{"id":25444177,"url":"https://github.com/dioptx/inhalesense","last_synced_at":"2025-11-01T18:30:33.196Z","repository":{"id":78768370,"uuid":"181346052","full_name":"dioptx/InhaleSense","owner":"dioptx","description":"A deep learning approach for respiratory audio discovery and classification.","archived":false,"fork":false,"pushed_at":"2024-09-30T12:57:13.000Z","size":52287,"stargazers_count":7,"open_issues_count":2,"forks_count":3,"subscribers_count":4,"default_branch":"master","last_synced_at":"2025-02-15T19:16:23.408Z","etag":null,"topics":[],"latest_commit_sha":null,"homepage":"","language":"Jupyter Notebook","has_issues":true,"has_wiki":null,"has_pages":null,"mirror_url":null,"source_name":null,"license":"mit","status":null,"scm":"git","pull_requests_enabled":true,"icon_url":"https://github.com/dioptx.png","metadata":{"files":{"readme":"README.md","changelog":null,"contributing":null,"funding":null,"license":"LICENSE","code_of_conduct":null,"threat_model":null,"audit":null,"citation":null,"codeowners":null,"security":null,"support":null,"governance":null}},"created_at":"2019-04-14T17:40:14.000Z","updated_at":"2024-10-21T15:08:30.000Z","dependencies_parsed_at":"2023-07-21T12:39:53.962Z","dependency_job_id":null,"html_url":"https://github.com/dioptx/InhaleSense","commit_stats":null,"previous_names":["dioptx/inhalesense"],"tags_count":0,"template":false,"template_full_name":null,"repository_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dioptx%2FInhaleSense","tags_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dioptx%2FInhaleSense/tags","releases_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dioptx%2FInhaleSense/releases","manifests_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories/dioptx%2FInhaleSense/manifests","owner_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners/dioptx","download_url":"https://codeload.github.com/dioptx/InhaleSense/tar.gz/refs/heads/master","host":{"name":"GitHub","url":"https://github.com","kind":"github","repositories_count":239315439,"owners_count":19618768,"icon_url":"https://github.com/github.png","version":null,"created_at":"2022-05-30T11:31:42.601Z","updated_at":"2022-07-04T15:15:14.044Z","host_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub","repositories_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repositories","repository_names_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/repository_names","owners_url":"https://repos.ecosyste.ms/api/v1/hosts/GitHub/owners"}},"keywords":[],"created_at":"2025-02-17T15:29:46.561Z","updated_at":"2025-11-01T18:30:33.154Z","avatar_url":"https://github.com/dioptx.png","language":"Jupyter Notebook","funding_links":[],"categories":[],"sub_categories":[],"readme":"# InhaleSense\n\nThe goal of this project is to produce a deep learning model that discovers and classifies sections of interest in audio files.\n\n\nThe dataset used for the initial stage of the implementation is not provided. \n\n[Research Gate \u0026 Publication Link](https://www.researchgate.net/publication/335135907_Recognition_of_breathing_activity_and_medication_adherence_using_LSTM_Neural_Networks)\n\n### Authors of the publication:\n- Dionisis Pettas (dennis.petta@gmail.com)\n- Stavros Nousias (nousias.stavros@gmail.com)\n- Evangelia Zacharaki (ezachar@upatras.gr)\n\n### Some other notes:\n\n\n- The approach makes use of a simple LSTM model in order to discover inhalations, exhalations and Drug administration in \n.wav audio files.\n\n- A trained model can be found in the data section.\n\n- The preparation and processing files house utility functions whereas the Jupyter notebooks provide some usecases based on the dataset\ndescribed in the paper: \n__Recognition of breathing activity and medication\nadherence using LSTM Neural Networks - BIBE 2019__\n\n- The environment for this project can be replicated with the environment.yml file provided.\n\n- The dataset used for this paper is only accessible by request, but the model works with any .wav file containing respiratory sounds.\n\n\n\n### Demo with dataset included\n\nAn extended version of the code also including and comparing other methods is made available:\n\n- https://codeocean.com/capsule/8383844/tree/ \n- https://github.com/snousias/Revisiting-Content-Based-Audio-Classification-for-Asthma-Medication-Adherence/tree/master\n\n\n### Dataset on IEEE Dataport\n\nThe dataset is available in IEEE Dataport and the dataset format can be summarized as follows: \n\nLink:\n\n- https://ieee-dataport.org/documents/respiratory-and-drug-actuation-dataset\n\nGeneric format:\n```\nFilename, Class, Sample index at the beginning of the acoustic event, Sample index at the end of the acoustic event\n\n```\n\nExample:\n\n```\nrec2018-01-22_17h41m33.475s.wav,Exhale,6015,17437\nrec2018-01-22_17h41m33.475s.wav,Inhale,20840,31655\nrec2018-01-22_17h41m33.475s.wav,Drug,31898,37610\nrec2018-01-22_17h41m33.475s.wav,Exhale,43686,59969\nrec2018-01-22_17h41m49.809s.wav,Inhale,5043,17316\nrec2018-01-22_17h41m49.809s.wav,Drug,18288,24364\nrec2018-01-22_17h41m49.809s.wav,Exhale,31412,46724\nrec2018-01-22_17h42m07.718s.wav,Exhale,303,9782\nrec2018-01-22_17h42m07.718s.wav,Inhale,16951,28010\n```\n\n# \n_Feel free to fork and use it with your dataset._\n","project_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdioptx%2Finhalesense","html_url":"https://awesome.ecosyste.ms/projects/github.com%2Fdioptx%2Finhalesense","lists_url":"https://awesome.ecosyste.ms/api/v1/projects/github.com%2Fdioptx%2Finhalesense/lists"}