Seite - 376 - in Intelligent Environments 2019 - Workshop Proceedings of the 15th International Conference on Intelligent Environments

works (csn). In Proceedings of the 13th international conference on Ubiquitous computing (Ubi- Comp11), 2011. [18] OscarDLara,MiguelALabrador,etal.Asurveyonhumanactivityrecognitionusingwearablesensors. IEEECommunicationsSurveysandTutorials, 15(3):1192–1209,2013. [19] YannLeCunandYoshuaBengio. Thehandbookof brain theory andneural networks. pages255–258, 1998. [20] MohammadMalekzadeh,RichardGClegg,AndreaCavallaro, andHamedHaddadi. Protectingsensory dataagainstsensitiveinferences. InProceedingsofthe1stWorkshoponPrivacybyDesigninDistributed Systems (P2DS18), 2018. [21] Carlos Medrano, Raul Igual, Inmaculada Plaza, and Manuel Castro. Detecting falls as novelties in accelerationpatternsacquiredwith smartphones.PloSone, 9(4):e94811,2014. [22] DanielaMicucci,MarcoMobilio, and PaoloNapoletano. Unimib shar: A dataset for human activity recognitionusingaccelerationdata fromsmartphones.AppliedSciences, 7(10), 2017. [23] Daniela Micucci, Marco Mobilio, Paolo Napoletano, and Francesco Tisato. Falls as anomalies? an experimental evaluation using smartphone accelerometer data. Journal of Ambient Intelligence and HumanizedComputing, 8(1):87–99,2017. [24] AlexAdimObinikpoandBurakKantarci.Bigdataaggregationinthecaseofheterogeneity:afeasibility studyfordigitalhealth. InternationalJournalofMachineLearningandCybernetics, pages1–13,2019. [25] Alexander Ratner, Stephen H Bach, Henry Ehrenberg, Jason Fries, Sen Wu, and Christopher Re´. Snorkel: Rapid training data creationwithweak supervision. Proceedings of the VLDBEndowment, 11(3):269–282,2017. [26] NishkamRavi,NikhilDandekar, PreethamMysore, andMichaelLLittman. Activity recognition from accelerometerdata. InProceedingsof the17thconferenceon Innovativeapplicationsofartificial intel- ligence (IAAI05), 2005. [27] Jorge-LReyes-Ortiz, LucaOneto, Albert Sama`, Xavier Parra, andDavideAnguita. Transition-aware humanactivity recognitionusingsmartphones.Neurocomputing, 171:754–767,2016. [28] CharissaAnnRonao and Sung-BaeCho. Human activity recognitionwith smartphone sensors using deep learningneuralnetworks.Expert systemswithapplications, 59:235–244,2016. [29] ErikaRovini, CarloMaremmani, andFilippoCavallo. Howwearable sensors can support parkinson’s diseasediagnosis and treatment:Asystematic review.Frontiers inNeuroscience, 11(555), 2017. [30] Muhammad Shoaib, Stephan Bosch, Incel Ozlem Durmaz, Hans Scholten, and Paul J. M. Havinga. Fusion of smartphonemotion sensors for physical activity recognition. Sensors, 14(6):10146–10176, 2014. [31] PekkaSiirtola,HeliKoskima¨ki, and JuhaRo¨ning. Openhar:Amatlab toolbox for easy access to pub- licly open human activity data sets. InProceedings of the 2018ACM International Joint Conference and2018 International SymposiumonPervasive andUbiquitousComputingandWearableComputers (UbiComp18), 2018. [32] TimoSztyler andHeiner Stuckenschmidt. On-body localizationofwearable devices:An investigation of position-aware activity recognition. In IEEEInternationalConferenceonPervasiveComputingand Communications (PerCom16), 2016. [33] PrabithaUrwyler,RetoStucki,LucaRampa,Rene´Mu¨ ri,UrsP.Mosimann, andTobiasNef. Cognitive impairment categorized in community-dwellingolder adultswith andwithout dementia using in-home sensors that recogniseactivitiesofdaily living. ScientificTechnicalReport42084,PMC,2017. [34] Vincent T Van Hees, Lukas Gorzelniak, Emmanuel Carlos Dean Leon, Martin Eder, Marcelo Pias, SalmanTaherian, Ulf Ekelund, FridaRenstro¨m, PaulWFranks, AlexanderHorsch, et al. Separating movement andgravity components in anacceleration signal and implications for the assessmentofhu- mandailyphysical activity.PloSone, 8(4):e61691,2013. [35] George Vavoulas, Charikleia Chatzaki, ThodorisMalliotakis,Matthew Pediaditis, andManolis Tsik- nakis. Themobiactdataset:Recognitionofactivitiesofdaily livingusingsmartphones. InProceedings of the InternationalConferenceon InformationandCommunicationTechnologies forAgeingWell and e-Health (ICT4AgeingWell16), 2016. [36] MingZeng,LeTNguyen,BoYu,OleJMengshoel, JiangZhu,PangWu,andJoyZhang.Convolutional neural networks for human activity recognition usingmobile sensors. In6th InternationalConference onMobileComputing,ApplicationsandServices (MobiCASE14), 2014. A.Ferrari etal. /AFramework forLong-TermDataCollection376