{"status":"ok","message-type":"work","message-version":"1.0.0","message":{"indexed":{"date-parts":[[2026,7,22]],"date-time":"2026-07-22T16:33:23Z","timestamp":1784738003962,"version":"3.55.0"},"reference-count":82,"publisher":"Wiley","license":[{"start":{"date-parts":[[2023,6,22]],"date-time":"2023-06-22T00:00:00Z","timestamp":1687392000000},"content-version":"unspecified","delay-in-days":0,"URL":"https:\/\/creativecommons.org\/licenses\/by\/4.0\/"}],"content-domain":{"domain":[],"crossmark-restriction":false},"short-container-title":["Journal of Computer Networks and Communications"],"published-print":{"date-parts":[[2023,6,22]]},"abstract":"<jats:p>Currently, the widespread of real-time applications such as VoIP and videos-based applications require more data rates and reduced latency to ensure better quality of service (QoS). A well-designed traffic classification mechanism plays a major role for good QoS provision and network security verification. Port-based approaches and deep packet inspection (DPI) techniques have been used to classify and analyze network traffic flows. However, none of these methods can cope with the rapid growth of network traffic due to the increasing number of Internet users and the growth of real-time applications. As a result, these methods lead to network congestion, resulting in packet loss, delay, and inadequate QoS delivery. Recently, a deep learning approach has been explored to address the time-consumption and impracticality gaps of the abovementioned methods and maintain existing and future traffics of real-time applications. The aim of this research is then to design a dynamic traffic classifier that can detect elephant flows to prevent network congestion. Thus, we are motivated to provide efficient bandwidth and fast transmission requirements to many Internet users using SDN capability and the potential of deep learning. Specifically, DNN, CNN, LSTM, and Deep autoencoder are used to build elephant detection models that achieve an average accuracy of 99.12%, 98.17%, and 98.78%, respectively. Deep autoencoder is also one of the promising algorithms that do not require human class labeler. It achieves an accuracy of 97.95% with a loss of 0.13. Since the loss value is closer to zero, the performance of the model is good. Therefore, the study has a great importance to Internet service providers, Internet subscribers, as well as for future researchers in this area.<\/jats:p>","DOI":"10.1155\/2023\/1495642","type":"journal-article","created":{"date-parts":[[2023,6,22]],"date-time":"2023-06-22T23:29:51Z","timestamp":1687476591000},"page":"1-18","source":"Crossref","is-referenced-by-count":10,"title":["Elephant Flows Detection Using Deep Neural Network, Convolutional Neural Network, Long Short-Term Memory, and Autoencoder"],"prefix":"10.1155","volume":"2023","author":[{"ORCID":"https:\/\/orcid.org\/0000-0002-0348-3824","authenticated-orcid":true,"given":"Getahun","family":"Wassie Geremew","sequence":"first","affiliation":[{"name":"IP Networking and Mobile Internet Track, Addis Ababa University, Addis Ababa, Ethiopia"}],"role":[{"vocabulary":"crossref","role":"author"}]},{"ORCID":"https:\/\/orcid.org\/0000-0002-8927-0968","authenticated-orcid":true,"given":"Jianguo","family":"Ding","sequence":"additional","affiliation":[{"name":"Department of Computer Science, Blekinge Institute of Technology, 37179 Karlskrona, Sweden"}],"role":[{"vocabulary":"crossref","role":"author"}]}],"member":"311","reference":[{"key":"1","doi-asserted-by":"publisher","DOI":"10.1109\/tnsm.2022.3150664"},{"key":"2","doi-asserted-by":"crossref","article-title":"SDN-based architecture for providing QoS to high performance distributed applications","author":"A. T. Oliveira","DOI":"10.1109\/ISCC.2018.8538694"},{"key":"3","doi-asserted-by":"publisher","DOI":"10.11113\/jt.v64.2079"},{"key":"4","article-title":"Bilal KhaContinuance intention