检索结果-内蒙古大学图书馆

Brazilian Conference on Intelligent Systems (BRACIS)

作者： Fabiano Berardo de Sousa Liang Zhao Inst. of Math. & Comput. Sci. Universidade de Sao Paulo Sao Paulo SÃ£o Paulo BR School of Philosophy Sciences and Literatures University of São Paulo Ribeirão Preto SP Brazil

Complex networks became a very important tool in machine learning field, helping researchers to investigate and mine data. They can model real dynamic networks, aiding to unveil information's about the systems they model. Communities are notable groups that may exist in a complex network and the community detection problem is the focus of attention of many researchers. The igraph library implements a good set of community detection algorithms, allowing researchers to easily apply them to data mining tasks. But each algorithm uses a different approach, leading to different performances. In this paper, the community detection algorithms implemented in the igraph library are investigated and ranked according to their performances in a set of different scenarios. Results show walktrap and multi-level got the highest scores while leading eigenvector and spinglass got the lowest ones. These findings are an important contribution for aiding researchers to select or discard algorithms in their own experiments using igraph library.

关键词： Communities Mathematical model Libraries Equations Graphics Algorithm design and analysis detection algorithms

来源：评论

学校读者我要写书评

暂无评论

High-knowledge shilling attack detection method based on genetic co-forest

High-knowledge shilling attack detection method based on gen...

引用

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

作者： Lingvue Su Yongli Wang School of Computer Science and Engineering Nanjing University of Science and Technology Nanjing China

ISBN: (数字)9798350381993

ISBN: (纸本)9798350382006

Shilling attack is the behavior of malicious users to elevate or suppress ratings in collaborative filtering recommendation system, which can destroy the balance of recommendation and disrupt the order of competition. In previous studies, shilling attack detection techniques can be divided into three categories according to the labeling scale of samples: supervised, semi-supervised and unsupervised methods. The semi-supervised method is better at using a small number of labeled samples and a large number of unlabeled samples to improve the detection efficiency. However, in practice, it is found that the existing semi-supervised methods perform poorly in the face of high-knowledge shilling attacks such as PUA and PIA, and the generalization ability is significantly reduced when the proportion of labeled data becomes smaller. Therefore, this paper proposes a semi-supervised detection method GA-CoF. Different from the existing divergent semi-supervisors, the proposed method regards the solution set of unlabeled samples as gene sequences, the error rate as the fitness function, and the aggregation degree as the penalty term. In the experiments, we extract the user behavior characteristics of standard shilling attacks, and compare our method with four representative shilling attack detection algorithms on two datasets, MovieLens-25M and Amazon-5Cores. The results show that our method can maintain high F1 score and is not sensitive to the attack scale when facing high-knowledge shilling attacks, and performs well on real datasets. The proposed method has good module plugging ability and expansion prospects.

关键词： Privacy Error analysis Collaborative filtering Genetics Security Labeling detection algorithms

来源：评论

学校读者我要写书评

暂无评论

An Overlapping Community detection Algorithm for Label Propagation Based on Node Influence 3

An Overlapping Community Detection Algorithm for Label Propa...

引用

2021年第三届先进计算机技术、信息科学与通信国际会议(CTISC2021)

作者： QI LIU YAOFENG SU QICHAO PENG KEBIN CHEN YUNJUN LU College of Information and Communication National University of Defense Technology

ISBN: (纸本)9781665418683

LPA algorithm is an effective community detection algorithm. based on the original algorithm, a new algorithm based on node importance, similarity between nodes, influence of adjacent nodes and label propagation strategy is proposed in view of the randomness and instability of overlapping community detection in LPA algorithm. First, the importance of nodes, the similarity between nodes, the influence of adjacent nodes are calculated, and the label set of nodes is generated according to the calculation results. Through the label update strategy, the attribution coefficient of each node to the community is calculated, and the updated label set is iterated continuously. The results show that the algorithm has near linear time complexity and can effectively improve the accuracy and stability of large-scale overlapping community detection.

关键词： Information science Complex networks detection algorithms Time complexity

来源：评论

学校读者我要写书评

暂无评论

IMDoC: Identification of Malicious Domain Campaigns via DNS and Communicating Files

引用

IEEE ACCESS 2021年 9卷 45242-45258页

作者： Lazar, David Cohen, Kobi Freund, Alon Bartik, Avishay Ron, Aviv Ben Gurion Univ Negev Dept Comp Sci IL-8410501 Beer Sheva Israel Ben Gurion Univ Negev Sch Elect & Comp Engn IL-8410501 Beer Sheva Israel IBM Cyber Secur Ctr Excellence IL-8489325 Beer Sheva Israel

