20.500.12556/RUL-161681 Napovedovanje sekvence dogodkov v pametnem domu Predicting sequence of events in smart home environment Pametni domovi so se z razvojem brezžične tehnologije in IoT tehnologije v zadnjem času precej razvili in postali uporabnikom bolj dostopni. Sprva smo lahko hišne naprave upravljali zgolj prek centralnega vmesnika, nato pa smo jih lahko kontrolirali tudi prek prenosnih naprav in večjim številom vmesnikov po celotni hiši. Z nadaljnjim razvojem tehnologije smo pametne domove poskušali še bolj avtomatizirati, tako na področju udobja kot tudi na energetskem in varnostnem področju. Da bi to lahko dosegli, smo razvili različne algoritme za napovedovanje sekvenc dogodkov, ki so eden izmed ključnih dejavnikov na poti do tega cilja. V tem diplomskem delu smo pregledali nekaj že znanih rešitev na tem področju. Najprej smo se osredotočili na bolj preproste algoritme za napovedovanje sekvenc dogodkov, kot sta SPEED in Active LeZi, ki temeljita na LZW kompresijskih algoritmih ter Markovskih verigah. Nato smo pregledali še področje bolj aktualnih in kompleksnih metod, ki temeljijo na globokem učenju. Predstavili smo področje globokega učenja in navedli primere uporabe nevronskih mrež LSTM ter kombinacije CNN-LSTM nevronske mreže v pametnem domu. V drugem delu diplomskega dela smo na realnih podatkih iz pametnega doma preizkusili model globokega učenja, ki temelji na nevronski mreži GPT. Cilj raziskave je bil preveriti vpliv različnih nastavitev hiperparametrov na natančnost napovedi in čas učenja modela. Ugotovili smo, da ima model visoko točnost napovedi naslednjega dogodka, vendar se ta točnost s spreminjanjem njegovih parametrov ni bistveno spremenila. Povečal se je le čas učenja nevronske mreže. To bi lahko bila posledica enostavnosti nabora podatkov, ker imajo naprave v pametnem domu po navadi binaren značaj, ali pa dobrega delovanja naše mreže, saj so se GPT modeli izkazali za zelo učinkovite na tem področju. Smart homes have significantly evolved and become more accessible to users with the advancement of wireless technology and IoT (Internet of Things) technology in recent times. Initially, home devices could only be controlled through a central interface, but later, they could be managed via portable devices and an increasing number of interfaces throughout the house. With the further development of technology, we have aimed to make smart homes even more automated, not only in terms of comfort but also in energy efficiency and security. To achieve this, we developed various algorithms for predicting event sequences, which are one of the key factors in reaching this goal. In this thesis, we reviewed some of the already known solutions in this area. We first focused on simpler algorithms for predicting event sequences, such as SPEED and Active LeZi, which are based on LZW compression algorithms and Markov chains. Then, we explored more recent and complex methods that rely on deep learning. We presented the field of deep learning and provided examples of the use of LSTM neural networks and the combination of CNN-LSTM neural networks in a smart home. In the second part of the thesis, we also tested a deep learning model on real data from a smart home. This model was based on a GPT neural network. We found that the model has high accuracy in predicting the next event; however, this accuracy did not change with the modification of its parameters. Only the training time of the neural network increased. This could be due to the simplicity of the data set, as devices in the home typically have a binary nature, or due to the good performance of our network, as GPT models have proven to be very effective in this field. pametni domovi napovedovanje sekvenc SPEED Active LeZi globoko učenje GPT smart homes sequence prediction SPEED Active LeZi deep learning GPT true false false Slovenski jezik Angleški jezik Diplomsko delo/naloga 2024-09-13 08:05:00 2024-09-13 08:05:10 2024-09-15 03:31:13 0000-00-00 00:00:00 2024 0 0 0000-00-00 NiDoloceno NiDoloceno NiDoloceno 0000-00-00 0000-00-00 0000-00-00 62586 207417347 Vishaj_Alberim_-_Napovedovanje_sekvence_dogodkov_v_pametnem_domu.pdf Vishaj_Alberim_-_Napovedovanje_sekvence_dogodkov_v_pametnem_domu.pdf 1 E4299DA30F3ECFBCEF86082CDB3C8971 9c159eb59397da7d68bdebd5d294c5fbcaaa045e15b31ab45aba0e3b5e6410e6 122cef05-7196-11ef-b232-0050569b8976 https://repozitorij.uni-lj.si/Dokument.php?lang=slv&id=190657 Fakulteta za elektrotehniko 0 0 0