首页 > 最新文献

2021 5th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI)最新文献

英文 中文
Convolutional Neural Networks for Raman Spectral Analysis of Chemical Mixtures 卷积神经网络用于化学混合物的拉曼光谱分析
Pub Date : 2021-12-06 DOI: 10.1109/SLAAI-ICAI54477.2021.9664686
M. Mozaffari, L. Tay
In the spectroscopy domain, one-dimensional Convolutional Neural Networks (1D CNN) assist researchers in recognizing one pure chemical compound and distinguishing it from unknown substances. The novelty of this approach is that a trained CNN operates automatically with almost no pre-or post-processing of data. However, the application of 1-D CNNs has typically been restricted to a binary classification of pure chemical substances. This study highlights a new approach in spectral recognition and quantification of components in chemical mixtures. Two 1-D CNN models, RaMixNet I and II, have been developed for this purpose as two multi-label classifiers. Depending on data availability, there is no limit to the number of compounds in an unknown mixture to recognize by RaMixNet models. We trained RaMixNet models using generated Raman spectra utilizing a novel data augmentation technique that adds random noise and different baselines to each spectrum as well as random wavenumber shifts for Raman peaks. The experimental results over hundreds of generated synthetic test mixtures revealed that the classification accuracy of RaMixNet I and II is 100%; at the same time, the RaMixNet II model could reach an average means square error rate of 0.06 and R2 score of 0.76 for the quantification of each component. In a comparison study, RaMixNet models could distinguish components of six actual chemical mixtures better than well-established distance-based techniques in the literature.
在光谱学领域,一维卷积神经网络(1D CNN)帮助研究人员识别一种纯化合物,并将其与未知物质区分开来。这种方法的新颖之处在于,经过训练的CNN可以自动运行,几乎不需要对数据进行预处理或后处理。然而,一维cnn的应用通常仅限于纯化学物质的二元分类。本研究为化学混合物中组分的光谱识别和定量提供了一种新的方法。为此开发了两个一维CNN模型RaMixNet I和II,作为两个多标签分类器。根据数据的可用性,RaMixNet模型识别的未知混合物中化合物的数量没有限制。我们使用一种新的数据增强技术来训练RaMixNet模型,该技术使用生成的拉曼光谱,在每个光谱中添加随机噪声和不同的基线,以及拉曼峰的随机波数移位。对生成的数百种合成测试混合物的实验结果表明,RaMixNet I和II的分类准确率为100%;同时,RaMixNet II模型对各成分的量化平均均方错误率为0.06,R2评分为0.76。在一项比较研究中,RaMixNet模型可以比文献中建立的基于距离的技术更好地区分六种实际化学混合物的成分。
{"title":"Convolutional Neural Networks for Raman Spectral Analysis of Chemical Mixtures","authors":"M. Mozaffari, L. Tay","doi":"10.1109/SLAAI-ICAI54477.2021.9664686","DOIUrl":"https://doi.org/10.1109/SLAAI-ICAI54477.2021.9664686","url":null,"abstract":"In the spectroscopy domain, one-dimensional Convolutional Neural Networks (1D CNN) assist researchers in recognizing one pure chemical compound and distinguishing it from unknown substances. The novelty of this approach is that a trained CNN operates automatically with almost no pre-or post-processing of data. However, the application of 1-D CNNs has typically been restricted to a binary classification of pure chemical substances. This study highlights a new approach in spectral recognition and quantification of components in chemical mixtures. Two 1-D CNN models, RaMixNet I and II, have been developed for this purpose as two multi-label classifiers. Depending on data availability, there is no limit to the number of compounds in an unknown mixture to recognize by RaMixNet models. We trained RaMixNet models using generated Raman spectra utilizing a novel data augmentation technique that adds random noise and different baselines to each spectrum as well as random wavenumber shifts for Raman peaks. The experimental results over hundreds of generated synthetic test mixtures revealed that the classification accuracy of RaMixNet I and II is 100%; at the same time, the RaMixNet II model could reach an average means square error rate of 0.06 and R2 score of 0.76 for the quantification of each component. In a comparison study, RaMixNet models could distinguish components of six actual chemical mixtures better than well-established distance-based techniques in the literature.","PeriodicalId":252006,"journal":{"name":"2021 5th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122233804","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: 5
SLAAI-ICAI 2021 Agenda
Pub Date : 2021-12-06 DOI: 10.1109/slaai-icai54477.2021.9664691
{"title":"SLAAI-ICAI 2021 Agenda","authors":"","doi":"10.1109/slaai-icai54477.2021.9664691","DOIUrl":"https://doi.org/10.1109/slaai-icai54477.2021.9664691","url":null,"abstract":"","PeriodicalId":252006,"journal":{"name":"2021 5th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI)","volume":"9 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128973173","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
