检索结果-内蒙古大学图书馆

2022 International Conference on Algorithms, Microchips and Network applications

作者： Liu, Xingyuan Miao, Xianghua Faculty of Information Engineering and Automation Kunming University of Science and Technology Kunming650500 China Computer Technology Application Key Laboratory of Yunnan Province Kunming650500 China

ISBN: (纸本)9781510653290

Intrusion detection based on machine learning plays an important role in the security protection of the network environment. In order to improve the accuracy of network intrusion detection, intrusion detection algorithm based on dilated convolution and a two-way gating unit is proposed. Firstly, dilated convolution (DCNN) is used to increase the receptive field of information and extract spatial features. Secondly, the bidirectional gated cyclic unit (bigru) model is used to capture the temporal features of data, and the attention mechanism is introduced to increase the calculation of feature importance. Compared with the classical machine learning classifier, this model has a high detection rate. The multi-classification experiments on the famous UNSW-NB15 data set show that the model has leading performance, and its classification accuracy can reach 97.14%. © COPYRIGHT SPIE. Downloading of the abstract is permitted for personal use only.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

Breaking Speaker Recognition with Paddingback

Breaking Speaker Recognition with Paddingback

引用

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

作者： Zhe Ye Diqun Yan Li Dong Kailai Shen Faculty of Electrical Engineering and Computer Science Ningbo University Ningbo China Zhejiang Key Laboratory of Mobile Network Application Technology China

Machine Learning as a Service (MLaaS) has gained popularity due to advancements in Deep Neural Networks (DNNs). However, untrusted third-party platforms have raised concerns about AI security, particularly in backdoor attacks. Recent research has shown that speech backdoors can utilize transformations as triggers, similar to image backdoors. However, human ears can easily be aware of these transformations, leading to suspicion. In this paper, we propose PaddingBack, an inaudible backdoor attack that utilizes malicious operations to generate poisoned samples, rendering them indistinguishable from clean ones. Instead of using external perturbations as triggers, we exploit the widely-used speech signal operation, padding, to break speaker recognition systems. Experimental results demonstrate the effectiveness of our method, achieving a significant attack success rate while retaining benign accuracy. Furthermore, Padding-Back demonstrates the ability to resist defense methods and maintain its stealthiness against human perception.

关键词：

来源：评论

学校读者我要写书评

暂无评论

P4AI: E-application for Researching Student Interests based on Artificial Intelligence 10

P4AI: E-Application for Researching Student Interests based ...

引用

10th International Conference on Cyber and IT Service Management, CITSM 2022

作者： Adrian Sasmoko Manalu, Sonya Rapinta Indrianti, Yasinta Computer Science School of Computer Science Bina Nusantara University Jakarta Indonesia Bina Nusantara University Faculty of Humanities Education Department Jakarta Indonesia Mobile Application & Technology School of Computer Science Bina Nusantara University Jakarta Indonesia Universitas Agung Podomoro Entrepreneurship Department Jakarta Indonesia

ISBN: (数字)9781665460743

ISBN: (纸本)9781665460743

The disruptive era has led to various adaptation efforts so that it has an impact on a shift from the old profession being replaced with a variety of new professions. Therefore, it is necessary to have an instrument that is able to measure the interest and profession of students in accordance with current needs. This study aims to build an e-application based on artificial intelligence to measure Profiling for Aptitude Indicators (P4AI). The development of e-application is carried out using the waterfall method. The application development model that will be used is Agile with the Scrum model. Scrum is used to develop innovative products or services. The design of this application development will use UML and ERD based on the analyzed features. Algorithm, code, logic, and validation testing of application programs using integration testing This test method will test all modules if combined into one group to see if the program runs well or not. The results of the research are in the form of an e-application that users can use to conduct self-assessment about their interests and professions. Thus, this e-application can help the self-development needed related to the specialization and profession they have. © 2022 IEEE.

关键词： Integration testing

来源：评论

学校读者我要写书评

暂无评论

Machine Learning applications in Early Detection of Hepatic Steatosis Disease

Machine Learning Applications in Early Detection of Hepatic ...

引用

Applied Artificial Intelligence and Computing (ICAAIC), International Conference on

作者： Vishal Rajendrabhai Patel Payal Dhanesha Parthi Dharmeshkumar Soni Faculty of Computer Science Sankalchand Patel University Visnagar Gujarat India Faculty of Computer Application (IT) GLS University Ahmedabad Gujarat India Silver Oak College of Computer Applications Silver Oak University Ahmedabad Gujarat India

ISBN: (数字)9798350375190

ISBN: (纸本)9798350375206

applications “of machine learning (ML) have become vital for the early identification and treatment of hepatic steatosis illness, which is a common liver condition characterized by increased buildup of fat in the liver without a significant amount of alcohol use. This innovative approach takes use of a variety of patient-specific data, including body mass index (BMI), height, weight, gender, and follow-up time (futime), to develop prediction models and algorithms. These characteristics are used to generate models and algorithms. Patient outcomes can be improved by healthcare professionals through proactive intervention, the customization of treatment programs, and the identification of patterns, correlations, and risk factors associated with non-alcoholic fatty liver disease (NAFLD) through the analysis of multidimensional datasets by machine learning algorithms. By using machine learning (ML) to the process of identifying nonalcoholic fatty liver disease (NAFLD), diagnostic accuracy is improved, and customized medicine techniques are advanced. This, in turn, leads to advancements in the treatment and early management of this chronic liver textbf” disease.

