Pub Date : 2019-02-01DOI: 10.1109/ICAIIC.2019.8668971
Songpu Ai, Antorweep Chakravorty, Chunming Rong
The popularization of electric vehicle, the commercialization of micro-generation, and the advance of local storage lead great challenges to the local power grid on household and neighbourhood level. A potential solution is to construct a home/neighbourhood energy management system (HEMS) to coordinate all available electrical equipment together using AI. As a portion of HEMS, peak demand prediction is critically important on triggering load scheduling among the household power environment to achieve better electricity usage curve. Long short-term memory (LSTM) network as an eminent type of machine learning method is generally considered to be capable on forecasting based on time series data including temporal dynamic behaviours with unknown lags. Various LSTM networks are adopted in existing researches to provide predictions in energy informatics field. However, the presented network structures are commonly selected through empirical or enumerative approaches. The utilized networks are generally carefully tuned as case by case studies. In this article, an evolutionary ensemble LSTM (EELSTM) method is proposed to pool LSTM networks with the same structure or with similar structures to obtain a more reliable prediction automatically. Experimental study demonstrates that networks with suitable structures and initialization are selected out through the learning process. A better performed peak demand prediction is achieved comparing with single LSTM unit network. In addition, the evolutionary parameters have variant impacts on the model performance.
{"title":"Evolutionary Ensemble LSTM based Household Peak Demand Prediction","authors":"Songpu Ai, Antorweep Chakravorty, Chunming Rong","doi":"10.1109/ICAIIC.2019.8668971","DOIUrl":"https://doi.org/10.1109/ICAIIC.2019.8668971","url":null,"abstract":"The popularization of electric vehicle, the commercialization of micro-generation, and the advance of local storage lead great challenges to the local power grid on household and neighbourhood level. A potential solution is to construct a home/neighbourhood energy management system (HEMS) to coordinate all available electrical equipment together using AI. As a portion of HEMS, peak demand prediction is critically important on triggering load scheduling among the household power environment to achieve better electricity usage curve. Long short-term memory (LSTM) network as an eminent type of machine learning method is generally considered to be capable on forecasting based on time series data including temporal dynamic behaviours with unknown lags. Various LSTM networks are adopted in existing researches to provide predictions in energy informatics field. However, the presented network structures are commonly selected through empirical or enumerative approaches. The utilized networks are generally carefully tuned as case by case studies. In this article, an evolutionary ensemble LSTM (EELSTM) method is proposed to pool LSTM networks with the same structure or with similar structures to obtain a more reliable prediction automatically. Experimental study demonstrates that networks with suitable structures and initialization are selected out through the learning process. A better performed peak demand prediction is achieved comparing with single LSTM unit network. In addition, the evolutionary parameters have variant impacts on the model performance.","PeriodicalId":273383,"journal":{"name":"2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"43 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127261701","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}
Pub Date : 2019-02-01DOI: 10.1109/ICAIIC.2019.8669040
Sina Fathi Kazerooni, Yagiz Kaymak, R. Rojas-Cessa
A network eavesdropper may invade the privacy of an online user by collecting the passing traffic and classifying the applications that generated the network traffic. This collection may be used to build fingerprints of the user’s Internet usage. In this paper, we investigate the feasibility of performing such breach on encrypted network traffic generated by actual users. We adopt the random forest algorithm to classify the applications in use by users of a campus network. Our classification system identifies and quantifies different statistical features of user’s network traffic to classify applications rather than looking into packet contents. In addition, application classification is performed without employing a port mapping at the transport layer. Our results show that applications can be identified with an average precision and recall of up to 99%.