Determine the Architecture of ANNs by Using the Peak Search Algorithm and Delta Values 利用峰值搜索算法和Delta值确定人工神经网络的结构
Pub Date : 2021-12-06 DOI: 10.1109/SLAAI-ICAI54477.2021.9664680
Mihirini Wagarachchi, A. Karunananda, Dinithi Navodya
The solution obtained by an Artificial Neural Network does not guarantee that it always yields with the simplest neural network architecture for particular problem. This causes computational complexity of training, deployment, and usage of the trained of an artificial neural network. It has observed that the hidden layer architecture of an artificial neural network significantly influences on its solution. However, still modeling of the hidden layer architecture of an artificial neural network remains as a research challenge. This paper presents a theoretically-based approach to prune hidden layers of trained artificial neural networks, ensuring better or the same performance of a simpler network as compared with the original network and then discusses how to extend the proposed method to deep learning nets. The method was inspired by the facts of neuroplasticity. It achieves the solution by two phases. First, the number of hidden layers is determined by using a peak search algorithm and then newly discovered simpler network with lesser number of hidden layers and highest generalization power considered for pruning of its hidden neurons. Experiments have shown that the resultant architecture generated by this approach exhibits same or better performance as compared with the original network architecture.
对于特定的问题,人工神经网络所得到的解并不能保证它总是产生最简单的神经网络结构。这导致人工神经网络训练、部署和使用的计算复杂性。研究发现,人工神经网络的隐层结构对其解有显著影响。然而,人工神经网络隐层结构的建模仍然是一个研究挑战。本文提出了一种基于理论的方法来修剪经过训练的人工神经网络的隐藏层,以确保与原始网络相比,更简单的网络具有更好或相同的性能,然后讨论了如何将所提出的方法扩展到深度学习网络。这种方法的灵感来自于神经可塑性。它通过两个阶段来实现解决方案。首先利用峰值搜索算法确定隐层数,然后考虑新发现的隐层数较少、泛化能力最高的简单网络对其隐神经元进行剪枝。实验表明,与原始网络结构相比,该方法生成的网络结构具有相同或更好的性能。
{"title":"Determine the Architecture of ANNs by Using the Peak Search Algorithm and Delta Values","authors":"Mihirini Wagarachchi, A. Karunananda, Dinithi Navodya","doi":"10.1109/SLAAI-ICAI54477.2021.9664680","DOIUrl":"https://doi.org/10.1109/SLAAI-ICAI54477.2021.9664680","url":null,"abstract":"The solution obtained by an Artificial Neural Network does not guarantee that it always yields with the simplest neural network architecture for particular problem. This causes computational complexity of training, deployment, and usage of the trained of an artificial neural network. It has observed that the hidden layer architecture of an artificial neural network significantly influences on its solution. However, still modeling of the hidden layer architecture of an artificial neural network remains as a research challenge. This paper presents a theoretically-based approach to prune hidden layers of trained artificial neural networks, ensuring better or the same performance of a simpler network as compared with the original network and then discusses how to extend the proposed method to deep learning nets. The method was inspired by the facts of neuroplasticity. It achieves the solution by two phases. First, the number of hidden layers is determined by using a peak search algorithm and then newly discovered simpler network with lesser number of hidden layers and highest generalization power considered for pruning of its hidden neurons. Experiments have shown that the resultant architecture generated by this approach exhibits same or better performance as compared with the original network architecture.","PeriodicalId":252006,"journal":{"name":"2021 5th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI)","volume":"19 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127577655","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
Adaptive Stock Market Portfolio Management and Stock Prices Prediction Platform for Colombo Stock Exchange of Sri Lanka 斯里兰卡科伦坡证券交易所自适应证券市场投资组合管理与股价预测平台
Pub Date : 2021-12-06 DOI: 10.1109/SLAAI-ICAI54477.2021.9664735
Samudith Nanayakkara, A. Wanniarachchi, D. Vidanagama
