检索结果-内蒙古大学图书馆

2024 International Conference on Advanced Technologies for Communications, ATC 2024

作者： Vu-Thanh, Trung He, Jing Duong-Bao, Ninh Lee, Seon-Woo Thi, Luong Nguyen Nguyen-Huu, Khanh College of Computer Science and Electronic Engineering Hunan University Changsha China Dalat University Faculty of Mathematics and Informatics Dalat Viet Nam Hallym University Division of Software Chuncheon Korea Republic of Dalat University Faculty of Information Technology Dalat Viet Nam Dalat University Department of Electronics and Telecommunications Dalat Viet Nam

ISBN: (纸本)9798350353983

Using WiFi Fingerprinting for indoor positioning is becoming increasingly popular due to its cost-effectiveness. However, to ensure the system can operate with high accuracy and stability, this technique requires a burden of data collection tasks from a dense distribution of reference points (RPs). To decrease the cost of data collection, as well as to improve the WiFi fingerprint database with irregular distribution of RPs, this study applies and compares different interpolation methods. Evaluating these methods in a public dataset including multiple sub-datasets with irregular distributions of RPs, the results highlight the Linear Barycentric interpolation (LB) as the most favorable method due to its low complexity and stable performance. The LB-based fingerprint database achieves an average interpolation error of less than 3 dBm compared to the original one. When applying the interpolated database to positioning tasks, it can help reduce acquisition costs by up to 50% while improving positioning accuracy by up to 11%. The study reveals the feasibility of interpolation in optimizing WiFi fingerprint data collection, especially in large and complex environments where regular distribution of RPs cannot be deployed. © 2024 IEEE.

关键词： Interpolation

来源：评论

学校读者我要写书评

暂无评论

Feature Analysis and Selection for BGP Anomaly Detection

Feature Analysis and Selection for BGP Anomaly Detection

引用

International Conference on Intelligence in Next Generation Networks (ICIN)

作者： Rifqy Hakimi Martin J. Reed School of Computer Science and Electronic Engineering University of Essex Colchester United Kingdom School of Electrical Engineering and Informatics Bandung Institute of Technology Bandung Indonesia

ISBN: (数字)9798331542399

ISBN: (纸本)9798331542405

Automated incidence reporting requires accurate and timely anomaly detection. This paper considers this in the context of the Border Gateway Protocol (BGP). BGP is crucial for Internet routing but is vulnerable to attacks due to a lack of widespread authentication. While rare, BGP disruptions can be highly detrimental to Internet performance and security. Detecting BGP anomalies helps network operators protect their networks and improve Internet reliability. In this work, we investigate and develop anomaly detection for BGP using Machine-Learning. We extract relevant features of BGP control plane messages from RIPE RIS and RouteViews public datasets. After extracting features, we employ various feature selection algorithms to extract the most relevant features and explore balancing the datasets. Finally, we explore detection latency, an important operating parameter for automated anomaly detection. The results show that BGP anomalies can be detected in the order of seven minutes when using real attack data and that the observation point for the BGP data has a significant effect on anomaly detection.

关键词： Technological innovation Soft sensors Machine learning Feature extraction Routing Border Gateway Protocol Security Reliability Anomaly detection Faces

来源：评论

学校读者我要写书评

暂无评论

Multi Socket Network Transmission with Elliptic Curve Cryptography Encryption Algorithm 1

Multi Socket Network Transmission with Elliptic Curve Crypto...

引用

1st International Conference on technology, engineering, and Computing Applications, ICTECA 2023

作者： Kawet, Hetly Brinner Yusak Heikhmakhtiar, Aulia Rahardjo, Budi Mantoro, Teddy The Republic of Indonesia Defence University Sains and Defence Technology Faculty Bogor Indonesia Institut Teknologi Bandung School of Electrical Engineering and Informatics Bandung Indonesia Sampoerna University Media-Tech Lab Department of Computer Science Jakarta Indonesia

