Pengembangan Sistem Smart Home Berbasis Pengenalan Suara Menggunakan Model Long Short-Term Memory
Abstrak
Perkembangan teknologi informasi telah mendorong terciptanya solusi inovatif seperti Smart Home, yang memungkinkan otomatisasi dan kontrol perangkat rumah tangga. Penelitian ini mengembangkan sistem Smart Home berbasis pengenalan suara menggunakan model Long Short-Term Memory (LSTM). Sistem dirancang untuk mengenali perintah suara pengguna dan mengontrol perangkat seperti lampu, kipas, dan kunci pintu. Fitur suara diolah menggunakan Mel-Frequency Cepstral Coefficients (MFCC) untuk menghasilkan representasi data yang optimal bagi model LSTM. Pengujian dilakukan pada model dengan dataset yang mencakup perintah-perintah suara dari beberapa subjek. Hasil pengujian menunjukkan bahwa sistem memiliki akurasi total sebesar 54%, dengan akurasi lebih tinggi untuk subjek yang datanya telah dilatih dibandingkan subjek baru. Implementasi model LSTM memungkinkan pengenalan suara berjalan secara efisien pada perangkat keras kecil seperti Raspberry Pi 5, yang memfasilitasi respons real-time terhadap perintah suara. Penelitian ini memberikan kontribusi pada pengembangan teknologi Smart Home, khususnya pada aspek pengendalian berbasis suara. Pengembangan lebih lanjut dapat difokuskan pada penambahan dataset yang lebih beragam, pengurangan noise, dan eksplorasi arsitektur jaringan saraf lain untuk meningkatkan akurasi sistem.
Referensi
Cholik, C.A., 2021. Perkembangan teknologi informasi komunikasi / ICT dalam berbagai bidang. Perkembangan Teknologi Informasi Komunikasi / ICT Dalam Berbagai Bidang.
Hasan, M., Biswas, P., Bilash, M.T.I. and Dipto, Md.A.Z., 2018. Smart Home Systems: Overview and Comparative analysis. Smart Home Systems: Overview and Comparative Analysis. [online] https://doi.org/10.1109/icrcicn.2018.8718722.
ShariqSuhail, M., ViswanathaReddy, G., Rambabu, G., DharmaSavarni, C.V.R. and Mittal, V.K., 2016. Multi-functional secured smart home. Multi-functional Secured Smart Home. [online] https://doi.org/10.1109/icacci.2016.7732455
Dahoumane, T., Haddadi, M. and Amokrane, Z., 2018. Web Services and GSM based Smart Home Control System. 2018 International Conference on Applied Smart Systems (ICASS). [online] https://doi.org/10.1109/icass.2018.8651956
Kang, B., Kim, S., Choi, M.-I., Cho, K., Jang, S. and Park, S., 2016. Analysis of types and importance of sensors in smart home services. Analysis of Types and Importance of Sensors in Smart Home Services. [online] https://doi.org/10.1109/hpcc-smartcity-dss.2016.0196
Stojmenski, A., Joksimoski, B., Chorbev, I. and Trajkovikj, V., 2016. Smart home environment aimed for people with physical disabilities. Smart Home Environment Aimed for People With Physical Disabilities. [online] https://doi.org/10.1109/iccp.2016.7737115
Shewalkar, A., Nyavanandi, D. and Ludwig, S.A., 2019c. Performance evaluation of deep neural networks applied to speech recognition: RNN, LSTM and GRU. Journal of Artificial Intelligence and Soft Computing Research, [online] 9(4), pp.235–245. https://doi.org/10.2478/jaiscr-2019-0006
Maryamah, M., Pradiptamurty, N.J.K., Shafro, H.K., Qurtubi, M.S.A., Tambahjong, G.A. and Almaulidiyah, Q., 2023. Speech Emotion Recognition (SER) dengan Metode Bidirectional LSTM. Speech Emotion Recognition (SER) Dengan Metode Bidirectional LSTM, [online] 3(1), pp.153–161. https://doi.org/10.33005/senada.v3i1.105.