Cyber attacks have become more sophisticated and frequent over the years. Detecting the components operated during a cyber attack and relating them to a specific threat actor is one of the main challenges facing cyber security systems. Reliable detection of malicious components and identification of the threat actor is imperative to mitigate security issues by Security Operations Center (SOC) analysts. The Domain Name System (DNS) plays a significant role in most cyber attacks observed nowadays in that domains act as a Command and Control (C&C) in coordinated bot network attacks or impersonate legitimate websites in phishing attacks. Thus, DNS analysis has become a popular tool for malicious domain identification. In this collaborative research associating Ben-Gurion University and IBM, we develop a novel algorithm to detect malicious domains and relate them to a specific malware campaign in a large-scale real-data DNS traffic environment, dubbed Identification of Malicious Domain Campaigns (IMDoC) algorithm. Its novelty resides in developing a framework that combines the existence of communicating files for the observed domains and their DNS request patterns in a real production environment. The analysis was conducted on real data from Quad9 (9.9.9.9) DNS recursive resolvers combined with malicious communicating files extracted from VirusTotal, and confirms the strong performance of the algorithm on a real large-scale data production environment.

关键词： Malware Servers IP networks Security Production Prediction algorithms Reliability Cyber security domain name system (DNS) clustering methods detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Deep learning model for speech emotion classification based on GCI and GOI detection

Deep learning model for speech emotion classification based ...

引用

Emerging Trends in Industry 4.0 (ETI 4.0)

作者： Omkar Vernekar S.R. Nirmala Kavita Chachadi KLE Technological University Hubballi India

The temporal regions of considerable stimulation to the vocal tract during the production of spoken speech are referred to as glottal closure instants (GCIs) and glottal opening instants (GOIs). These instants from speech signals are important for various speech and biomedical applications. The performance of the GCI and GOI detection algorithm is not studied for emotion speech using deep learning technique. Hence, the motivation behind this work is to use the current edge technology. To the best of our knowledge ours is the first deep learning CNN model to classify different emotions of speech based on GCI and GOI. In this work, an attempt is made to study the performance for different emotions using GCI and GOI detection algorithm and make the comparison with the state of art methods. The performance of the developed model is evaluated using traditional evaluation metrics. The results show that GCIs and GOIs are helpful in classification of speech emotion and that performance of the proposed model decreases for anger and sad emotions.

关键词： Deep learning Measurement Art Image edge detection Biological system modeling Production detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Towards De-Anonymization of Google Play Search Rank Fraud

引用

IEEE TRANSACTIONS ON KNOWLEDGE AND DATA ENGINEERING 2021年第11期33卷 3648-3661页

作者： Rahman, Mizanur Hernandez, Nestor Carbunar, Bogdan Chau, Duen Horng Florida Int Univ Miami FL 33199 USA Florida Int Univ SCIS Miami FL 33199 USA Georgia Tech Atlanta GA 30332 USA

Search rank fraud, the fraudulent promotion of products hosted on peer-review sites, is driven by expert workers recruited online, often from crowdsourcing sites. In this paper we introduce the fraud de-anonymization problem, that goes beyond fraud detection, to unmask the human masterminds responsible for posting search rank fraud in peer-review sites. We collect and study data from crowdsourced search rank fraud jobs, and survey the capabilities and behaviors of 58 search rank fraud workers recruited from 6 crowdsourcing sites. We collect a gold standard dataset of Google Play user accounts attributed to 23 crowdsourced workers and analyze their fraudulent behaviors in the wild. We propose Dolos, a fraud de-anonymization system that leverages traits and behaviors we extract from our studies, to attribute detected fraud to crowdsourcing site workers, thus to real identities and bank accounts. We introduce MCDense, a min-cut dense component detection algorithm to uncover groups of user accounts controlled by different workers, and use stylometry and supervised learning to attribute them to crowdsourcing site profiles. Dolos correctly identified the owners of 95 percent of fraud worker-controlled communities, and uncovered fraud workers who promoted as many as 97.5 percent of fraud apps we collected from Google Play. When evaluated on 13,087 apps (820,760 reviews), which we monitored over more than 6 months, Dolos identified 1,056 apps with suspicious reviewer groups. We report orthogonal evidence of their fraud, including fraud duplicates and fraud re-posts. Dolos significantly outperformed adapted dense subgraph detection and loopy belief propagation competitors, on two new coverage scores that measure the quality of detected community partitions.

