2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI)最新文献

筛选
英文 中文
AutoML and Neural Architecture Search for Gaze Estimation 注视估计的AutoML和神经结构搜索
Adrian Bublea, C. Căleanu
{"title":"AutoML and Neural Architecture Search for Gaze Estimation","authors":"Adrian Bublea, C. Căleanu","doi":"10.1109/SACI55618.2022.9919471","DOIUrl":"https://doi.org/10.1109/SACI55618.2022.9919471","url":null,"abstract":"This paper focuses on employing the AutoKeras neural architecture search tool and Automatic Machine Learning (AutoML) methods to find an optimal gaze estimation system. The Network Architecture Search (NAS) means automatically tuning already existing deep neural network configurations using a dataset of interest. The algorithm will search in the architectural space for a better neural model along with its optimized parameters. In the paper context, an AutoML solution will perform similarly, but using just ‘pure’ ML models. Considering “Appearance-based Gaze Estimation in the Wild” (MPIIGaze) and “Columbia Gaze Data Set” (CAVE) datasets, the experiments showed results comparable to those of with manually designed models.","PeriodicalId":105691,"journal":{"name":"2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"13 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"120964167","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 2
A Numerical Model and a Code Development for Photogeneration Rate Calculation for a Dye Sensitized Solar Cell 染料敏化太阳能电池产光率计算的数值模型及程序开发
Z. Varga, Ervin Rácz
{"title":"A Numerical Model and a Code Development for Photogeneration Rate Calculation for a Dye Sensitized Solar Cell","authors":"Z. Varga, Ervin Rácz","doi":"10.1109/SACI55618.2022.9919499","DOIUrl":"https://doi.org/10.1109/SACI55618.2022.9919499","url":null,"abstract":"Dye Sensitized Solar Cell (DSSC) is an excellent option for the future energy supply because it provides outstanding promise in delivering a low-cost, easy manufacturability. For a deeper understanding of the mechanisms of the DSSCs, the modelling and simulation are required. In this paper, the development of a MatLab code is presented which is able to calculate the photogeneration rate in function of the cell thickness. The operation of the code is illustrated through an example, two different DSSCs were used for, proving and providing that the code works. The MatLab code is based on different equations of photo electrochemical in the Dye Sensitized Solar Cell. Based on solving the photogeneration rate, the model uses the numerical finite-element method. In accordance with the studied literature, the presented code has not been used before. The results also highlight that the photogeneration rate in function of the cell thickness of the cell depends on the optical parameters of the sensitized dye.","PeriodicalId":105691,"journal":{"name":"2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"114532081","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Role of Artificial Intelligence Techniques in Active Safety using Image Processing for Autonomous Driving Vehicles 人工智能技术在自动驾驶汽车图像处理主动安全中的作用
Delia Moga, I. Filip
{"title":"Role of Artificial Intelligence Techniques in Active Safety using Image Processing for Autonomous Driving Vehicles","authors":"Delia Moga, I. Filip","doi":"10.1109/SACI55618.2022.9919513","DOIUrl":"https://doi.org/10.1109/SACI55618.2022.9919513","url":null,"abstract":"This paper presents a study on the importance of using Artificial Intelligence methods in developing self-driving vehicles. Advances in Artificial Intelligence are one of the key enablers of the Autonomous Vehicles development. There are several ways to increase the level of autonomy of a vehicle and make it capable to avoid or prevent crashes. Advanced Driver Assistance Systems will help autonomous vehicles become a reality. Image processing of various traffic scenarios can be drastically improved by the use of the superior degrees of computer processing and computer vision techniques. With the help of convolutional neural networks (CNNs), not only that a single object can be detected and tracked in a sequence, but all relevant objects can be detected and classified for further processing. CNN s, the current state-of-the art for efficiently implementing deep neural networks for vision, are more efficient because they reuse a lot of weights across the image. Also, an introduction in synthetic data generation field is presented as a way to overcome the lack of labeled datasets for training networks.","PeriodicalId":105691,"journal":{"name":"2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"60 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"117322728","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Power Estimation Algorithm for High-Power Wind Turbines with Time Variable Wind Speed 时变风速大功率风力机功率估计算法
Mihaela-Codruta Ancuti, C. Șorândaru, S. Musuroi, Meda Alexandra Lazar, Alin Marius Stanciu, R. Ancuti