{"title":"Tracking User Application Activity by using Machine Learning Techniques on Network Traffic","authors":"Sina Fathi Kazerooni, Yagiz Kaymak, R. Rojas-Cessa","doi":"10.1109/ICAIIC.2019.8669040","DOIUrl":"https://doi.org/10.1109/ICAIIC.2019.8669040","url":null,"abstract":"A network eavesdropper may invade the privacy of an online user by collecting the passing traffic and classifying the applications that generated the network traffic. This collection may be used to build fingerprints of the user’s Internet usage. In this paper, we investigate the feasibility of performing such breach on encrypted network traffic generated by actual users. We adopt the random forest algorithm to classify the applications in use by users of a campus network. Our classification system identifies and quantifies different statistical features of user’s network traffic to classify applications rather than looking into packet contents. In addition, application classification is performed without employing a port mapping at the transport layer. Our results show that applications can be identified with an average precision and recall of up to 99%.","PeriodicalId":273383,"journal":{"name":"2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"84 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121735499","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}
Pub Date : 2019-02-01DOI: 10.1109/ICAIIC.2019.8669032
Michiko Miyamoto
The purpose of this paper is empirically investigates whether IT strategies, business strategies and divisions are aligned to meet overall business goals for Japanese corporations, including both large and small and medium enterprises (SMEs), based on Structured based Strategic Alignment Model [1], and make comparison with those of Japanese SMEs studied in 2014. Using 101 valid responses of corporations throughout Japan, this study found Business strategy is positive, strongly, and significantly influence over IT strategy, which is the same as the previous study. HR/Administrative department still have a major influence over some departments such as Logistic, Technology and Manufacturing, but not much so for Marketing. It is positive but weak and not significant relationships between HR departments and both business strategy and IT strategy, which are different from the previous study.
{"title":"IT-Business Alignments among Different Divisions of Japanese Corporations","authors":"Michiko Miyamoto","doi":"10.1109/ICAIIC.2019.8669032","DOIUrl":"https://doi.org/10.1109/ICAIIC.2019.8669032","url":null,"abstract":"The purpose of this paper is empirically investigates whether IT strategies, business strategies and divisions are aligned to meet overall business goals for Japanese corporations, including both large and small and medium enterprises (SMEs), based on Structured based Strategic Alignment Model [1], and make comparison with those of Japanese SMEs studied in 2014. Using 101 valid responses of corporations throughout Japan, this study found Business strategy is positive, strongly, and significantly influence over IT strategy, which is the same as the previous study. HR/Administrative department still have a major influence over some departments such as Logistic, Technology and Manufacturing, but not much so for Marketing. It is positive but weak and not significant relationships between HR departments and both business strategy and IT strategy, which are different from the previous study.","PeriodicalId":273383,"journal":{"name":"2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131022611","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}
Pub Date : 2019-02-01DOI: 10.1109/ICAIIC.2019.8669014
Tosin A. Adesuyi, Byeong-Man Kim
Datasets are sources of information mining where knowledge can be derived. The versatility of these dataset determines the quality of knowledge gained. However, several of these data contains personal sensitive information that can lead to infringement of privacy. Existing research tends to deliver DNN models that can preserve privacy of personal information but the accuracy of these models are rather much lower as compared to their non-privacy preserving counterparts. This is due to the degree of noise and the points where noise was added to perturb the model data. Consequently, this has led to minimal adoption of privacy preserving DNN models in the industrial world. In this paper, we present a layer-wise perturbation approach and differential privacy technique to determine points of perturbation and preserve privacy. Our approach was able to narrow down the accuracy gap between privacy-preserving and non-privacy preserving DNN model.
{"title":"A layer-wise Perturbation based Privacy Preserving Deep Neural Networks","authors":"Tosin A. Adesuyi, Byeong-Man Kim","doi":"10.1109/ICAIIC.2019.8669014","DOIUrl":"https://doi.org/10.1109/ICAIIC.2019.8669014","url":null,"abstract":"Datasets are sources of information mining where knowledge can be derived. The versatility of these dataset determines the quality of knowledge gained. However, several of these data contains personal sensitive information that can lead to infringement of privacy. Existing research tends to deliver DNN models that can preserve privacy of personal information but the accuracy of these models are rather much lower as compared to their non-privacy preserving counterparts. This is due to the degree of noise and the points where noise was added to perturb the model data. Consequently, this has led to minimal adoption of privacy preserving DNN models in the industrial world. In this paper, we present a layer-wise perturbation approach and differential privacy technique to determine points of perturbation and preserve privacy. Our approach was able to narrow down the accuracy gap between privacy-preserving and non-privacy preserving DNN model.","PeriodicalId":273383,"journal":{"name":"2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"103 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"131533542","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}
Pub Date : 2019-02-01DOI: 10.1109/ICAIIC.2019.8669025
A. Irawan, G. Witjaksono, W. Wibowo
This paper proposes a deep-neural-networks scheme for decoding polar coded short packets. We consider packet transmission over frequency-flat quasi-static Rayleigh fading channels, where the channel coefficient is constant over a packet but changes packet-by-packet. Potential applications of the proposed technique are machine-type communications, messaging services, smart metering networks, and other wireless sensor networks requiring high reliability and low-latency. Computer simulations results confirm that even with simple codebook construction for an additive white Gaussian noise (AWGN) channel without fading, the proposed technique closes to the theoretical outage and achieves the coding gain in fading channel. Analyses of the learning epochs and training signal-to-noise power ratio (SNR) selections are also presented to demonstrate the effectiveness of the technique.
