{"corpus_id":53776110,"paper_sha":"7848098e71692bc6b104b01bafdff9d311370f63","doi":"10.1109/COMST.2018.2846401","arxiv_id":null,"pmid":null,"pmcid":null,"mag_id":2807731816,"dblp_id":"journals/comsur/MaoHH18","acl_id":null,"title":"Deep Learning for Intelligent Wireless Networks: A Comprehensive Survey","year":2018,"publication_date":"2018-06-12","venue":"IEEE Communications Surveys and Tutorials","journal":{"name":"IEEE Communications Surveys & Tutorials","pages":"2595-2621","volume":"20"},"journal_issn":null,"journal_title":null,"publication_types":["JournalArticle","Review"],"pubmed_pub_types":null,"s2_fields_of_study":["Computer Science","Engineering"],"reference_count":118,"citation_count":689,"influential_citation_count":19,"is_open_access":false,"arxiv_categories":null,"arxiv_license":null,"arxiv_journal_ref":null,"mesh_headings":null,"chemicals":null,"comments_corrections":null,"source_flags":1,"s2_open_access_pdf_url":null,"s2_open_access_landing_url":null,"s2_open_access_license":null,"s2_open_access_status":null,"pmc_open_access_pdf_url":null,"pmc_open_access_landing_url":null,"pmc_open_access_license":null,"pmc_open_access_status":null,"unpaywall_open_access_pdf_url":null,"unpaywall_open_access_landing_url":null,"unpaywall_open_access_license":null,"unpaywall_open_access_status":null,"abstract":"As a promising machine learning tool to handle the accurate pattern recognition from complex raw data, deep learning (DL) is becoming a powerful method to add intelligence to wireless networks with large-scale topology and complex radio conditions. DL uses many neural network layers to achieve a brain-like acute feature extraction from high-dimensional raw data. It can be used to find the network dynamics (such as hotspots, interference distribution, congestion points, traffic bottlenecks, spectrum availability, etc.) based on the analysis of a large amount of network parameters (such as delay, loss rate, link signal-to-noise ratio, etc.). Therefore, DL can analyze extremely complex wireless networks with many nodes and dynamic link quality. This paper performs a comprehensive survey of the applications of DL algorithms for different network layers, including physical layer modulation/coding, data link layer access control/resource allocation, and routing layer path search, and traffic balancing. The use of DL to enhance other network functions, such as network security, sensing data compression, etc., is also discussed. Moreover, the challenging unsolved research issues in this field are discussed in detail, which represent the future research trends of DL-based wireless networks. This paper can help the readers to deeply understand the state-of-the-art of the DL-based wireless network designs, and select interesting unsolved issues to pursue in their research.","claims":[{"public_id":"cl_4c5b1d8379695e76a0ec8fefb5cdc0fa","status":"active","text":"Applications of deep learning are reviewed across the physical layer, data link layer, and routing layer, including modulation/coding, access control/resource allocation, path search, and traffic balancing.","confidence":0.96,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_4c5b1d8379695e76a0ec8fefb5cdc0fa"},{"public_id":"cl_a20275a9828bda01864db8cd9d23a3f5","status":"active","text":"Deep learning can identify network dynamics such as hotspots, interference distribution, congestion points, traffic bottlenecks, and spectrum availability from large sets of network parameters.","confidence":0.91,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_a20275a9828bda01864db8cd9d23a3f5"},{"public_id":"cl_a88cd89c8d8562f96a9db4fdd1e496e6","status":"active","text":"Deep learning is surveyed as an enabling approach for adding intelligence to wireless networks with large-scale topology and complex radio conditions.","confidence":0.95,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_a88cd89c8d8562f96a9db4fdd1e496e6"},{"public_id":"cl_05a37e139af4c3a18cdf81ea3605c156","status":"active","text":"Deep learning-based approaches for network security and sensing data compression are also discussed as additional wireless-network functions.","confidence":0.86,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_05a37e139af4c3a18cdf81ea3605c156"},{"public_id":"cl_a6614ada99c2d428fdf8e691fa97de40","status":"active","text":"Unsolved research issues in deep learning-based wireless networks are identified as future research trends.","confidence":0.89,"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/claims/cl_a6614ada99c2d428fdf8e691fa97de40"}],"concepts":[{"public_id":"co_2ac83dcd8d764fbe6707b302a9f8d69f","status":"active","name":"sensing data compression","description":"Compression of sensed data to reduce communication or storage requirements.","types":["signal processing function"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_2ac83dcd8d764fbe6707b302a9f8d69f"},{"public_id":"co_31724bc430dc3cbe787e5ec434de78b6","status":"active","name":"network security","description":"Protection of networked systems and communications against unauthorized access or attacks.","types":["network function"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_31724bc430dc3cbe787e5ec434de78b6"},{"public_id":"co_39194cfd31b5f04df06bfa8f3d921dfb","status":"active","name":"future