{"title":"Power Estimation Algorithm for High-Power Wind Turbines with Time Variable Wind Speed","authors":"Mihaela-Codruta Ancuti, C. Șorândaru, S. Musuroi, Meda Alexandra Lazar, Alin Marius Stanciu, R. Ancuti","doi":"10.1109/SACI55618.2022.9919593","DOIUrl":"https://doi.org/10.1109/SACI55618.2022.9919593","url":null,"abstract":"Using data from measurements (wind speed and wind turbine speed values), this study analyzes under what conditions maximum wind energy is gathered at a wind turbine operating at wind speeds that change substantially over time. The wind energy variation in time is calculated by measuring the wind speed, which may also be visualized by showing the time moments when the wind speed has the same value. Wind turbine speeds are determined at these times, and wind turbine outputs are estimated based on them. A method for determining wind turbine powers is described in this research, which allows viewing the operating points on the power characteristic. An examination of the performance of the control systems is performed using the provided technique. It is utilized in wind power facilities that operate at varying wind speeds. The conclusions achieved in this example were based on experimental data from the wind turbines region in Dobrogea.","PeriodicalId":105691,"journal":{"name":"2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"39 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129706039","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Towards malware detection based on performance counters using deep learning classification models 基于性能计数器的深度学习分类模型的恶意软件检测
Omar Mohamed, Ciprian-Bogdan Chirila
{"title":"Towards malware detection based on performance counters using deep learning classification models","authors":"Omar Mohamed, Ciprian-Bogdan Chirila","doi":"10.1109/SACI55618.2022.9919602","DOIUrl":"https://doi.org/10.1109/SACI55618.2022.9919602","url":null,"abstract":"Security exploits and subsequent malware is a challenge for computing systems. For detecting anomalies and discovering vulnerabilities in computing systems several methods are used: i) malware aware processors; ii) static program analysis; iii) dynamic program analysis. Malware aware processors require online hardware which is not always a practical and scalable solution. Static analysis methods imply automated static analysis tools that have a limited performance with a detection capability that not always meets the requirements of the project regarding the criticality of the application. Dynamic analysis on the other hand overcame static analysis in latest trends. In this trend performance counters analysis are used in several approaches. Operating system performance counters are collected and stored as time series in two contexts: i) in the presence and ii) in the absence of malware. Ten deep learning models are used for time series classification. From the experiments we learned that 2 models are able to detect accurately the presence of malware in an infested operating system, while the rest of the models tend to overfit the data.","PeriodicalId":105691,"journal":{"name":"2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125514788","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Deep Learning Method for Sentence Embeddings Based on Hadamard Matrix Encodings 基于Hadamard矩阵编码的句子嵌入深度学习方法
Mircea Trifan, B. Ionescu, D. Ionescu
{"title":"A Deep Learning Method for Sentence Embeddings Based on Hadamard Matrix Encodings","authors":"Mircea Trifan, B. Ionescu, D. Ionescu","doi":"10.1109/SACI55618.2022.9919604","DOIUrl":"https://doi.org/10.1109/SACI55618.2022.9919604","url":null,"abstract":"Sentence Embedding is recently getting an accrued attention from the Natural Language Processing (NLP) community. An embedding maps a sentence to a vector of real numbers with applications to similarity and inference tasks. Our method uses: word embeddings, dependency parsing, Hadamard matrix with spread spectrum algorithm and a deep learning neural network trained on the Sentences Involving Compositional Knowledge (SICK) corpus. The dependency parsing labels are associated with rows in a Hadamard matrix. Words embeddings are stored at corresponding rows in another matrix. Using the spread spectrum encoding algorithm the two matrices are combined into a single unidimensional vector. This embedding is then fed to a neural network achieving 80% accuracy while the best score from the SEMEVAL 2014 competition is 84%. The advantages of this method stem from encoding of any sentence size, using only fully connected neural networks, tacking into account the word order and handling long range word dependencies.","PeriodicalId":105691,"journal":{"name":"2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"27 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127414573","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
A Review of Cyber Security and Blockchain 网络安全和区块链综述
Silvana Qose, Beatrix Fregan