{"title":"Deep Learning for Polar Codes over Flat Fading Channels","authors":"A. Irawan, G. Witjaksono, W. Wibowo","doi":"10.1109/ICAIIC.2019.8669025","DOIUrl":"https://doi.org/10.1109/ICAIIC.2019.8669025","url":null,"abstract":"This paper proposes a deep-neural-networks scheme for decoding polar coded short packets. We consider packet transmission over frequency-flat quasi-static Rayleigh fading channels, where the channel coefficient is constant over a packet but changes packet-by-packet. Potential applications of the proposed technique are machine-type communications, messaging services, smart metering networks, and other wireless sensor networks requiring high reliability and low-latency. Computer simulations results confirm that even with simple codebook construction for an additive white Gaussian noise (AWGN) channel without fading, the proposed technique closes to the theoretical outage and achieves the coding gain in fading channel. Analyses of the learning epochs and training signal-to-noise power ratio (SNR) selections are also presented to demonstrate the effectiveness of the technique.","PeriodicalId":273383,"journal":{"name":"2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130876871","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}
Pub Date : 2019-02-01DOI: 10.1109/ICAIIC.2019.8669086
Jong-jin Jung, Kyung Won Kim, Jongbin Park
This paper introduces a framework of big data analysis about IoT home devices which are delivered to the consumer through several distribution channels, are used by a home user in the smart home, and are repaired in A/S center (repair shop). We collect big data and make an analysis at three major stages that are distribution stage, customer-usage stage, and A/S stage. The ultimate purpose of the presented framework is to help the small/medium companies to make an elastic strategy for the new product. Therefore they can make a more effective decision at three major stages. For example, they can reduce redundancy about a distribution channel, they can adjust a quantity of warehousing, release, stock. They can make a decision on what to upgrade the new next device, how to increase durability, and so on. For these purposes, this framework consists of three subsystems. 1) A data crawler that collects and stores big data about IoT-home devices at three major stages, 2) A big data analyzer about IoT-home device with an appreciate analytic model, 3) A visualization of insights, which help a user to understand the analytic output.
{"title":"Framework of Big data Analysis about IoT-Home-device for supporting a decision making an effective strategy about new product design","authors":"Jong-jin Jung, Kyung Won Kim, Jongbin Park","doi":"10.1109/ICAIIC.2019.8669086","DOIUrl":"https://doi.org/10.1109/ICAIIC.2019.8669086","url":null,"abstract":"This paper introduces a framework of big data analysis about IoT home devices which are delivered to the consumer through several distribution channels, are used by a home user in the smart home, and are repaired in A/S center (repair shop). We collect big data and make an analysis at three major stages that are distribution stage, customer-usage stage, and A/S stage. The ultimate purpose of the presented framework is to help the small/medium companies to make an elastic strategy for the new product. Therefore they can make a more effective decision at three major stages. For example, they can reduce redundancy about a distribution channel, they can adjust a quantity of warehousing, release, stock. They can make a decision on what to upgrade the new next device, how to increase durability, and so on. For these purposes, this framework consists of three subsystems. 1) A data crawler that collects and stores big data about IoT-home devices at three major stages, 2) A big data analyzer about IoT-home device with an appreciate analytic model, 3) A visualization of insights, which help a user to understand the analytic output.","PeriodicalId":273383,"journal":{"name":"2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"61 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"132848367","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}
Pub Date : 2019-02-01DOI: 10.1109/ICAIIC.2019.8669074
S. Jang
An intelligent mobile augmented reality (IMAR) can be a useful scheme when users want get additional information about products or objects in a store. One of the problems to be resolved in the service is how to manage huge number of augmented objects. One of the approaches is to separate object's metadata from real objects. By doing this, we can reduce amount of storage and object searching time. However, to apply such scheme seamlessly, we have to well organize each object's metadata and store them efficiently. To do this, this paper present a scheme that is based on metadata registry (MDR). In the scheme, all objects are organized in the ways specified by MDR standards.