Over the past few years various studies have been conducted to develop an optimum stock market related portfolio management platform that will assists investors to actively perform the portfolio management process. Risk and level of investor participation is considered to be one of the challenging aspects identified for optimum portfolio management. Along with portfolio management, stock price prediction is one of the key contributing factors that helps an investor to arrive mid- and long-term strategic investment decisions. Various deep learning concepts are evaluated to determine the most accurate algorithm to implement the stock price-based prediction system. Currently Colombo Stock Exchange have identified a desperate requirement of a portfolio management system with prediction capabilities to support the local and foreign investors to actively engage in trading activities among different stock exchanges in different countries. A critical study has been conducted using supportive research papers, similar applications developed and using various requirement elicitation techniques to determine the functional requirements, non-functional requirements, investor requirements, UI/UX considerations etc. The paper further describes various technological mechanisms implemented and system architectures used to develop the portfolio management and stock price prediction system. Accordingly, the implementation of Brownian Motion algorithm-based model and LSTM (Long Short-Term Memory) model are in detailed presented by the author. Finally, evaluation and testing results of the completed system and stock price prediction models are presented to prove the successfulness of the completed application and accuracy of the models implemented.
在过去的几年里,人们进行了各种各样的研究,以开发一个最佳的股票市场相关的投资组合管理平台,帮助投资者积极地进行投资组合管理过程。风险和投资者参与水平被认为是确定最佳投资组合管理的具有挑战性的方面之一。与投资组合管理一样,股票价格预测是帮助投资者做出中长期战略投资决策的关键因素之一。评估各种深度学习概念,以确定最准确的算法来实现基于股票价格的预测系统。目前,科伦坡证券交易所已经确定了迫切需要一个具有预测能力的投资组合管理系统,以支持本地和外国投资者积极参与不同国家不同证券交易所之间的交易活动。使用支持性研究论文、开发的类似应用程序和使用各种需求引出技术来确定功能需求、非功能需求、投资者需求、UI/UX考虑因素等,进行了一项关键研究。本文进一步描述了用于开发投资组合管理和股票价格预测系统的各种技术机制和系统架构。在此基础上,作者详细介绍了基于布朗运动算法的模型和长短期记忆模型的实现。最后,给出了完成的系统和股票价格预测模型的评估和测试结果,以证明完成的应用是成功的,所实现的模型是准确的。
{"title":"Adaptive Stock Market Portfolio Management and Stock Prices Prediction Platform for Colombo Stock Exchange of Sri Lanka","authors":"Samudith Nanayakkara, A. Wanniarachchi, D. Vidanagama","doi":"10.1109/SLAAI-ICAI54477.2021.9664735","DOIUrl":"https://doi.org/10.1109/SLAAI-ICAI54477.2021.9664735","url":null,"abstract":"Over the past few years various studies have been conducted to develop an optimum stock market related portfolio management platform that will assists investors to actively perform the portfolio management process. Risk and level of investor participation is considered to be one of the challenging aspects identified for optimum portfolio management. Along with portfolio management, stock price prediction is one of the key contributing factors that helps an investor to arrive mid- and long-term strategic investment decisions. Various deep learning concepts are evaluated to determine the most accurate algorithm to implement the stock price-based prediction system. Currently Colombo Stock Exchange have identified a desperate requirement of a portfolio management system with prediction capabilities to support the local and foreign investors to actively engage in trading activities among different stock exchanges in different countries. A critical study has been conducted using supportive research papers, similar applications developed and using various requirement elicitation techniques to determine the functional requirements, non-functional requirements, investor requirements, UI/UX considerations etc. The paper further describes various technological mechanisms implemented and system architectures used to develop the portfolio management and stock price prediction system. Accordingly, the implementation of Brownian Motion algorithm-based model and LSTM (Long Short-Term Memory) model are in detailed presented by the author. Finally, evaluation and testing results of the completed system and stock price prediction models are presented to prove the successfulness of the completed application and accuracy of the models implemented.","PeriodicalId":252006,"journal":{"name":"2021 5th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI)","volume":"11 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"115324624","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: 1
Main Organizing Committee 主要组织委员会
Pub Date : 2021-12-06 DOI: 10.1109/apace.2012.6457701
{"title":"Main Organizing Committee","authors":"","doi":"10.1109/apace.2012.6457701","DOIUrl":"https://doi.org/10.1109/apace.2012.6457701","url":null,"abstract":"","PeriodicalId":252006,"journal":{"name":"2021 5th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI)","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127132313","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
Comparative Study of Face Detection Methods for Robust Face Recognition Systems 鲁棒人脸识别系统中人脸检测方法的比较研究
Pub Date : 2021-12-06 DOI: 10.1109/SLAAI-ICAI54477.2021.9664689
