Matches in SemOpenAlex for { <https://semopenalex.org/work/W3088665058> ?p ?o ?g. }
- W3088665058 endingPage "2676" @default.
- W3088665058 startingPage "2662" @default.
- W3088665058 abstract "We present a processing pipeline for flow-based traffic classification using a machine learning component leveraging Deep Neural Networks (DNNs). The system is trained to predict likely characteristics of real-world traffic flows from a campus network ahead of time, e.g., a flow's throughput or duration. Training and evaluation of DNN models are continuously performed on a flow data stream collected from a university data center. Instead of the common binary classification into “mice” and “elephant” (throughput) or “short-term” and “long-term” (duration) flows, predicted flow characteristics are quantized into three classes. Various communication contexts (subset of network traffic, e.g., only TCP) and flow feature groups (subset of flow features, e.g., only a flow's 5-tuple), which are supported through an enrichment strategy, are considered and investigated. An in-depth description of the data acquisition process, including preprocessing steps and anonymization used to protect sensitive information, is given. Additionally, we employ an accelerated variant of t-distributed Stochastic Neighbor Embedding (t-SNE) to visualize network traffic data. This enables the understanding of traffic characteristics and relations between communication flows at a glance. Furthermore, possible use-cases and a high-level architecture for flow-based routing scenarios utilizing the developed pipeline are proposed." @default.
- W3088665058 created "2020-10-01" @default.
- W3088665058 creator A5007226831 @default.
- W3088665058 creator A5030810660 @default.
- W3088665058 creator A5057029027 @default.
- W3088665058 creator A5073874147 @default.
- W3088665058 date "2020-12-01" @default.
- W3088665058 modified "2023-10-17" @default.
- W3088665058 title "Predicting Network Flow Characteristics Using Deep Learning and Real-World Network Traffic" @default.
- W3088665058 cites W1994926493 @default.
- W3088665058 cites W2040340473 @default.
- W3088665058 cites W2056665251 @default.
- W3088665058 cites W2065889189 @default.
- W3088665058 cites W2069354103 @default.
- W3088665058 cites W2096118443 @default.
- W3088665058 cites W2147118406 @default.
- W3088665058 cites W2167403301 @default.
- W3088665058 cites W2168595508 @default.
- W3088665058 cites W2260783129 @default.
- W3088665058 cites W2268383675 @default.
- W3088665058 cites W2511505324 @default.
- W3088665058 cites W2522019248 @default.
- W3088665058 cites W2551429935 @default.
- W3088665058 cites W2567615407 @default.
- W3088665058 cites W2617931713 @default.
- W3088665058 cites W2759910885 @default.
- W3088665058 cites W2768254111 @default.
- W3088665058 cites W2783034914 @default.
- W3088665058 cites W2809684781 @default.
- W3088665058 cites W2883529420 @default.
- W3088665058 cites W2902912511 @default.
- W3088665058 cites W2913856657 @default.
- W3088665058 cites W2954607187 @default.
- W3088665058 cites W2962862703 @default.
- W3088665058 cites W2969984724 @default.
- W3088665058 cites W2972276771 @default.
- W3088665058 cites W2973082347 @default.
- W3088665058 cites W2978285052 @default.
- W3088665058 cites W2980887937 @default.
- W3088665058 cites W2990103141 @default.
- W3088665058 cites W3010002476 @default.
- W3088665058 cites W3126135128 @default.
- W3088665058 doi "https://doi.org/10.1109/tnsm.2020.3025131" @default.
- W3088665058 hasPublicationYear "2020" @default.
- W3088665058 type Work @default.
- W3088665058 sameAs 3088665058 @default.
- W3088665058 citedByCount "23" @default.
- W3088665058 countsByYear W30886650582020 @default.
- W3088665058 countsByYear W30886650582021 @default.
- W3088665058 countsByYear W30886650582022 @default.
- W3088665058 countsByYear W30886650582023 @default.
- W3088665058 crossrefType "journal-article" @default.
- W3088665058 hasAuthorship W3088665058A5007226831 @default.
- W3088665058 hasAuthorship W3088665058A5030810660 @default.
- W3088665058 hasAuthorship W3088665058A5057029027 @default.
- W3088665058 hasAuthorship W3088665058A5073874147 @default.
- W3088665058 hasBestOaLocation W30886650581 @default.
- W3088665058 hasConcept C108583219 @default.
- W3088665058 hasConcept C114809511 @default.
- W3088665058 hasConcept C120314980 @default.
- W3088665058 hasConcept C124101348 @default.
- W3088665058 hasConcept C126255220 @default.
- W3088665058 hasConcept C138885662 @default.
- W3088665058 hasConcept C154945302 @default.
- W3088665058 hasConcept C157764524 @default.
- W3088665058 hasConcept C158379750 @default.
- W3088665058 hasConcept C169988225 @default.
- W3088665058 hasConcept C199360897 @default.
- W3088665058 hasConcept C207512268 @default.
- W3088665058 hasConcept C2776401178 @default.
- W3088665058 hasConcept C31258907 @default.
- W3088665058 hasConcept C33923547 @default.
- W3088665058 hasConcept C34736171 @default.
- W3088665058 hasConcept C41008148 @default.
- W3088665058 hasConcept C41895202 @default.
- W3088665058 hasConcept C43521106 @default.
- W3088665058 hasConcept C489000 @default.
- W3088665058 hasConcept C555944384 @default.
- W3088665058 hasConcept C76155785 @default.
- W3088665058 hasConcept C77088390 @default.
- W3088665058 hasConcept C79403827 @default.
- W3088665058 hasConceptScore W3088665058C108583219 @default.
- W3088665058 hasConceptScore W3088665058C114809511 @default.
- W3088665058 hasConceptScore W3088665058C120314980 @default.
- W3088665058 hasConceptScore W3088665058C124101348 @default.
- W3088665058 hasConceptScore W3088665058C126255220 @default.
- W3088665058 hasConceptScore W3088665058C138885662 @default.
- W3088665058 hasConceptScore W3088665058C154945302 @default.
- W3088665058 hasConceptScore W3088665058C157764524 @default.
- W3088665058 hasConceptScore W3088665058C158379750 @default.
- W3088665058 hasConceptScore W3088665058C169988225 @default.
- W3088665058 hasConceptScore W3088665058C199360897 @default.
- W3088665058 hasConceptScore W3088665058C207512268 @default.
- W3088665058 hasConceptScore W3088665058C2776401178 @default.
- W3088665058 hasConceptScore W3088665058C31258907 @default.
- W3088665058 hasConceptScore W3088665058C33923547 @default.
- W3088665058 hasConceptScore W3088665058C34736171 @default.
- W3088665058 hasConceptScore W3088665058C41008148 @default.