{"title":"Object Management Based on Metadata Registry for Intelligent Mobile Augmented Reality","authors":"S. Jang","doi":"10.1109/ICAIIC.2019.8669074","DOIUrl":"https://doi.org/10.1109/ICAIIC.2019.8669074","url":null,"abstract":"An intelligent mobile augmented reality (IMAR) can be a useful scheme when users want get additional information about products or objects in a store. One of the problems to be resolved in the service is how to manage huge number of augmented objects. One of the approaches is to separate object's metadata from real objects. By doing this, we can reduce amount of storage and object searching time. However, to apply such scheme seamlessly, we have to well organize each object's metadata and store them efficiently. To do this, this paper present a scheme that is based on metadata registry (MDR). In the scheme, all objects are organized in the ways specified by MDR standards.","PeriodicalId":273383,"journal":{"name":"2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"1 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"130213329","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}
Pub Date : 2019-02-01DOI: 10.1109/ICAIIC.2019.8668841
J. M. Moon, C. Chun, Jun Ho Kim, H. Kim, Tae Kim
Since MPEG-H supports not only channel-based but also object-based audio content, there is a need for a sound source separation technique that converts channel-based to object-based audio. Among the various sound source separation techniques, azimuth-frequency (AF) based sound source separation has been proposed for converting channel-based audio to object-based audio. Unfortunately, it is difficult to set the optimal azimuth and width using this technique. In this paper, we propose a method to determine the optimal azimuth and width based on a convolutional neural network (CNN) classifier. First, depending on numerous azimuths and widths, different sets of audio signals are separated. After that, each audio set is categorized into a specific audio class using the CNN classifier. Then, in order to separate a desired audio signal, the azimuth and width with the highest similarity for a given class are selected. The performance of the CNN classifier is evaluated in terms of separation accuracy and objective measures such as signal-to-distortion ratio (SDR), signal-to-interference ratio (SIR), and signal-to-artifacts ratio (SAR). Consequently, the proposed method provides higher SDR, SAR, SIR, and separation accuracy than a minimum variance distortionless response (MVDR) beamformer as well as a method that only uses AF analysis.
{"title":"Multi-Channel Audio Source Separation Using Azimuth-Frequency Analysis and Convolutional Neural Network","authors":"J. M. Moon, C. Chun, Jun Ho Kim, H. Kim, Tae Kim","doi":"10.1109/ICAIIC.2019.8668841","DOIUrl":"https://doi.org/10.1109/ICAIIC.2019.8668841","url":null,"abstract":"Since MPEG-H supports not only channel-based but also object-based audio content, there is a need for a sound source separation technique that converts channel-based to object-based audio. Among the various sound source separation techniques, azimuth-frequency (AF) based sound source separation has been proposed for converting channel-based audio to object-based audio. Unfortunately, it is difficult to set the optimal azimuth and width using this technique. In this paper, we propose a method to determine the optimal azimuth and width based on a convolutional neural network (CNN) classifier. First, depending on numerous azimuths and widths, different sets of audio signals are separated. After that, each audio set is categorized into a specific audio class using the CNN classifier. Then, in order to separate a desired audio signal, the azimuth and width with the highest similarity for a given class are selected. The performance of the CNN classifier is evaluated in terms of separation accuracy and objective measures such as signal-to-distortion ratio (SDR), signal-to-interference ratio (SIR), and signal-to-artifacts ratio (SAR). Consequently, the proposed method provides higher SDR, SAR, SIR, and separation accuracy than a minimum variance distortionless response (MVDR) beamformer as well as a method that only uses AF analysis.","PeriodicalId":273383,"journal":{"name":"2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"17 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"129673807","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}
Pub Date : 2019-02-01DOI: 10.1109/ICAIIC.2019.8668970
Nattawat Sodsong, Kun-Ming Yu, Ouyang Wen
The fluctuation in solar photovoltaic (PV) generation system causes inefficiency in PV power management. Thus, predicting solar PV power is essential to assist PV system in improving the overall performance of a solar plant operation. In this paper, solar PV forecasting model with multiple Gated Recurrent Unit (GRU) networks is proposed to effectively improve the prediction accuracy and the training time compared to the typical GRU network. In addition, other popular prediction machine learning algorithms, namely Feed-forward Artificial Neural Network (ANN), Support Vector Regression (SVR) and K Nearest Neighbors (KNN), were implemented for comparison with the proposed model. Each model was evaluated with Normalized Root Mean Squared Error (NRMSE). The proposed model, GRU, Feed-forward ANN, SVR, and KNN has NRMSE of 9.64%, 10.53%, 11.62%, 11.45%, and 11.89%, respectively. Hence, the proposed model provides enhanced prediction accuracy with improved speed compared with a GRU network.
