检索结果-内蒙古大学图书馆

Workshops of the 11th EETN Conference on Artificial Intelligence, SETN 2020 Workshops

作者： Evangelou, Sotirios Akasiadis, Charilaos Dept. of Electrical and Computer Engineering University of Thessaly Greece Institute of Informatics and Telecommunications N.C.S.R. 'Demokritos' Greece

The Internet of Things (IoT) and "Smart Everything" trend is a reality that is becoming part of our daily lives. Consequently, there is a gradual increase in the deployment of real world IoT systems that attempt to make use of the various possibilities and benefits the IoT offers. However, the connection of billions of-usually inherently insecure-devices in a network, paired with the lack of a clear security framework for the development of IoT systems and platforms has widened the attack surface of these systems leading to them being targeted by malicious actors. In this paper, we explore the problem and related research, devise an assets taxonomy and focus on the security requirements for each asset category. Then, we discuss countermeasures and good practices as well as new approaches based on AI that improve security and intrusion detection capabilities. We also introduce a metric that can be incorporated by automated security auditing methods. The relevance of this metric is evaluated with respect to correlation across findings from a real-world study. Copyright © 2020 for this paper by its authors. Use permitted under Creative Commons License Attribution 4.0 International (CC BY 4.0).

关键词： Internet of things

来源：评论

学校读者我要写书评

暂无评论

A Web and Mobile Application to Identify the Availability of Drinking Water Information During a Water Crisis

A Web and Mobile Application to Identify the Availability of...

引用

Intelligent Computing and Control for engineering and Business Systems (ICCEBS)

作者： Suhail Razeeth Fathima Shihara Kasuni Pavithra Maran Kaliyamoorthy Samsudeen Sabraz Nawaz Rkar Kariyapper Dept. of Information and Communication Technology South Eastern University of Sri Lanka Sri Lanka Dept. of Computer Science and Informatics Uva Wellassa University of Sri Lanka Sri Lanka Sri Sai Ram Institute of Management Studies Sri Sai Ram Engineering College India Department of Management and Information Technology South Eastern University of Sri Lanka Sri Lanka

Sri Lanka faces drinking water related issues often due to many reasons like weather changes, floods, droughts, and tsunamis, affecting the drinking water availability. In such instances, people find difficult to gather information regarding consumable drinking water availability. In order to facilitate the meeting of commercial water sellers and customers and to engage the general public and social services in addressing the drinking water problem, this study is focused on building both web and mobile applications. The web application was implemented with a selected set of functionalities such as social login, social sharing, geocoding, reverse geocoding, viewing, and filtering posts using Angular 6, *** web framework, and Leaflet. The mobile application was developed to direct the customers to the water availability location with a shortest path using the Dijkstra's algorithm. Case evaluation was conducted with the Rotaract Club members in Badulla and thinking aloud method was used to pick up the user's ideas while interacting with the system. It can be concluded that the created web and mobile applications would offer the public a clever way to draw attention to an issue with water availability, and the commercial water service providers are given a venue to market their services and locate potential customers.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Clustering Based User Allocation in 5G Networks*

Clustering Based User Allocation in 5G Networks*

引用

International Symposium on Networks, computers and Communications (ISNCC)

作者： Christos Bouras Rafail Kalogeropoulos Ioannis Sina Computer Technology Institute & Press “Diophantus201D Univ. of Patras Greece Patras Greece Computer Engineering and Informatics Dept.