关键词： Measurement Support vector machines Radio frequency Machine learning algorithms Accuracy Liver diseases Machine learning

来源：评论

学校读者我要写书评

暂无评论

SQAT-LD: SPeech Quality Assessment Transformer Utilizing Listener Dependent Modeling for Zero-Shot Out-of-Domain MOS Prediction

SQAT-LD: SPeech Quality Assessment Transformer Utilizing Lis...

引用

IEEE Workshop on Automatic Speech Recognition and Understanding

作者： Kailai Shen Diqun Yan Li Dong Ying Ren Xiaoxun Wu Jing Hu Faculty of Electrical Engineering and Computer Science Ningbo University Zhejiang Key Laboratory of Mobile Network Application Technology

In this paper, we propose the speech quality assessment transformer utilizing listener dependent modeling (SQAT-LD) mean opinion score (MOS) prediction system, which was submitted to the 2023 VoiceMOS Challenge. The system is based on a combination of self-supervised learning (SSL) models and listener-dependent modeling. Due to this challenge’s emphasis on real-world and challenging zero-shot out-of-domain MOS prediction in three different voice evaluation scenarios, we specifically designed a two-branch module to predict scores and weights for each frame, aiming to achieve better generalization. In the challenge, our system achieved fourth place in Track 1a, second place in Track 1b and first place in Track 2. Additionally, we conducted an ablation study to investigate the effectiveness of our proposed method.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Distill Vision Transformers to CNNs via Teacher Collaboration

Distill Vision Transformers to CNNs via Teacher Collaboratio...

引用

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

作者： Sunqi Lin Chong Wang Yujie Zheng Chenchen Tao Xinmiao Dai Yuqi Li Faculty of Electrical Engineering and Computer Science Ningbo University China Zhejiang Engineering Research Center of Advcanced Mass Spectrometry and Clinical Application China

The vision transformer (ViT) has recently emerged as a leading approach in various domains, outperforming other methods. Therefore, it is logical to explore the possibility of transferring the superior knowledge from ViT to more compact and cost-effective convolutional neural networks (CNNs). However, due to substantial architectural disparities in representation and logits between these models, conventional knowledge distillation methods have proven ineffective in this context. To address this issue, a novel cross-architecture knowledge distillation scheme based on teacher collaboration is proposed to alleviate the architecture gap. Two different teachers, i.e. one ViT and one CNN, are utilized to simultaneously distill the student by feature reaggregation and logit correction. The experiments show that the proposed scheme outperforms conventional methods on CIFAR-100 dataset. The code is available at https://***/SunkiLin/RCD.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Intrusion Detection Based on Deep Belief Network and Stacking Method 3

Intrusion Detection Based on Deep Belief Network and Stackin...

引用

3rd International Conference on computer Communication and Network Security, CCNS 2022

作者： Wang, Jia Bao Miao, Xiang Hua Li, Xiang Faculty of Information Engineering and Automation Kunming University of Science and Technology Yunnan Kunming650500 China Yunnan Key Laboratory of Computer Technology Application Kunming University of Science and Technology Yunnan Kunming650500 China

ISBN: (纸本)9781510660113

After data preprocessing, the feature dimension of NSL-KDD dataset increases from 42 dimensions to 122 dimensions. High dimensional data will make it more difficult for the model to learn the characteristics of the data, and there will be a lot of redundant data in the data set. Therefore, this paper uses the deep belief network to reduce the dimension of the characteristics of the intrusion detection data set after data preprocessing, and uses the stacking algorithm as the classifier to construct the intrusion detection model. Through comparative experiments, it is proved that the model has good performance in the four evaluation indexes of accuracy, precision, recall and F1 score, and effectively improves the performance of intrusion detection model. © 2022 SPIE.

关键词： Intrusion detection

来源：评论

学校读者我要写书评

暂无评论

The present situation and shifts observed in wetlands within the *** Seaway region of Canada,utilizing imagery from the Landsat archive and the cloud-based platform Google Earth Engine

引用

Big Earth Data 2025年第1期9卷 47-71页

作者： Meisam Amani Mohammad Kakooei Rebecca Warren Sahel Mahdavi Kevin Murnaghan Arsalan Ghorbanian Amin Naboureh Digital Environmental Group WSP Canada Inc.OttawaONCanada Department of Computer Science Chalmers University of TechnologyGothenburgSweden Digital Environmental Group WSP Canada Inc.EdmontonABCanada dIndependent Researcher Department of Photogrammetry and Remote Sensing Faculty of Geodesy and Geomatics EngineeringK.N.Toosi University of TechnologyTehranIran Research Center for Digital Mountain and Remote Sensing Application Institute of Mountain Hazards and EnvironmentChinese Academy of SciencesChengduChina