Thilinda Edirisooriya, E. Jayatunga
Face detection systems are used in various computer vision-based applications such as biometrics, security, surveillance, etc. Computationally immoderate face detection methods may not be convenient for devices with inadequate resources. On the other hand, an appropriate face detection approach should be considered in order to achieve high accuracy and substantial performance. This paper deliberates different methods of facial detection and contrasts them to find a better approach for a robust facial recognition system. Five methods of face detection were used in this comparison namely, ViolaJones, Histogram of Oriented Gradient with Support Vector Machine (HOG-SVM), Multi-task Cascaded Convolutional Network (MTCNN), Single Shot Multibox Detector (SSD) and Maxmargin Object Detection (MMOD). Each method was evaluated by varying illumination intensity, angle of the face, the scale of the face and different occlusion types. Video data and WIDERFACE image samples were used for the analysis. Obtained experimental results depict that SSD performs better on the task of face detection with high accuracy and performance, while MMOD has the lowest performance and Viola-Jones gives the lowest accuracy.
人脸检测系统用于各种基于计算机视觉的应用,如生物识别、安全、监视等。计算量过大的人脸检测方法对于资源不足的设备可能不方便。另一方面,为了达到较高的准确率和较好的性能,需要考虑一种合适的人脸检测方法。本文研究了不同的人脸检测方法,并对它们进行了对比,以找到一种更好的鲁棒人脸识别系统。本次比较使用了ViolaJones、HOG-SVM、Multi-task cascading Convolutional Network (MTCNN)、Single Shot Multibox Detector (SSD)和Maxmargin Object detection (MMOD)五种人脸检测方法。通过改变光照强度、人脸角度、人脸尺度和不同遮挡类型对每种方法进行评估。使用视频数据和WIDERFACE图像样本进行分析。得到的实验结果表明,SSD在人脸检测任务上表现较好,具有较高的准确率和性能,而MMOD的性能最低,Viola-Jones的准确率最低。
{"title":"Comparative Study of Face Detection Methods for Robust Face Recognition Systems","authors":"Thilinda Edirisooriya, E. Jayatunga","doi":"10.1109/SLAAI-ICAI54477.2021.9664689","DOIUrl":"https://doi.org/10.1109/SLAAI-ICAI54477.2021.9664689","url":null,"abstract":"Face detection systems are used in various computer vision-based applications such as biometrics, security, surveillance, etc. Computationally immoderate face detection methods may not be convenient for devices with inadequate resources. On the other hand, an appropriate face detection approach should be considered in order to achieve high accuracy and substantial performance. This paper deliberates different methods of facial detection and contrasts them to find a better approach for a robust facial recognition system. Five methods of face detection were used in this comparison namely, ViolaJones, Histogram of Oriented Gradient with Support Vector Machine (HOG-SVM), Multi-task Cascaded Convolutional Network (MTCNN), Single Shot Multibox Detector (SSD) and Maxmargin Object Detection (MMOD). Each method was evaluated by varying illumination intensity, angle of the face, the scale of the face and different occlusion types. Video data and WIDERFACE image samples were used for the analysis. Obtained experimental results depict that SSD performs better on the task of face detection with high accuracy and performance, while MMOD has the lowest performance and Viola-Jones gives the lowest accuracy.","PeriodicalId":252006,"journal":{"name":"2021 5th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI)","volume":"99 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134550446","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: 1
Evaluation of Deep Learning Approaches for Anomaly Detection 异常检测的深度学习方法评价
Pub Date : 2021-12-06 DOI: 10.1109/SLAAI-ICAI54477.2021.9664669
Asela Hevapathige
Deep learning is a machine learning technique which is inspired by basic human instincts and functionality of the brain. It can be leveraged to tackle anomaly detection problems due to their ability in performing complex learning and prediction. However, this has been challenging due to the diversity of anomalies, class imbalance and curse of dimensionality. This research study focused on analyzing the performance of deep learning models for anomaly detection in various domains. Multi-Layer Perceptron, Deep Neural Network, Recurrent Neural Network and Auto Encoder algorithms were tested on 7 numerical datasets ranging from small scale to large scale in terms of both data size and features. The experimental design used one class classification to train the models from non-anomalous data to identify new instances as either anomalous or non-anomalous. The experimental results indicate that deep learning algorithms improve performance with the increase of data size. This study also identified certain limitations of deep learning models on anomaly detection.