Machine learning is an extremely efficient technique for solving complex problems without the use of traditional programming but rather enabling machines to learn from an input of data and train them to cope with various problems. The rapid growth in the number of active mobile devices, mobile applications and services dictates an efficient utilization of mobile and wireless networking infrastructure. Communication networks need to evolve and valorize machine learning methods in order to process large volumes of data without introducing excessive time delay in these computations. Upcoming 5G systems are expected to be the first network infrastructure to support exploding mobile traffic volumes and machine learning techniques can be used in order to help manage the rise in data volumes. We present a mechanism for resource allocation in mobile and wireless networks, that effectively utilizes machine learning techniques.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Refinement of an Epilepsy Dictionary through Human Annotation of Health-related posts on Instagram

arXiv

引用

arXiv 2024年

作者： Min, Aehong Wang, Xuan Correia, Rion Brattig Rozum, Jordan Miller, Wendy R. Rocha, Luis M. Donald Bren School of Information & Computer Sciences University of California IrvineCA United States Luddy School of Informatics Computing & Engineering Indiana University BloomingtonIN United States Instituto Gulbenkian de Ciência Oeiras Portugal Dept. of Systems Science & Industrial Engineering Binghamton University BinghamtonNY United States School of Nursing Indiana University IndianapolisIN United States

Objective — To (1) identify health-related terms used on social media posts that do not precisely match the health-related meaning of terms in a biomedical dictionary, (2) decide which terms need to be removed in order to improve the quality of the dictionary in the scope of biomedical text mining tasks, (3) evaluate the effect of removing imprecise terms on such tasks, and (4) discuss how human-centered annotation complements automated annotation in social media mining for biomedical purposes. Materials and Methods — We used a dictionary built from biomedical terminology extracted from various sources such as DrugBank, MedDRA, MedlinePlus, TCMGeneDIT, to tag more than 8 million Instagram posts by users who have mentioned an epilepsy-relevant drug at least once, between 2010 and early 2016. A random sample of 1,771 posts with 2,947 term matches was evaluated by human annotators to identify false-positives. Frequent terms with a high false-positive rate were removed from the dictionary. To study the effect of removing those terms, we constructed knowledge networks using the refined and the original dictionaries and performed an eigenvector-centrality analysis on both networks. OpenAI’s GPT series models were compared against human annotation. Results — Analysis of the estimated false-positive rates of the annotated terms revealed 8 ambiguous terms (plus synonyms) used in Instagram posts, which were removed from the original dictionary. We show that the refined dictionary thus produced leads to a significantly different rank of important terms, as measured by their eigenvector-centrality of the knowledge networks. Furthermore, the most important terms obtained after refinement are of greater medical relevance. In addition, we show that OpenAI’s GPT series models fare worse than human annotators in this task. Discussion — Dictionaries built from traditional clinical terminology are not tailored for social media language and can bias results when used in biomedical infe

关键词： Eigenvalues and eigenfunctions

来源：评论

学校读者我要写书评

暂无评论

Mutation types and pathogenicity classification using multi-label multi-class deep networks

引用

AIP Conference Proceedings 2024年第1期3097卷

作者： Rana H. Saloom Hussein K. Khafaji Informatics Institute Iraqi Commission for Computers and Informatics (ICCI) Baghdad Iraq Computer Communications Engineering Dept. Al-Rafidain University College Baghdad Iraq

In recent years, considerable progress has been made in genomics and proteomics, resulting in much biological data. To draw inferences from this data, advanced computer analysis techniques are required. Bioinformatics is crucial to interpreting and applying this data in any endeavor. As huge amounts of genomic, proteomic, and other data begin to be collected and integrated, the relevance of this emerging area of study will increase. The detection of variation in Next Generation Sequencing is now a standard and indispensable technique in all areas of the biological sciences. Life-threatening conditions like cancer and other diseases may be caused by DNA mutation sequences (genetic mutations). Thus, it’s important to discover these mutations early, classify them, and understand their effects on the DNA sequence. Bioinformatics is mostly concerned with the changes to DNA that will occur in the cells of the next generation. The primary goal of this research is to develop a sophisticated and comprehensive approach for classifying the mutation type and categorizing the influence of known disease-causing genetic variations on an individual’s risk of disease using a multi-label multi-class deep learning classification technique. A deep neural network was trained using the TP53 dataset (The TP53 gene is a tumor suppressor gene on chromosome 17) to discover the mutation type and its impact in a unified model, as described. To evaluate the performance of the suggested method, the accuracy, recall, precision, and F1 score evaluation scales were utilized. and the results demonstrate that it can accurately determine the mutation type and its effects with an accuracy of 97.58%, Precision 98%, Recall 95%, and F1 score 96%.