to use digital payments in mitigating the spread of COVID-19 virus","volume":"6","author":"B. Khalida","year":"2022","journal-title":"International Journal of Data and Network Science"},{"key":"5","article-title":"Cloud computing classroom acceptance model in Thailand higher education's institutes A conceptual framework","author":"P. W. Singha"},{"key":"6","article-title":"QOS for multimedia applications with emphasize on video conferencing","volume-title":"Modern Communication System and Networks","author":"A. Gholamhosseinian","year":"2011"},{"key":"7","article-title":"Touchdown on the cloud:the impact of the super bowl on cloud","author":"C. Wang"},{"key":"8","article-title":"Hierarchical video frame sequence representation with deep convolutional graph network","author":"M. Feng"},{"key":"9","doi-asserted-by":"publisher","DOI":"10.1109\/tnet.2020.3002783"},{"key":"10","article-title":"Classifying elephant and mice flows in high-speed scientific networks","author":"A. Chhabra"},{"key":"11","doi-asserted-by":"publisher","DOI":"10.1109\/access.2020.2987977"},{"key":"12","doi-asserted-by":"crossref","article-title":"Investigation of machine learning based network traffic classification","author":"Fan","DOI":"10.1109\/ISWCS.2017.8108090"},{"key":"13","article-title":"Online encrypted Skype identification based on an updating mechanism","author":"D. Shi","year":"2022"},{"key":"14","article-title":"Deep packet: a novel approach for encrypted trafic classification using deep learning","author":"M. J. Siavoshani","year":"2018"},{"key":"15","doi-asserted-by":"publisher","DOI":"10.14569\/ijacsa.2010.010102"},{"key":"16","doi-asserted-by":"publisher","DOI":"10.15837\/ijccc.2014.6.234"},{"key":"17","article-title":"Optimal QoS-aware network reconfiguration in software defined cloud data centers","volume":"120","author":"B. Akbari","year":"2017","journal-title":"Computer Networks"},{"key":"18","article-title":"Deep packet inspection as a service","author":"Y. Harchol"},{"key":"19","article-title":"Traffic classification model based on integration of multiple classifiers","volume":"8","author":"D. Z. Shi","year":"2012","journal-title":"Journal of Computational Information Systems"},{"key":"20","doi-asserted-by":"publisher","DOI":"10.1016\/j.eswa.2021.114885"},{"key":"21","doi-asserted-by":"publisher","DOI":"10.1016\/j.cosrev.2021.100379"},{"key":"22","article-title":"Neural packet classification","author":"H. Zhu","year":"2019"},{"key":"23","doi-asserted-by":"publisher","DOI":"10.1016\/j.ijin.2021.06.002"},{"key":"24","doi-asserted-by":"crossref","DOI":"10.1201\/9781003161233","article-title":"Foundations of deep learning and its applications to health informatics","volume-title":"Deep Learning in Biomedical and Health Informatics,","author":"M. A. Jabbar","year":"2021"},{"key":"25","doi-asserted-by":"publisher","DOI":"10.1007\/s10462-020-09825-6"},{"key":"26","volume-title":"Deep Learning with Python","author":"C. ran\u00e7ois","year":"2018"},{"key":"27","article-title":"LSTM-autoencoder based anomaly detection for indoor air quality time series data","author":"Y. Wei","year":"2022"},{"key":"28","doi-asserted-by":"crossref","DOI":"10.3390\/make4020015","volume-title":"An Attention-Based ConvLSTM Autoencoder with Dynamic Thresholding for Unsupervised Anomaly Detection in Multivariate Time Series","author":"T. Tayeh","year":"2022"},{"key":"29","doi-asserted-by":"publisher","DOI":"10.1109\/tnse.2020.3009832"},{"key":"30","doi-asserted-by":"publisher","DOI":"10.1109\/tnsm.2019.2899085"},{"key":"31","article-title":"SDN-based overlay networks for QoS-aware routing","author":"B. Pablo"},{"key":"32","article-title":"Real-time QoS-aware routing scheme in SDN-based robotic cyber-physical systems","author":"H. Rutvij"},{"key":"33","article-title":"Network traffic classification techniques and