深度学习是一种机器学习技术,它的灵感来自于人类的基本本能和大脑的功能。由于它们具有执行复杂学习和预测的能力,因此可以利用它来解决异常检测问题。然而,由于异常的多样性、职业的不平衡和维度的诅咒,这一直是具有挑战性的。本研究重点分析了深度学习模型在不同领域异常检测中的性能。对多层感知器、深度神经网络、递归神经网络和自动编码器算法在7个从小规模到大规模的数值数据集上进行了数据量和特征的测试。实验设计采用单类分类从非异常数据中训练模型,以识别异常或非异常的新实例。实验结果表明,深度学习算法的性能随着数据量的增加而提高。本研究还发现了深度学习模型在异常检测方面的某些局限性。
{"title":"Evaluation of Deep Learning Approaches for Anomaly Detection","authors":"Asela Hevapathige","doi":"10.1109/SLAAI-ICAI54477.2021.9664669","DOIUrl":"https://doi.org/10.1109/SLAAI-ICAI54477.2021.9664669","url":null,"abstract":"Deep learning is a machine learning technique which is inspired by basic human instincts and functionality of the brain. It can be leveraged to tackle anomaly detection problems due to their ability in performing complex learning and prediction. However, this has been challenging due to the diversity of anomalies, class imbalance and curse of dimensionality. This research study focused on analyzing the performance of deep learning models for anomaly detection in various domains. Multi-Layer Perceptron, Deep Neural Network, Recurrent Neural Network and Auto Encoder algorithms were tested on 7 numerical datasets ranging from small scale to large scale in terms of both data size and features. The experimental design used one class classification to train the models from non-anomalous data to identify new instances as either anomalous or non-anomalous. The experimental results indicate that deep learning algorithms improve performance with the increase of data size. This study also identified certain limitations of deep learning models on anomaly detection.","PeriodicalId":252006,"journal":{"name":"2021 5th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI)","volume":"18 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129346347","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: 1
DDoS Attack Traffic Identification Using Recurrent Neural Network 基于递归神经网络的DDoS攻击流量识别
Pub Date : 2021-12-06 DOI: 10.1109/SLAAI-ICAI54477.2021.9664685
Yu Li, Hao Shi, Mingyu Fan
Cyber security plays a very important role in all walks of our life, especially in information industries. We all know, there are a lot of cyber attacks in network. Among all, DDoS attacks are more common and harmful than other types. Nowadays, with the rapid development of distributed computing technologies, cloud technologies and Internet, the scope of DDoS attacks is increased. These DDoS attacks are of different types like denial of service, distributed denial of service, Slowloris, and so on. We know that there are a number of technologies to detect the attacks, and the most popular way is machine learning. In this paper, we propose a recurrent neural network-based solution for DDoS attack traffic flow detection. This solution can be used for online intrusion detection systems and intrusion prevention systems. Firstly, we need to collect dataset. Due to the lack of reliable test and validation datasets, the existing datasets illustrate that most of them are out of date and useless, we use DDoS 2019 dataset for our experiment. Secondly, we extract features by CICFlowMeter tool. Thirdly, the extracted features are converted into grayscale images by a certain algorithm. Finally, the grayscale images are used as input to the RNN classifier. Regardless of a feature appears in the image, through RNN classifier, we will get the same output, this is a fundamental and most important benefit of RNN classifiers. With this implementation, we can achieve an accuracy of 99.95%.
