha R. Kuppuchamy N. Krishnamoorthy Department of Computer Science & Engineering Kongu Engineering College Perundurai India Department of Computer Applications PSNA College of Engineering and Technology Dindigul Tamilnadu India Department of Software Systems and Engineering Vellore Campus Vellore Institute of Technology India

Today’s marketing strategies place a high priority on comprehending customer sentiments. It will not only give businesses a better understanding of how their clients view their goods and/or services, but it will also give them suggestions on how to enhance their offerings. We make an effort to comprehend the relationship between various factors in customer reviews on an online store for women’s clothing. The proposed system also classifies each review, according to, whether it recommends the product in question or not, and whether it has a positive, negative, or neutral sentiment. With the exception of review titles and review texts, we used univariate and multivariate analyses on datasets features to accomplish these goals. Additionally, we have implemented a bidirectional recurrent neural network (RNN) with a long-short term memory unit (LSTM) for sentiment and recommendation.

关键词： Deep learning Recurrent neural networks Filtering Clothing Informatics Recommender systems Business

来源：评论

学校读者我要写书评

暂无评论

A Novel Method for Pneumothorax Diagnosis and Segmentation Using Deep Convolution Neural Network

A Novel Method for Pneumothorax Diagnosis and Segmentation U...

引用

International Conference on computer Communication and Informatics (ICCCI)

A pneumothorax is the accumulation of air in the pleural space between the chest and lungs. Air that is in the lungs during breathing can leak out of the lungs and become trapped between the chest and lungs in the thoracic cavity, causing chest pain, difficulty breathing, and ultimately the complete collapse of the taut lungs. pneumothorax. Therefore, early diagnosis and treatment should be started. Neural networks have proven effective in image classification tasks, and many researchers believe that training neural network models can detect radiologist-diagnosed chest abnormalities such as pneumonia and pneumothorax. is proving. Moreover, we utilize various techniques, including Stochastic Weight Averaging (SWA), aggressive data augmentation, and learning rate schedule. We use the chest x-ray dataset provided by the 2019 SIIM-ACR In this study, a ResNet-34 neural network is trained on a data set of chest x-rays containing over 10,675 images to create a model that predicts the presence of pneumothorax from chest *** suggested system receives a Dice Similarity Coefficient (DSC) of 0.8410

关键词： Training Image segmentation Schedules Pulmonary diseases Neural networks Lung Stochastic processes

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：