challenges","author":"Noora"},{"key":"34","doi-asserted-by":"publisher","DOI":"10.14569\/ijacsa.2022.0130414"},{"key":"35","doi-asserted-by":"publisher","DOI":"10.1109\/tnsm.2021.3098157"},{"key":"36","doi-asserted-by":"publisher","DOI":"10.1007\/s12243-021-00876-6"},{"key":"37","article-title":"Intelligent SDN traffic classification using deep learning","author":"M. Ali"},{"key":"38","doi-asserted-by":"publisher","DOI":"10.1109\/tnsm.2021.3120804"},{"key":"39","doi-asserted-by":"publisher","DOI":"10.1016\/j.dcan.2022.02.003"},{"key":"40","article-title":"Fs-net: a flow sequence network for encrypted traffic classification","author":"L. Chang"},{"key":"41","article-title":"An efficient internet traffic classification system using deep learning for IoT","author":"M. Basit","year":"2021"},{"key":"42","doi-asserted-by":"publisher","DOI":"10.1007\/s00521-017-3081-x"},{"key":"43","article-title":"Deep learning for network traffic classification","author":"W. J. Niloofar","year":"2021"},{"issue":"2","key":"44","article-title":"Deep learning based traffic classification in software defined networking","volume":"9","author":"R. T. K. Tamil Selvi","year":"2020","journal-title":"International Journal Of Scientific and Technology Research"},{"key":"45","doi-asserted-by":"crossref","first-page":"3414","DOI":"10.3390\/app9163414","article-title":"An LSTM-Based Deep Learning Approach for Classifying Malicious Traffic at the Packet Level","volume":"9","author":"H. Ren-Hung","year":"2019","journal-title":"Applied Sciences"},{"key":"46","doi-asserted-by":"publisher","DOI":"10.3390\/s17091967"},{"key":"47","doi-asserted-by":"publisher","DOI":"10.3390\/cancers13092013"},{"key":"48","doi-asserted-by":"publisher","DOI":"10.3390\/s21227731"},{"issue":"4","key":"49","doi-asserted-by":"crossref","first-page":"420","DOI":"10.3844\/ajassp.2016.420.431","article-title":"Online traffic measurement and analysis in big data: comparative research review","volume":"13","author":"L. T. Ibrahim","year":"2016","journal-title":"American Journal of Applied Sciences"},{"key":"50","article-title":"Feature selection algorithm based on correlation between muti metric network traffic flow features","volume":"14","author":"D. Shi","year":"2017","journal-title":"The International Arab Journal of Information Technology"},{"key":"51","article-title":"A classification supervised auto-encoder based on predefined evenly-distributed class centroids","volume-title":"School of Communication and Information Engineering","author":"Q. Zhang","year":"2019"},{"key":"52","doi-asserted-by":"publisher","DOI":"10.1016\/j.comnet.2010.12.002"},{"key":"53","article-title":"Nicauca Version2 dataset","author":"zgzhengSEU","year":"2021"},{"key":"54","article-title":"Identifying elephant flows using dynamic thresholds in programmable IXP networks","volume":"11","author":"B. Marcus Vinicius","year":"2020","journal-title":"Journal of Internet Services and Applications"},{"key":"55","volume-title":"Cisco Application Centric Infrastructure","author":"G. Tam","year":"2018"},{"key":"56","volume-title":"A Survey on Deep Learning: Algorithms, Techniques, and Applications","author":"P. Samira","year":"2018"},{"key":"57","article-title":"Deep learning techniques: an overview","author":"P. Amudha"},{"key":"58","article-title":"Decision tree-based blending method using deep-learning for network management","author":"Ons"},{"key":"59","doi-asserted-by":"publisher","DOI":"10.1155\/2021\/5518460"},{"key":"60","article-title":"Intelligent traffic management in next-generation networks","volume":"14","author":"K. Piamrat","year":"2022","journal-title":"Future Internet"},{"key":"61","article-title":"A neural network architecture for learning dynamical systems","volume":"35","author":"D. Piga","year":"2021","journal-title":"IDSIA Dalle Molle Institute for Artificial Intelligence"},{"key":"62","volume-title":"Automated Leaf Disease Detection and Treatment Recommendation Using