{"title":"A Review of Cyber Security and Blockchain","authors":"Silvana Qose, Beatrix Fregan","doi":"10.1109/SACI55618.2022.9919583","DOIUrl":"https://doi.org/10.1109/SACI55618.2022.9919583","url":null,"abstract":"Since the introduction of the Blockchain in Satoshi Nakamoto's study in 2008, Blockchain has become one of the foremost often mentioned ways to secure information storage and transfers for the trustless. This article is based on a literature review of decentralized technology and peer-to-peer systems that represents a scientific analysis of the most frequently adopted blockchain security applications in the usage of the Blockchain for cyber security functions. The findings indicate that the Internet of Things (IoT) and networks, machine visualization, and public-key cryptography hands themselves innovative to blockchain applications, just like safe storage of Personally Identifiable Information or online applications and certification schemes. This is a well-timed study based on systematic studies from several scientific journals. It will be an additional mild assessment of future prospects in Blockchain and cyber security research and blockchain security for AI data, including the safety of Blockchain in IoT and sidechain safety.","PeriodicalId":105691,"journal":{"name":"2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"28 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127432282","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Analysis of the Relaxation Effect by Vibrations on Some Rheological Models of Tissues 振动对组织流变模型松弛效应的分析
A. Neamtu, D. Simoiu, Andreea Raluca Ursu, L. Bereteu
{"title":"Analysis of the Relaxation Effect by Vibrations on Some Rheological Models of Tissues","authors":"A. Neamtu, D. Simoiu, Andreea Raluca Ursu, L. Bereteu","doi":"10.1109/SACI55618.2022.9919537","DOIUrl":"https://doi.org/10.1109/SACI55618.2022.9919537","url":null,"abstract":"Vibration therapy, or biomechanical stimulation, is a method used for improvement of muscle strength, power, and flexibility and has become a very popular method in recent years, both in physical therapy and in sports. This popularity is due to the fact that, as a result of analyzing the groups of subjects, the effects of small amplitude vibration and low frequency vibration, were found an increase in the force developed by the feet, a hardening of bone strength or an increase in bone density. The generic term used where any vibration of any frequency is transferred to the human body is “whole-body vibration”. In this paper it is proposed to give a possible explanation of the stress relaxation in muscle and/or bone after whole body vibration treatment. To do this, it is considered some rheological models that, when subjected to vibrations and analysis of their response, lead to the results obtained from different experiments.","PeriodicalId":105691,"journal":{"name":"2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130676165","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Research on resilience process model of space-based communication networks based on OPM 基于OPM的天基通信网络弹性过程模型研究
Yuxian Xie, Chengyu Liu, Hongxu Li, Yuzhi Wang, Yingchao Zhang
{"title":"Research on resilience process model of space-based communication networks based on OPM","authors":"Yuxian Xie, Chengyu Liu, Hongxu Li, Yuzhi Wang, Yingchao Zhang","doi":"10.1109/SACI55618.2022.9919547","DOIUrl":"https://doi.org/10.1109/SACI55618.2022.9919547","url":null,"abstract":"Space-based communication networks (SBCN) is subject to transmission delay, transmission interruption and other security threats due to the intricate relationships among the internal systems. Faced with a wide variety of security threats, SBCN still face many challenges in ensuring the effective completion of missions. Based on the resilience theory method and from the perspective of the resilience of SBCN, the architecture characteristics and security threats of SBCN were comprehensively analyzed, the resilience process model of SBCN was constructed according to the object process method (OPM), and the resilience design of SBCN was carried out. This study improves the resilience modeling analysis framework of SBCN and provides the foundation for the subsequent theoretical research.","PeriodicalId":105691,"journal":{"name":"2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"116657689","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
Parallel Data and Information Visualization 并行数据和信息可视化
J. Hreno, G. Lukac, M. Smatanova
{"title":"Parallel Data and Information Visualization","authors":"J. Hreno, G. Lukac, M. Smatanova","doi":"10.1109/SACI55618.2022.9919531","DOIUrl":"https://doi.org/10.1109/SACI55618.2022.9919531","url":null,"abstract":"We present a visualization tool developed for parallel data and information visualization in the domain of healthcare. The tool was used to get an insight into patient's current state in a limited time during clinic visits by different clinicians. Based on this tool, a new generic interactive visualization platform is proposed. The platform will use a specific knowledge model to identify suitable visualizations based on a chosen domain, previous cases, and available data.","PeriodicalId":105691,"journal":{"name":"2022 IEEE 16th International Symposium on Applied Computational Intelligence and Informatics (SACI)","volume":"31 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2022-05-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127751737","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
引用次数: 0
0
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
确定
请完成安全验证×
相关产品
×
本文献相关产品
联系我们:info@booksci.cn Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。 Copyright © 2023 布克学术 All rights reserved.
京ICP备2023020795号-1
ghs 京公网安备 11010802042870号
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术官方微信