网络安全在我们的各行各业,特别是在信息产业中发挥着非常重要的作用。我们都知道,网络上有很多网络攻击。其中,DDoS攻击比其他类型的攻击更常见,危害也更大。如今,随着分布式计算技术、云技术和互联网的快速发展,DDoS攻击的范围越来越大。这些DDoS攻击有不同的类型,如拒绝服务、分布式拒绝服务、慢速攻击等。我们知道有许多技术可以检测攻击,最流行的方法是机器学习。本文提出了一种基于递归神经网络的DDoS攻击流量检测方案。该方案适用于在线入侵检测系统和入侵防御系统。首先,我们需要收集数据集。由于缺乏可靠的测试和验证数据集,现有的数据集表明大多数数据集已经过时且无用,我们使用DDoS 2019数据集进行实验。其次,利用CICFlowMeter工具提取特征。第三,通过一定的算法将提取的特征转换为灰度图像。最后,将灰度图像作为RNN分类器的输入。无论图像中出现什么特征,通过RNN分类器,我们都会得到相同的输出,这是RNN分类器最基本也是最重要的优点。通过这种实现,我们可以达到99.95%的准确率。
{"title":"DDoS Attack Traffic Identification Using Recurrent Neural Network","authors":"Yu Li, Hao Shi, Mingyu Fan","doi":"10.1109/SLAAI-ICAI54477.2021.9664685","DOIUrl":"https://doi.org/10.1109/SLAAI-ICAI54477.2021.9664685","url":null,"abstract":"Cyber security plays a very important role in all walks of our life, especially in information industries. We all know, there are a lot of cyber attacks in network. Among all, DDoS attacks are more common and harmful than other types. Nowadays, with the rapid development of distributed computing technologies, cloud technologies and Internet, the scope of DDoS attacks is increased. These DDoS attacks are of different types like denial of service, distributed denial of service, Slowloris, and so on. We know that there are a number of technologies to detect the attacks, and the most popular way is machine learning. In this paper, we propose a recurrent neural network-based solution for DDoS attack traffic flow detection. This solution can be used for online intrusion detection systems and intrusion prevention systems. Firstly, we need to collect dataset. Due to the lack of reliable test and validation datasets, the existing datasets illustrate that most of them are out of date and useless, we use DDoS 2019 dataset for our experiment. Secondly, we extract features by CICFlowMeter tool. Thirdly, the extracted features are converted into grayscale images by a certain algorithm. Finally, the grayscale images are used as input to the RNN classifier. Regardless of a feature appears in the image, through RNN classifier, we will get the same output, this is a fundamental and most important benefit of RNN classifiers. With this implementation, we can achieve an accuracy of 99.95%.","PeriodicalId":252006,"journal":{"name":"2021 5th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI)","volume":"42 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"126127816","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
Evaluation and Validation of Subfertility Ontology and Decision Support System 亚生育本体与决策支持系统的评价与验证
Pub Date : 2021-12-06 DOI: 10.1109/SLAAI-ICAI54477.2021.9664683
T. Yogarajah, Kuhaneswaran Banujan, S. Vasanthapriyan
Evaluation and Validation of ontology verify the quality and perfection of the ontology. Decision Support System ’s Evaluation and Validation provides an error-free and accurate system for users. This paper describes the validation of ontology procedures which verifies the content of the ontology and examines the application of developed subfertility treatment method ontology. We gathered ontology expert suggestions and assessment methods for developed ontology also from the users’ feedback from the doctors and medical students. Ontology accuracy and quality validated by Corpus-based Approach, Delphi Method, Modified Delphi Method, and OntOlogy Pitfall Scanner (web-based pitfall scanner tool) are some approaches employed for ontology evaluation. Certain concepts such as DL Query and SPARQL Query have been utilized to assess ontology, which is included in the Protégé OWL Ontology editor 5.5. The technique of verification adheres to the coherence and structure of ontology while the methods of validation focus to assess their application in the real world. Validity and assessment determine the ontology model’s consistency and user satisfaction. Decision Support System (DSS) evaluated and validated by the field test and user’s feedback. This Evaluation and Validation provide the perfectness of decision-making in a specified domain.