关键词：

来源：评论

学校读者我要写书评

暂无评论

Big Data against Security Threats: The SPEAR Intrusion Detection System 3

Big Data against Security Threats: The SPEAR Intrusion Detec...

引用

3rd World Symposium on Communication engineering, WSCE 2020

作者： Pliatsios, Dimitrios Sarigiannidis, Panagiotis Psannis, Konstantinos Goudos, Sotirios K. Vitsas, Vasileios Moscholios, Ioannis University of Western Macedonia Dept. of Electrical and Computer Engineering Kozani50100 Greece University of Macedonia Dept. of Applied Informatics Thessalonikii54636 Greece Aristotle University of Thessaloniki School of Physics Thessaloniki54124 Greece International Hellenic University Dept. of Information and Electronic Systems Engineering Thessaloniki57400 Greece University of Peloponnese Dept. of Informatics and Telecommunications Tripolis22100 Greece

ISBN: (纸本)9781728185644

The environmental concerns, the limited availability of conventional energy sources, the integration of alternative energy sources and the increasing number of power-demanding appliances change the way electricity is generated and distributed. Smart Grid (SG) is an appealing concept, which was developed in response to the emerging issues of electricity generation and distribution. By leveraging the latest advancements of Information and Communication Technologies (ICT), it offers significant benefits to energy providers, retailers and consumers. Nevertheless, SG is vulnerable to cyber attacks, that could cause critical economic and ecological consequences. Traditional Intrusion Detection Systems (IDSs) are becoming less efficient in detecting and mitigating cyberattacks, due to their limited capabilities of analyzing the exponentially increasing volume of network traffic. In this paper, we present the Secure and PrivatE smArt gRid (SPEAR) platform, which features a Big Data enabled IDS that timely detects and identifies cyber attacks against SG components. In order to validate the efficiency of the SPEAR platform regarding the protection of critical infrastructure, we installed the platform in a small wind power plant. © 2020 IEEE.

关键词： Smart power grids

来源：评论

学校读者我要写书评

暂无评论

Outage Performance of Cross-Packet HARQ

arXiv

引用

arXiv 2022年

作者： Feng, Jiahui Shi, Zheng Yang, Guanghua Miridakis, Nikolaos I. Ma, Shaodan Tsiftsis, Theodoros A. The School of Intelligent Systems Science and Engineering Jinan University Zhuhai519070 China The Dept. of Informatics and Computer Engineering University of West Attica Aegaleo 12243 Greece The State Key Laboratory of Internet of Things for Smart City University of Macau China

As opposed to hybrid automatic repeat request with incremental redundancy (HARQ-IR) that all the resources are occupied to resend the redundant information, cross-packet HARQ (XP-HARQ) allows the introduction of new information into retransmissions to substantially exploit the remaining resources. This letter provides a profound investigation into the outage performance of XP-HARQ. In particular, the exact outage expression of XP-HARQ is derived if the maximum number of transmissions is two, and tight outage bounds are obtained for more than two transmissions. Moreover, the asymptotic outage analysis of XP-HARQ in the high signal-to-noise ratio (SNR) regime is carried out not only to simplify the outage expression, but also to show that full time diversity is achievable by XP-HARQ. The simulation results are eventually presented for verifications. © 2022, CC BY.

关键词： Signal to noise ratio

来源：评论

学校读者我要写书评

暂无评论

Constructing a Cryptocurrency-Price Prediction Model Using Deep Learning 8

Constructing a Cryptocurrency-Price Prediction Model Using D...