research trends","description":"Likely directions for subsequent research identified from open problems and challenges.","types":["research direction"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_39194cfd31b5f04df06bfa8f3d921dfb"},{"public_id":"co_3c2c009248361024e7e46e859caa5c02","status":"active","name":"wireless networks","description":"Networks that communicate over radio links and may have dynamic topology and varying channel conditions.","types":["system"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_3c2c009248361024e7e46e859caa5c02"},{"public_id":"co_47861690c84d7d65ee1fce6a19aedfb5","status":"active","name":"traffic balancing","description":"Methods for distributing network load to avoid congestion and improve performance.","types":["network function"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_47861690c84d7d65ee1fce6a19aedfb5"},{"public_id":"co_52aca6651d610b7aed58b6599a4e155c","status":"active","name":"network dynamics","description":"Time-varying operational patterns in a network, such as congestion, interference, and traffic hotspots.","types":["phenomenon"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_52aca6651d610b7aed58b6599a4e155c"},{"public_id":"co_603965af0f82369e26536561c956a908","status":"active","name":"routing layer path search","description":"Routing-layer procedures for finding paths through a network.","types":["network layer function"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_603965af0f82369e26536561c956a908"},{"public_id":"co_82ff538af8a3a4fc3313afeaa59f9e88","status":"active","name":"deep learning","description":"A machine learning approach using multiple neural network layers to learn representations from data.","types":["method"],"aliases":["DL"],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_82ff538af8a3a4fc3313afeaa59f9e88"},{"public_id":"co_c05749492de1b9c929711f8802d57a55","status":"active","name":"data link layer access control/resource allocation","description":"Data-link-layer mechanisms for controlling medium access and allocating network resources.","types":["network layer function"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_c05749492de1b9c929711f8802d57a55"},{"public_id":"co_c71f49efd395aabb9c9a214a9efb10fb","status":"active","name":"unsolved research issues","description":"Open problems in the surveyed area that remain unresolved.","types":["research topic"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_c71f49efd395aabb9c9a214a9efb10fb"},{"public_id":"co_ed880881edf56c9b448e0e722e1f3ebf","status":"active","name":"physical layer modulation/coding","description":"Physical-layer techniques for transmitting information using modulation and channel coding.","types":["network layer function"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_ed880881edf56c9b448e0e722e1f3ebf"},{"public_id":"co_fccc3c57efa7772c7c272e80f44406f9","status":"active","name":"network parameters","description":"Measured quantities used to characterize network performance, such as delay, loss rate, and signal-to-noise ratio.","types":["measurement"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_fccc3c57efa7772c7c272e80f44406f9"},{"public_id":"co_ff4588ecb1b49c0b56310be8e496dff1","status":"active","name":"deep learning-based wireless networks","description":"Wireless-network designs that incorporate deep learning methods for analysis or control.","types":["system"],"aliases":[],"contributors":[{"id":1,"public_id":"12632b8b5f","public_label":"Anonymous (12632b8b5f)","roles":["extraction"],"url":"https://sah.borca.ai/u/12632b8b5f"}],"url":"https://sah.borca.ai/concepts/co_ff4588ecb1b49c0b56310be8e496dff1"}],"external_ids":{"DOI":"10.1109/COMST.2018.2846401","ArXiv":null,"PubMed":null,"PubMedCentral":null,"MAG":2807731816,"DBLP":"journals/comsur/MaoHH18","ACL":null},"open_access":{"is_open_access":false,"pdf_url":null,"landing_url":"https://sah.borca.ai/papers/53776110","source":null,"pdf_url_source":null,"license":null,"reason":"pdf_url_not_indexed"},"reference_availability":{"status":"available","references_indexed":true,"full_text_available":false,"full_text_source":null,"count_basis":"semantic_scholar_metadata","extraction_status":"not_applicable","reason":null},"source":{"provider":"episteme2","base_corpus":"semantic_scholar_dump","freshness_mode":"unknown","basis":["semantic_scholar_metadata","postgres_metadata"],"limits":["paper metadata is based on indexed upstream scholarly datasets","claims and concepts are available only for extracted papers","absence of claims or concepts means no extracted graph data is available in this response"],"status":"available","degraded":false,"degraded_reasons":[],"diagnostics":{"status":"available","degraded":false,"degraded_reasons":[],"metadata_status":"available","graph_status":"available","abstract_status":"available"},"source_flags":1},"paper_id":635171,"paper_uid":"9be68f41-f576-4c7c-a8e7-95edef96db80","canonical_identity":{"paper_id":635171,"paper_uid":"9be68f41-f576-4c7c-a8e7-95edef96db80","identity_status":"available","lookup_basis":"semantic_scholar_external_id","compatibility_path":"corpus_id"},"url":"https://sah.borca.ai/papers/53776110"}