This study examined wetland trends in the *** Seaway(~500,000 km^(2))in Canada over the past four *** this end,historical Landsat data within the Google Earth Engine(GEE)big geo data platform were *** samples were scrutinized using the Continuous Change Detection and Classification(CCDC)algorithm to identify spectrally unchanged *** spectrally unchanged samples were subsequently employed as training data within an object-based Random Forest(RF)model to generate wetland maps from 1984 to ***,a change analysis was conducted to calculate the loss and gain of different wetland ***,it was observed that approximately 45%(184,434 km^(2))and 55%(220,778 km^(2))of the entire study area are covered by wetland and non-wetland categories,*** was also observed that 2.46%(12,495 km^(2))of the study area was changed during 40 ***,there was a decline in the Bog and Fen classes,while the Marsh,Swamp,Forest,Grassland/Shrubland,Cropland,and Barren classes had an ***,the wetland gain and loss were 6,793 km^(2)and 5,701 km^(2),*** study demonstrated that the use of Landsat data,along with advanced machine learning and GEE,could provide valuable assistance for wetland classification and change studies.

关键词： Remote sensing Google Earth Engine(GEE) cloud computing satellite change detection continuous change detection and classification(CCDC) wetlands

来源：评论

学校读者我要写书评

暂无评论

Software Requirement Ambiguity Avoidance Framework (SRAAF) for Selecting Suitable Requirement Elicitation Techniques for Software Projects

Software Requirement Ambiguity Avoidance Framework (SRAAF) f...

引用

2022 IEEE International Conference on Current Development in Engineering and Technology, CCET 2022

作者： Gupta, Ashok Kumar Siddiqui, Shams Tabrez Qidwai, Khalid Ali Haider, Agha Salman Khan, Haneef Ahmad, Md Oqail Universiti Malaysia Terengganu Faculty of Science and Technology Kuala Terengganu Malaysia Jazan University Department of Computer Science Jazan Saudi Arabia Jazan University Department of Computer and Network Engineering Jazan Saudi Arabia B.S Abdur Rahman Crescent Institute of Science and Technology Department of Computer Application Tamil Nadu India

ISBN: (纸本)9781665454155

Ambiguity is an intrinsic deficiency of natural language written requirement documents. Requirement Engineers face difficulties while communicating with stakeholders from different backgrounds and knowledge to extract requirements. The selection of a suitable requirement elicitation technique plays a critical role to improve the quality of elicited requirements. Differences among elicitation techniques are very large;it implies that some techniques may perform better than others for a particular situation. Generally, requirement engineers select elicitation techniques based on their interests, knowledge, and experience. The selection of the right technique is critical as all techniques can not fit into different situations. In addition, before starting the new project, there is no software available that can help in selecting suitable elicitation techniques based on the situation. This paper proposed a software-based selection of suitable elicitation techniques used in SRAAF (Software Requirement Ambiguity Avoidance Framework). The tool focuses on the first phase of SRAAF, specifically the situational parameter based selection of effective elicitation techniques. These situational parameters are mapped onto the knowledge base for the selection process. The tool takes situational parameters as input related to three categories: project, requirement engineer, and stakeholders. The tool suggests a technique based on situational parameters under the current settings. If any new evidence related to situational parameters, elicitation technique or contextual value is originated, these values or information can be easily included in the tool. © 2022 IEEE.

关键词： Engineers

来源：评论

学校读者我要写书评

暂无评论

A multi-view comparative learning method for spatial transcriptomics data clustering

A multi-view comparative learning method for spatial transcr...

引用

2023 IEEE International Conference on Bioinformatics and Biomedicine, BIBM 2023

作者： Peng, Wei Zhang, Zhihao Dai, Wei Fu, Xiaodong Liu, Li Liu, Lijun Yu, Ning Kunming University of Science and Technology Faculty of Information Engineering and Automation Kunming China Kunming University of Science and Technology Computer Technology Application Key Lab of Yunnan Province Kunming China State University of New York The College at Brockport Department of Computing Sciences BrockportNY14422 United States

ISBN: (纸本)9798350337488

Clustering individual cells or spots based on their gene expression profiles in a spatial context is a powerful approach to uncovering the underlying biological diversity and relationships among cells. The intricate information within spatial transcriptomics data demands sophisticated algorithms that effectively integrate gene expression, cell position, and tissue image data for accurate cell or spot clustering. This work proposes a Multi-View Comparative Learning method for clustering Spatial Transcriptomics data (MVCLST). MVCLST first builds on two data views using gene expression profiles, cell space coordinates, and image features. Then it employs four different encoders to capture the common and private features of the two views. The model employs a contrastive learning loss to encourage effective interaction between the two views and ensure feature consistency. The shared and private features from both views are fused using corresponding decoders. Finally, the model employs the Leiden algorithm for downstream clustering of the learned features. We test the MVCLST method on a human dorsolateral prefrontal cortex dataset. The results show that MVCLST outperforms other state-of-the-art methods in most cases. Additionally, the clusters identified by MVCLST align closely with manual annotations and established neuroscience definitions. © 2023 IEEE.

关键词： contrast learning multiview learning spatial transcriptome data clustering

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：