{"title":"Short-Term Solar PV Forecasting Using Gated Recurrent Unit with a Cascade Model","authors":"Nattawat Sodsong, Kun-Ming Yu, Ouyang Wen","doi":"10.1109/ICAIIC.2019.8668970","DOIUrl":"https://doi.org/10.1109/ICAIIC.2019.8668970","url":null,"abstract":"The fluctuation in solar photovoltaic (PV) generation system causes inefficiency in PV power management. Thus, predicting solar PV power is essential to assist PV system in improving the overall performance of a solar plant operation. In this paper, solar PV forecasting model with multiple Gated Recurrent Unit (GRU) networks is proposed to effectively improve the prediction accuracy and the training time compared to the typical GRU network. In addition, other popular prediction machine learning algorithms, namely Feed-forward Artificial Neural Network (ANN), Support Vector Regression (SVR) and K Nearest Neighbors (KNN), were implemented for comparison with the proposed model. Each model was evaluated with Normalized Root Mean Squared Error (NRMSE). The proposed model, GRU, Feed-forward ANN, SVR, and KNN has NRMSE of 9.64%, 10.53%, 11.62%, 11.45%, and 11.89%, respectively. Hence, the proposed model provides enhanced prediction accuracy with improved speed compared with a GRU network.","PeriodicalId":273383,"journal":{"name":"2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"22 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125425836","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}
Pub Date : 2019-02-01DOI: 10.1109/ICAIIC.2019.8668995
Junghoon Woo, Joo-Yeop Song, Young-June Choi
Machine learning enables intrusion detection systems to detect network attacks adaptively and intelligently. Recently deep neural network has been investigated as such a solution owing to its high accuracy but it has limitation in real-time performance. To enhance the learning time, in this paper, we propose to use feature selection and layer configuration. We use the NSL-KDD data set, which is a refined version of the KDD CUP 99 data set and analyzed the associations between features using WEKA, a data mining tool. Our experimental results confirm that proper feature selection and layer configuration can reduce learning time while maintaining high average accuracy.
机器学习使入侵检测系统能够自适应地、智能地检测网络攻击。近年来，深度神经网络因其精度高而被研究作为一种解决方案，但在实时性方面存在局限性。为了提高学习时间，在本文中，我们提出使用特征选择和层配置。我们使用NSL-KDD数据集，这是KDD CUP 99数据集的改进版本，并使用数据挖掘工具WEKA分析了特征之间的关联。实验结果表明，适当的特征选择和层配置可以减少学习时间，同时保持较高的平均准确率。
{"title":"Performance Enhancement of Deep Neural Network Using Feature Selection and Preprocessing for Intrusion Detection","authors":"Junghoon Woo, Joo-Yeop Song, Young-June Choi","doi":"10.1109/ICAIIC.2019.8668995","DOIUrl":"https://doi.org/10.1109/ICAIIC.2019.8668995","url":null,"abstract":"Machine learning enables intrusion detection systems to detect network attacks adaptively and intelligently. Recently deep neural network has been investigated as such a solution owing to its high accuracy but it has limitation in real-time performance. To enhance the learning time, in this paper, we propose to use feature selection and layer configuration. We use the NSL-KDD data set, which is a refined version of the KDD CUP 99 data set and analyzed the associations between features using WEKA, a data mining tool. Our experimental results confirm that proper feature selection and layer configuration can reduce learning time while maintaining high average accuracy.","PeriodicalId":273383,"journal":{"name":"2019 International Conference on Artificial Intelligence in Information and Communication (ICAIIC)","volume":"2 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2019-02-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125152468","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}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：