ISBN: (纸本)9798350360554

Information systems play a crucial role in facilitating effective and efficient media sharing by enabling the exchange of information. However, the current technological landscape is plagued by numerous potential attacks that can compromise the security of exchanged information. Examples of such attacks include stealing user data through interception of user-server communication, spoofing, and sniffing. Robust security measures are essential to mitigate the risks of data leakage and ensure data confidentiality during network-based information exchange. This study proposes designing a communication system based on a multi-socket network, employing the elliptic curve cryptography (ECC) encryption algorithm. The system comprises a single server and multiple clients. This paper analyzes the security of ECC from the performance comparison of ECC and RSA when implemented in multi sochet server. This work uses cryptography library implementation using C programming language. The utilization of the ECC encryption algorithm in network transmission ensures a high level of security and data confidentiality during information exchange. Furthermore, the data transmission system implemented with the ECC algorithm exhibits a swift computation time, thereby expediting key processing and message transmission while maintaining a strong level of security. © 2023 IEEE.

关键词： Geometry

来源：评论

学校读者我要写书评

暂无评论

Data Science System of Predicting and Detecting the Chikungunya Virus using Ensemble Techniques 4

Data Science System of Predicting and Detecting the Chikungu...

引用

4th International Conference on Inventive Research in Computing Applications, ICIRCA 2022

作者： Reddy, Bommireddy Vijay Kumar Patel, Shail Singh, Anayna Singh, Nishant Ranjit, Sasanapuri Dantkale, Shreyas National Institute of Technology Srinagar Department Computer Science and Engineering Jammu and Kashmir India Vellore Institute of Technology Department Computer Science and Engineering Vellore India Niit University Department Computer Science and Engineering Neemrana India University of Delhi Department of Institute of Informatics and Communication Delhi India Pes University Department of Electronics and Communication Engineering Bangalore India Vishwakarma Institute of Technology Department of Electronics and Communication Engineering Pune India

ISBN: (数字)9781665497077

ISBN: (纸本)9781665497077

The ailment known as chikungunya fever is brought on by a virus that mosquitoes disseminate. Due to the infection's excruciating joint and muscular discomfort, the term translates to 'bends you up' or 'stooped walk.' The abrupt onset of a high temperature, headache, exhaustion, rash, nausea, and red eyes are other symptoms. Chikungunya symptoms frequently show up 2 to 7 days after being bitten by an infected mosquito. There isn't a vaccination yet. Additionally, there is no cure for the illness. However, fatalities or major complications with chikungunya are uncommon. Many people recover in a matter of weeks. However, some people experience joint and muscular discomfort that can linger for months or even years after they have been exposed to the virus. After one to two weeks, a lot of people are free of further problems. Others, though, can experience joint and muscular discomfort for years. This kind of arthritis is known as chronic chikungunya. At least 40persons who contract the virus are affected. Chikungunya is seldom fatal. But for certain people, the infection can lead to serious issues. Older persons, those with chronic illnesses like diabetes or high blood pressure, small children, and pregnant women who could pass the virus to their unborn children are at increased risk. Serious issues with the eyes, heart, and nerves can be complications. Once-infected individuals are likely to be resistant to subsequent infections. The main aim of the authors is to use the ensemble technqiue to find a novel approach and to compare the ensemble techniques. © 2022 IEEE.

关键词： Viruses

来源：评论

学校读者我要写书评

暂无评论

Tamper-Tolerant Diagnosability Under Bounded or Unbounded Attacks

引用

IFAC-PapersOnLine 2022年第28期55卷 52-57页

作者： Yuting Li Christoforos N. Hadjicostis Naiqi Wu Institute of Systems Engineering Macau University of Science and Technology Taipa 999078 Macau SAR China Department of Electrical and Computer Engineering University of Cyprus Nicosia 1678 Cyprus

This paper discusses fault diagnosis and diagnosability analysis in discrete-event systems modeled with nondeterministic finite automata, partially observed via a sensor measuring unit whose measurements (reported observations) may be vitiated by a malicious attacker. The attacks considered in this paper include arbitrary deletions, insertions, or substitutions of observed symbols. Assuming that each deletion, insertion, or substitution bears a positive cost to the attacker, two scenarios are taken into account: (1) a bounded number of attacks or, more generally, a total cost constraint on tampering actions; (2) an infinite number of attacks or, more generally, no constraints on the total cost of tampering actions. Several examples are presented to demonstrate the influence of cost constraints on tamper-tolerant diagnosis and tamper-tolerant system diagnosability.