本体的评价和验证验证了本体的质量和完善性。决策支持系统的评估与验证为用户提供了一个准确无误的系统。本文描述了本体的验证程序,验证了本体的内容,并对开发的治疗方法本体的应用进行了检验。我们收集了本体专家的建议和对已开发的本体的评价方法,以及来自医生和医学生的用户反馈。基于语料库的方法、德尔菲法、改进德尔菲法和本体陷阱扫描器(基于web的陷阱扫描器工具)验证了本体的准确性和质量。某些概念,如DL Query和SPARQL Query,已经被用来评估本体,它包含在prot OWL本体编辑器5.5中。验证技术坚持本体的一致性和结构,而验证方法侧重于评估其在现实世界中的应用。有效性和评估决定了本体模型的一致性和用户满意度。决策支持系统(DSS)通过现场测试和用户反馈进行评估和验证。这种评估和验证提供了在特定领域内决策的完备性。
{"title":"Evaluation and Validation of Subfertility Ontology and Decision Support System","authors":"T. Yogarajah, Kuhaneswaran Banujan, S. Vasanthapriyan","doi":"10.1109/SLAAI-ICAI54477.2021.9664683","DOIUrl":"https://doi.org/10.1109/SLAAI-ICAI54477.2021.9664683","url":null,"abstract":"Evaluation and Validation of ontology verify the quality and perfection of the ontology. Decision Support System ’s Evaluation and Validation provides an error-free and accurate system for users. This paper describes the validation of ontology procedures which verifies the content of the ontology and examines the application of developed subfertility treatment method ontology. We gathered ontology expert suggestions and assessment methods for developed ontology also from the users’ feedback from the doctors and medical students. Ontology accuracy and quality validated by Corpus-based Approach, Delphi Method, Modified Delphi Method, and OntOlogy Pitfall Scanner (web-based pitfall scanner tool) are some approaches employed for ontology evaluation. Certain concepts such as DL Query and SPARQL Query have been utilized to assess ontology, which is included in the Protégé OWL Ontology editor 5.5. The technique of verification adheres to the coherence and structure of ontology while the methods of validation focus to assess their application in the real world. Validity and assessment determine the ontology model’s consistency and user satisfaction. Decision Support System (DSS) evaluated and validated by the field test and user’s feedback. This Evaluation and Validation provide the perfectness of decision-making in a specified domain.","PeriodicalId":252006,"journal":{"name":"2021 5th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130738187","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
Deep COVID-19 Recognition Using Chest X-ray Images: A Comparative Analysis 使用胸部x射线图像进行COVID-19深度识别:比较分析
Pub Date : 2021-12-06 DOI: 10.1109/SLAAI-ICAI54477.2021.9664727
S. Thuseethan, C. Wimalasooriya, S. Vasanthapriyan
The novel coronavirus variant, which is also widely known as COVID-19, is currently a common threat to all humans across the world. Effective recognition of COVID-19 using advanced machine learning methods is a timely need. Although many sophisticated approaches have been proposed in the recent past, they still struggle to achieve expected performances in recognizing COVID-19 using chest X-ray images. In addition, the majority of them are involved with the complex pre-processing task, which is often challenging and time-consuming. Meanwhile, deep networks are end-to-end and have shown promising results in image-based recognition tasks during the last decade. Hence, in this work, some widely used state-of-the-art deep networks are evaluated for COVID-19 recognition with chest X-ray images. All the deep networks are evaluated on a publicly available chest X-ray image datasets. The evaluation results show that the deep networks can effectively recognize COVID-19 from chest X-ray images. Further, the comparison results reveal that the EfficientNetB7 network outperformed other existing state-of-the-art techniques.