Transfer Learning","author":"S. Malpe","year":"2019"},{"key":"63","volume-title":"Underfitting and Overfitting in Machine Learning","author":"J. Bilmes","year":"2020"},{"key":"64","article-title":"Autoencoder","author":"N. Koenigstein","year":"2020"},{"key":"65","volume-title":"TinyFlow: Breaking Elephants Down into Mice in Data Center Networks","author":"H. Xu","year":"2014"},{"key":"66","doi-asserted-by":"publisher","DOI":"10.3390\/cancers13092013"},{"key":"67","doi-asserted-by":"publisher","DOI":"10.1016\/j.ejor.2017.11.054"},{"key":"68","doi-asserted-by":"publisher","DOI":"10.1145\/3324884.3416545"},{"key":"69","article-title":"Network traffic classification using machine learning for software defined networks","author":"K. Piamrat"},{"issue":"6","key":"70","article-title":"Significance of epochs on training A neural network","volume":"9","author":"S. Rao Saahil Afaq","year":"2020","journal-title":"International Journal Of Scientific and Technology Research"},{"key":"71","doi-asserted-by":"publisher","DOI":"10.3171\/2019.10.JNS191251"},{"key":"72","article-title":"Speedy performance estimation for neural architecture search","author":"B. Ru","year":"2021"},{"key":"73","article-title":"Pre-interpolation loss behaviour in neural networks","author":"M. W. Theunissen","year":"2021"},{"key":"74","article-title":"Concise logarithmic loss function for robust training of anomaly detection model","author":"Y. H. Park","year":"2022"},{"key":"75","article-title":"How training data affect the accuracy and robustness of neural networks for image classification","author":"L. Suhua","year":"2018"},{"key":"76","doi-asserted-by":"publisher","DOI":"10.3390\/su13126527"},{"key":"77","article-title":"Empirical comparison between autoencoders and traditional dimensionality reduction methods","author":"Quentin"},{"key":"78","article-title":"A review of deep learning with special emphasis on architectures, applications and recent trends","volume":"20","author":"A. Sengupta","year":"2019","journal-title":"IEEE Transaction on XXX"},{"key":"79","doi-asserted-by":"publisher","DOI":"10.1515\/itms-2017-0003"},{"issue":"1","key":"80","first-page":"143","article-title":"Predicting drug response of tumors from integrated genomic profiles by deep neural network","volume":"12","author":"Y. Chia","year":"2019","journal-title":"BMC Medical Genomics"},{"key":"81","article-title":"An introduction to computer networks","author":"L. D. Peter","year":"2020"},{"key":"82","volume-title":"Towards Image Classification with Machine Learning Methodologies for Smartphones","author":"L. Zhu","year":"2019"}],"container-title":["Journal of Computer Networks and Communications"],"original-title":[],"language":"en","link":[{"URL":"http:\/\/downloads.hindawi.com\/journals\/jcnc\/2023\/1495642.pdf","content-type":"application\/pdf","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/jcnc\/2023\/1495642.xml","content-type":"application\/xml","content-version":"vor","intended-application":"text-mining"},{"URL":"http:\/\/downloads.hindawi.com\/journals\/jcnc\/2023\/1495642.pdf","content-type":"unspecified","content-version":"vor","intended-application":"similarity-checking"}],"deposited":{"date-parts":[[2023,6,22]],"date-time":"2023-06-22T23:30:10Z","timestamp":1687476610000},"score":1,"resource":{"primary":{"URL":"https:\/\/www.hindawi.com\/journals\/jcnc\/2023\/1495642\/"}},"subtitle":[],"editor":[{"given":"Giovanni","family":"Pau","sequence":"additional","affiliation":[],"role":[{"vocabulary":"crossref","role":"editor"}]}],"short-title":[],"issued":{"date-parts":[[2023,6,22]]},"references-count":82,"alternative-id":["1495642","1495642"],"URL":"https:\/\/doi.org\/10.1155\/2023\/1495642","relation":{},"ISSN":["2090-715X","2090-7141"],"issn-type":[{"value":"2090-715X","type":"electronic"},{"value":"2090-7141","type":"print"}],"subject":[],"published":{"date-parts":[[2023,6,22]]}}}