关键词： Discrete-event system Fault diagnosis False information Data tampering Cost constraint

来源：评论

学校读者我要写书评

暂无评论

Dynamics of hot random hyperbolic graphs

arXiv

引用

arXiv 2021年

作者： Papadopoulos, Fragkiskos Zambirinis, Sofoclis Department of Electrical Engineering Computer Engineering and Informatics Cyprus University of Technology Limassol3036 Cyprus

We derive the most basic dynamical properties of random hyperbolic graphs (the distributions of contact and intercontact durations) in the hot regime (network temperature T > 1). We show that in the thermodynamic limit the contact distribution decays as a power law with exponent 2+T > 3 for durations t > T, while for t thmoment. Otherwise, the contact distribution depends on the expected degree distribution and we show that if the latter is a power law with exponent γ ∈ (2, T+1], then the former decays as a power law with exponent γ+1 > 3. On the other hand, the intercontact distribution exhibits power-law decays with exponent 2-T ∈ (0, 1) for T ∈ (1,2), while for T > 2 it displays linear decays with a slope that depends on the observation interval. This result holds irrespective of the expected degree distribution as long as it has a finite Tthmoment if T ∈ (1,2), or a finite second moment if T > 2. Otherwise, the intercontact distribution depends on the expected degree distribution and if the latter is a power law with exponent γ ∈ (2, 3), then the former decays as a power law with exponent 3-γ ∈ (0,1). Thus, hot random hyperbolic graphs can give rise to contact and intercontact distributions that both decay as power laws. These power laws however are unrealistic for the case of the intercontact distribution, as their exponent is always less than one. These results suggest that hot random hyperbolic graphs are not adequate null models for real temporal networks, in stark contrast to cold random hyperbolic graphs (T Copyright © 2021, The Authors. All rights reserved.

关键词： Graphic methods

来源：评论

学校读者我要写书评

暂无评论

Late Breaking Results: Weight Decay is All You Need for Neural Network Sparsification 23

Late Breaking Results: Weight Decay is All You Need for Neur...

引用

Proceedings of the 60th Annual ACM/IEEE Design Automation Conference

作者： Xizi Chen Rui Pan Xiaomeng Wang Fengshi Tian Chi-Ying Tsui College of Informatics Huazhong Agricultural University China Department of Electronic and Computer Engineering The Hong Kong University of Science and Technology Hong Kong China

ISBN: (纸本)9798350323481

The heuristic iterative pruning strategy has been widely used for neural network sparsification. However, it is challenging to identify the right connections to remove at each pruning iteration with only a one-shot evaluation of weight magnitude, especially at the early pruning stage. The erroneously removed connections, unfortunately, can hardly be recovered. In this work, we propose a weight decay strategy as a substitute for pruning, which let the "insignificant" weights moderately decay instead of being directly clamped to zero. At the end of the training, the vast majority of redundant weights will naturally become close to zero, making it easier to identify which connections could be removed safely. Experimental results show that the proposed weight decay method can achieve an ultra-high sparsity of 99%. Compared to the current pruning strategy, the model size is further reduced by 34%, improving the compression rate from 69× to 106× at the same accuracy.

关键词： DNN

来源：评论

学校读者我要写书评

暂无评论

Transformer-Based Embeddings for Greek Language Categorization

Transformer-Based Embeddings for Greek Language Categorizati...

引用

International Conference on computer and Information Science (ACIS)

作者： Charalampos M. Liapis Konstantinos Kyritsis Isidoros Perikos Michael Paraskevas Mathematics Dept. University of Patras Computer Technology Institute & Press “Diophantus” Patras Greece Electrical and Computer Engineering Dept. University of Peloponnese Patras Greece Computer Engineering and Informatics Department Electrical and Computer Engineering Dept. University of Patras University of Peloponnese Computer Technology Institute and Press “Diophantus” Patras Greece Electrical and Computer Engineering Dept. University of Peloponnese Computer Technology Institute and Press “Diophantus” Patras Greece

ISBN: (数字)9798350376647

ISBN: (纸本)9798350376654

The Greek School Network (GSN) provides support to students, teachers, and school units in secondary education across Greece. Handling numerous user queries manually can be challenging, necessitating the development of an automated system for accurate categorization of these queries. This paper presents a comparative study of various transformer-based models for multi-class text categorization of Greek language queries submitted to the GSN helpdesk. We introduce a new experimental balanced dataset and extract vector representations from eleven transformer-based models. These representations are evaluated using ten classic machine learning classifiers. Our findings highlight the superior performance of the Multilingual E5 Text Embeddings model, particularly when paired with the extreme gradient-boosting classifier. This combination demonstrates a clear advantage in accurately categorizing user queries, paving the way for more efficient automated helpdesk systems.