引用

8th International Conference on engineering and Emerging Technologies, ICEET 2022

作者： Tran, Toai Kim Le, Thanh Thi Tuyet Bui, Thinh Tien Dang, Vang Quang Senkerik, Roman Ho Chi Minh City University of Technology and Education Faculty of Economics No 1 Vo Van Ngan Street Linh Chieu Ward Thu Duc City Viet Nam VSB-Technical University of Ostrava Faculty of Electrical Engineering and Computer Science Dept. of Computer Science 17. Listopadu 2172/15 Ostrava-Poruba708 00 Czech Republic Tomas Bata University in Zlin Faculty of Applied Informatics T. G. Masaryka 5555 Zlin76001 Czech Republic

ISBN: (纸本)9781665491068

The purpose of this study is to discover the optimal Deep Learning model for Bitcoin prediction among the Convolutional Neural Network (CNN), Recurrent Neural Network (RNN), and Long Short-Term Memory (LSTM). Our empirical results indicate that LSTM is the optimal model for predicting Bitcoin price and trend with the prediction accuracy of 88.9%. Our study serves as a stepping stone for novice cryptocurrency investors and future studies of more advanced and sophisticated algorithms. Finally, given that the ideal model for predicting the price of cryptocurrencies is still a topic of controversy, the findings of this study will serve as a valuable empirical resource for future studies. © 2022 IEEE.

关键词： Forecasting

来源：评论

学校读者我要写书评

暂无评论

Improving value-based e-government towards the achievement of smart government 5

Improving value-based e-government towards the achievement o...

引用

5th International Conference on informatics and Computing, ICIC 2020

作者： Hermanto, Agus Binti Ibrahim, Rosziati Kusnanto, Geri University of 17 Agustus 1945 Universiti Tun Hussein Onn Malaysia Dept. of Informatics Engineering Surabaya Indonesia Universiti Tun Hussein Onn Malaysia Faculty of Computer Science and Information Technology Johor Malaysia University of 17 Agustus 1945 Dept. of Informatics Engineering Surabaya Indonesia

ISBN: (纸本)9781728180472

The development of information technology in government so far is still experiencing problems with the lack of achievement of public value from e-government development. Therefore, this study aims to develop new perspectives at the macro level rather than the micro-level which has been widely used. The research method in this paper uses a value chain approach and digital transformation stages by strengthening technology and services that focus on the level of efficiency of government operational services which is increased from the micro level to the macro level and develops a reference model for increasing the value of services to achieve sustainable development goals. National. The result is the availability of models and frameworks that can be applied in e-government to build value-based e-government. © 2020 IEEE.

关键词： Smart city

来源：评论

学校读者我要写书评

暂无评论

A Location-Independent Flood Prediction Model for Bangladesh's Rivers

A Location-Independent Flood Prediction Model for Bangladesh...

引用

International Conference on Tools for Artificial Intelligence (ICTAI)

作者： Md Abid Hasan Nirjhor Tahmidur Rouf Md Sajid Hossain Lamia Binta Latif Anika Tasnim Marcin Grzegorzek Institute of Medical Informatics University of Lübeck Lübeck Germany Dept. Of ECE North Carolina State University USA department of EEE American International University Bangladesh Electrical and Electronic Engineering American International University Bangladesh Computer Science and Engineering Jahangirnagar University Bangladesh Silicon Engineering Ulkasemi Private Limited Bangladesh Fraunhofer IMTE Lübeck Germany

The involvement of a multitude of parameters adds to the complexity of modeling a flood. However, floods are among the most destructive of natural disasters and therefore, flood forecasting is one of the key priorities of hydrology. Flood forecasting goes a long way to minimize the loss of lives as well as economic losses. Furthermore, proper modeling of floods can contribute immensely towards future risk reduction and the introduction of necessary policies. At present, the application of machine learning in river and flood analysis has dramatically increased among hydrologists. In this research, we propose a location (District) independent flood prediction model (Random Forest-RF) of commercially significant rivers in Bangladesh. The data Imbalance problem is solved by synthetic minority oversampling of numerical and categorical (SMOTENC) data augmentation techniques. Our results show that the proposed framework outperforms the previously reported results by up to 9%. To the best of our knowledge, our proposed flood prediction framework achieved the best performance in terms of all evaluation matrices on the specific dataset.

关键词：

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：