新型冠状病毒变种,也被广泛称为COVID-19,目前是全球所有人类的共同威胁。利用先进的机器学习方法有效识别COVID-19是迫切需要的。尽管最近提出了许多复杂的方法,但在使用胸部x射线图像识别COVID-19方面,它们仍然难以达到预期的性能。此外,它们中的大多数都涉及复杂的预处理任务,这通常是具有挑战性和耗时的。同时,深度网络是端到端的,并且在过去十年中在基于图像的识别任务中显示出有希望的结果。因此,在这项工作中,评估了一些广泛使用的最先进的深度网络对胸部x射线图像的COVID-19识别。所有的深度网络都在公开可用的胸部x射线图像数据集上进行评估。评估结果表明,深度网络可以有效地从胸部x线图像中识别COVID-19。此外,比较结果显示,EfficientNetB7网络的性能优于其他现有的最先进的技术。
{"title":"Deep COVID-19 Recognition Using Chest X-ray Images: A Comparative Analysis","authors":"S. Thuseethan, C. Wimalasooriya, S. Vasanthapriyan","doi":"10.1109/SLAAI-ICAI54477.2021.9664727","DOIUrl":"https://doi.org/10.1109/SLAAI-ICAI54477.2021.9664727","url":null,"abstract":"The novel coronavirus variant, which is also widely known as COVID-19, is currently a common threat to all humans across the world. Effective recognition of COVID-19 using advanced machine learning methods is a timely need. Although many sophisticated approaches have been proposed in the recent past, they still struggle to achieve expected performances in recognizing COVID-19 using chest X-ray images. In addition, the majority of them are involved with the complex pre-processing task, which is often challenging and time-consuming. Meanwhile, deep networks are end-to-end and have shown promising results in image-based recognition tasks during the last decade. Hence, in this work, some widely used state-of-the-art deep networks are evaluated for COVID-19 recognition with chest X-ray images. All the deep networks are evaluated on a publicly available chest X-ray image datasets. The evaluation results show that the deep networks can effectively recognize COVID-19 from chest X-ray images. Further, the comparison results reveal that the EfficientNetB7 network outperformed other existing state-of-the-art techniques.","PeriodicalId":252006,"journal":{"name":"2021 5th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI)","volume":"8 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-06","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"133942884","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
期刊
2021 5th SLAAI International Conference on Artificial Intelligence (SLAAI-ICAI)
全部 Acc. Chem. Res. ACS Applied Bio Materials ACS Appl. Electron. Mater. ACS Appl. Energy Mater. ACS Appl. Mater. Interfaces ACS Appl. Nano Mater. ACS Appl. Polym. Mater. ACS BIOMATER-SCI ENG ACS Catal. ACS Cent. Sci. ACS Chem. Biol. ACS Chemical Health & Safety ACS Chem. Neurosci. ACS Comb. Sci. ACS Earth Space Chem. ACS Energy Lett. ACS Infect. Dis. ACS Macro Lett. ACS Mater. Lett. ACS Med. Chem. Lett. ACS Nano ACS Omega ACS Photonics ACS Sens. ACS Sustainable Chem. Eng. ACS Synth. Biol. Anal. Chem. BIOCHEMISTRY-US Bioconjugate Chem. BIOMACROMOLECULES Chem. Res. Toxicol. Chem. Rev. Chem. Mater. CRYST GROWTH DES ENERG FUEL Environ. Sci. Technol. Environ. Sci. Technol. Lett. Eur. J. Inorg. Chem. IND ENG CHEM RES Inorg. Chem. J. Agric. Food. Chem. J. Chem. Eng. Data J. Chem. Educ. J. Chem. Inf. Model. J. Chem. Theory Comput. J. Med. Chem. J. Nat. Prod. J PROTEOME RES J. Am. Chem. Soc. LANGMUIR MACROMOLECULES Mol. Pharmaceutics Nano Lett. Org. Lett. ORG PROCESS RES DEV ORGANOMETALLICS J. Org. Chem. J. Phys. Chem. J. Phys. Chem. A J. Phys. Chem. B J. Phys. Chem. C J. Phys. Chem. Lett. Analyst Anal. Methods Biomater. Sci. Catal. Sci. Technol. Chem. Commun. Chem. Soc. Rev. CHEM EDUC RES PRACT CRYSTENGCOMM Dalton Trans. Energy Environ. Sci. ENVIRON SCI-NANO ENVIRON SCI-PROC IMP ENVIRON SCI-WAT RES Faraday Discuss. Food Funct. Green Chem. Inorg. Chem. Front. Integr. Biol. J. Anal. At. Spectrom. J. Mater. Chem. A J. Mater. Chem. B J. Mater. Chem. C Lab Chip Mater. Chem. Front. Mater. Horiz. MEDCHEMCOMM Metallomics Mol. Biosyst. Mol. Syst. Des. Eng. Nanoscale Nanoscale Horiz. Nat. Prod. Rep. New J. Chem. Org. Biomol. Chem. Org. Chem. Front. PHOTOCH PHOTOBIO SCI PCCP Polym. Chem.
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
×
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
现在去查看 取消
×
提示
确定
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 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 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1