关键词： Information science Accuracy Computational modeling Text categorization Education Machine learning Transformers Vectors

来源：评论

学校读者我要写书评

暂无评论

Vehicle type recognition based on audio data 58

Vehicle type recognition based on audio data

引用

58th Hawaii International Conference on System Sciences, HICSS 2025

作者： Kobiela, Dariusz Hajdasz, Michal Erezman, Mateusz Nurzyńska, Karolina Zaporowski, Szymon Kurowski, Adam Weichbroth, Pawel Department of Software Engineering Faculty of Electronics Telecommunication and Informatics Gdańsk University of Technology Gabriela Narutowicza 11/12 Gdańsk80-233 Poland Department of Multimedia Systems Faculty of Electronics Telecommunication and Informatics Gdańsk University of Technology Gabriela Narutowicza 11/12 Gdańsk80-233 Poland Department of Algorithmics and Software Faculty of Automatic Control Electronics and Computer Science Silesian University of Technology Akademicka 16 Gliwice44-100 Poland

ISBN: (纸本)9780998133188

Identifying different vehicle types can help manage traffic more efficiently, reduce congestion, and improve public safety. This study aims to create a classification model that can recognize vehicle types based on the sound of passing vehicles. To achieve this, a database of raw audio files containing 1763 samples from two sources was assembled. The time-domain signals were converted to a time-frequency representation using the short-time Fourier transform to generate Mel Spectrograms. Mel-frequency Cepstral Coefficients (MFCCs) were also generated using the discrete cosine transform. In our experiments we compared these approaches. Since the data was imbalanced we applied online augmentation. Based on the literature review, we chose a Convolutional Neural Network (CNN) classifier because it is particularly well suited for analyzing large datasets due to its automatic feature extraction, parameter sharing and sparsity. The results showed that Mel Spectrograms were more effective for audio data preprocessing in this particular use case, achieving the highest accuracy of 0.875 and the highest f1-score of 0.877 compared to MFCCs. © 2025 IEEE computer Society. All rights reserved.

关键词： Image coding

来源：评论

学校读者我要写书评

暂无评论

Fast Mapping of Flexibility Regions at TSO-DSO Interfaces under Uncertainty

arXiv

引用

arXiv 2022年

作者： Patig, Alice Stanojev, Ognjen Aristidou, Petros Kiprakis, Aristides Hug, Gabriela Eeh - Power Systems Laboratory Eth Zurich Switzerland Department of Electrical Engineering Computer Engineering and Informatics Cyprus University of Technology Cyprus Institute for Energy Systems School of Engineering University of Edinburgh United Kingdom

The gradual decommissioning of fossil fuel-driven power plants, that traditionally provide most operational flexibility in power systems, has led to more frequent grid stability issues. To compensate for the lack of flexible resources, Distributed Energy Resources (DERs) in distribution networks can be employed. To facilitate the use of DERs, the aggregated flexibility in a distribution grid is commonly represented on a PQ-plane displaying the feasible active and reactive power exchange with the upstream grid. This paper proposes a fast feasible operating region mapping mechanism that utilizes a linear power flow approximation in combination with linearized generator, current, and voltage constraints to construct a high-dimensional polyhedral feasible set of DER power injections. The obtained polytope is projected onto the PQ-plane using Fourier-Motzkin Elimination to represent the aggregate network flexibility. Additionally, uncertainty in DER generation is addressed using chance-constraints. Our analysis of a modified 33-bus IEEE test system demonstrates that the proposed method obtains more accurate approximations than former geometric methods and is ten times faster than the tested optimization-based method. Copyright © 2022, The Authors. All rights reserved.

关键词： Electric load flow

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：