关键词： Crowdsourcing Google Standards Search problems Gold detection algorithms Supervised learning Search rank fraud peer-review system

来源：评论

学校读者我要写书评

暂无评论

Efficient Correlation Power Analysis (CPA) Focusing on Byte-Wise Calculation Points

引用

IEEE ACCESS 2021年 9卷 74275-74285页

作者： Jeon, Youngbae Jung, Ji Hyuk Yoon, Ji Won Korea Univ Sch Cybersecur Seoul 02841 South Korea

Correlation Power Analysis (CPA) uses a lot of computational resources for deploying side-channel analysis to power traces. For every guessing key, it searches all data points and all power traces to reveal the secret key implemented in the encryption module. In this work, we propose a novel technique to narrow down the target region for applying CPA to the power traces. As byte-wise operations occur in every clock period, the assumed amplitude value based on the power consumption model and the actual amplitude are most correlated at the points where the peaks are observed. We extract the calculation points of each power trace using signal processing and machine learning techniques, and select the region where the CPA will be applied to. Our proposed approach achieves an approximately 20% improvement in accuracy and requires less computational resources compared to conventional CPA.

关键词： Clocks Power demand Correlation Encryption Power measurement Time complexity detection algorithms Side-channel analysis correlation power analysis simple power analysis peak detection k-means algorithm AES

来源：评论

学校读者我要写书评

暂无评论

Design and Implementation of Mask detection System Based on Improved YOLOv5s

Design and Implementation of Mask Detection System Based on ...

引用

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

作者： Changyu Zhao Zhuo Yan Huangxin Xu Xueliang Chen Zheng Li Xinyu Zhong Cuiwei Liu Anyan Xiao Xingyan Lv School of Artificial Intelligence Shenyang Aerospace University Shenyang China School of Computer Science Shenyang Aerospace University Shenyang China

ISBN: (数字)9798350381993

ISBN: (纸本)9798350382006

In this paper, we propose a lightweight mask detection algorithm and implement an intelligent vehicle system. The algorithm uses YOLOv5s as the backbone network, and at the same time incorporates the SE attention mechanism to optimize the timeliness, and is finally deployed on an intelligent vehicle system with BCM2711 as the control platform. Experiments prove that the algorithm proposed in this paper reduces the detection time by 30% while ensuring a higher MAP, which has certain value for promotion.

关键词： YOLO Privacy Intelligent vehicles Real-time systems Security Task analysis detection algorithms

来源：评论

学校读者我要写书评

暂无评论

Rhythm-based accuracy improvement of heart beat detection algorithms

Rhythm-based accuracy improvement of heart beat detection al...

引用

Computers in Cardiology (CinC)

作者： Zoltán Gilián Péter Kovács Kaveh Samiee Department of Numerical Analysis Eötvös Loránd University Budapest Hungary Department of Signal Processing Tampere University of Technology Tampere Finland

Aims: Our aim is to improve the accuracy of existing heart beat detection algorithms in order to provide reliable heart beat locations in a multi-modal beat detection scheme. Methods: A rhythm-based algorithm is presented which on top of a base beat detection method processes the detected beats by rejecting annotations and filling in gaps while minimizing a deviation score. A novel beat detection method based on rational modelling of ECG signals is also presented as a base algorithm. Results: The rhythm-correction algorithm applied to Sachin Vernekar's phase 11 entry was submitted to the third phase of the PhysioNet/CinC Challenge 2014 contest. The algorithm has 99.98% gross and average sensitivity and 99.96% gross and average positive predictivity compared to 99.92% and 99.94%, respectively, of the base algorithm. Due to run-time performance problems, the rational algorithm was not able to qualifY in the contest. Conclusions: The rhythm-based method improves the results of the base algorithm on the training data set. The hidden records are not yet available at the time of writing of this paper; therefore we are not able to report the final performance of the algorithm. Run-time improvement of the rational algorithm remains future work.

关键词： Abstracts detection algorithms Reliability Prediction algorithms Heart beat Noise measurement

来源：评论

学校读者我要写书评

暂无评论

Improved blood cell detection method based on YOLOv5 algorithm

Improved blood cell detection method based on YOLOv5 algorit...

引用

IEEE Information Technology, Networking, Electronic and Automation Control Conference

作者： Meigen Huang Binjie Wang Jiangcheng Wan Cheng Zhou College of Computer Chongqing University of Posts and Telecommunications Chongqing China Laboratory of Broadband Network Innovation Chongqing China

The proposed blood cell target detection algorithm based on YOLOv5 addresses the issue of low average accuracy and serious miss detection due to small blood cells and serious cell adhesion in blood cell detection by target detection algorithms. By adding the CBAM (Convolutional Block Attention Module) to the YOLOv5 framework's backbone network and the BIFPN (bidirectional feature pyramid network) to the neck network, the algorithm improves the model's ability to extract features. The experimental results show that the average accuracy (mAP) of the improved YOLOv5 blood cell target detection algorithm is 89.9%, representing a increase over the native YOLOv5s type, and the recall rate and accuracy rate are also increased by 3.2% and 4.2%, respectively. This meets the requirements of the actual scene for blood cell detection.

关键词： Automation Adhesives Object detection Feature extraction Neck detection algorithms Blood

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：