Kumar, M. and Patidar, A., 2021. Sarcasm detection using Stacked Bi-Directional LSTM model. 2021 3rd International Conference on Advances in Computing, Communication Control and Networking (ICAC3N). [online] https://doi.org/10.1109/icac3n53548.2021.9725488.
Sovacool, B.K. and Del Rio, D.D.F., 2020. Smart home technologies in Europe: A critical review of concepts, benefits, risks and policies. Renewable and Sustainable Energy Reviews, [online] 120, p.109663. https://doi.org/10.1016/j.rser.2019.109663
Rabiner, L. and Juang, B.-H., 1993. Fundamentals of speech recognition.
Janiesch, C., Zschech, P. and Heinrich, K., 2021. Machine learning and deep learning. Electronic Markets. [online] 31(3), pp.685–695. https://doi.org/10.1007/s12525-021-00475-2
Staudemeyer, R.C. and Morris, E.R., 2019. Understanding LSTM -- a tutorial into Long Short-Term Memory Recurrent Neural Networks. arXiv (Cornell University). [online] https://doi.org/10.48550/arxiv.1909.09586.
Cholik, C.A., 2021. Perkembangan teknologi informasi komunikasi / ICT dalam berbagai bidang. Perkembangan Teknologi Informasi Komunikasi / ICT Dalam Berbagai Bidang.
Hasan, M., Biswas, P., Bilash, M.T.I. and Dipto, Md.A.Z., 2018. Smart Home Systems: Overview and Comparative analysis. Smart Home Systems: Overview and Comparative Analysis. [online] https://doi.org/10.1109/icrcicn.2018.8718722.
ShariqSuhail, M., ViswanathaReddy, G., Rambabu, G., DharmaSavarni, C.V.R. and Mittal, V.K., 2016. Multi-functional secured smart home. Multi-functional Secured Smart Home. [online] https://doi.org/10.1109/icacci.2016.7732455
Dahoumane, T., Haddadi, M. and Amokrane, Z., 2018. Web Services and GSM based Smart Home Control System. 2018 International Conference on Applied Smart Systems (ICASS). [online] https://doi.org/10.1109/icass.2018.8651956
Kang, B., Kim, S., Choi, M.-I., Cho, K., Jang, S. and Park, S., 2016. Analysis of types and importance of sensors in smart home services. Analysis of Types and Importance of Sensors in Smart Home Services. [online] https://doi.org/10.1109/hpcc-smartcity-dss.2016.0196
Stojmenski, A., Joksimoski, B., Chorbev, I. and Trajkovikj, V., 2016. Smart home environment aimed for people with physical disabilities. Smart Home Environment Aimed for People With Physical Disabilities. [online] https://doi.org/10.1109/iccp.2016.7737115
Shewalkar, A., Nyavanandi, D. and Ludwig, S.A., 2019c. Performance evaluation of deep neural networks applied to speech recognition: RNN, LSTM and GRU. Journal of Artificial Intelligence and Soft Computing Research, [online] 9(4), pp.235–245. https://doi.org/10.2478/jaiscr-2019-0006
Maryamah, M., Pradiptamurty, N.J.K., Shafro, H.K., Qurtubi, M.S.A., Tambahjong, G.A. and Almaulidiyah, Q., 2023. Speech Emotion Recognition (SER) dengan Metode Bidirectional LSTM. Speech Emotion Recognition (SER) Dengan Metode Bidirectional LSTM, [online] 3(1), pp.153–161. https://doi.org/10.33005/senada.v3i1.105.
Kumar, M. and Patidar, A., 2021. Sarcasm detection using Stacked Bi-Directional LSTM model. 2021 3rd International Conference on Advances in Computing, Communication Control and Networking (ICAC3N). [online] https://doi.org/10.1109/icac3n53548.2021.9725488.
Sovacool, B.K. and Del Rio, D.D.F., 2020. Smart home technologies in Europe: A critical review of concepts, benefits, risks and policies. Renewable and Sustainable Energy Reviews, [online] 120, p.109663. https://doi.org/10.1016/j.rser.2019.109663
Rabiner, L. and Juang, B.-H., 1993. Fundamentals of speech recognition.
Janiesch, C., Zschech, P. and Heinrich, K., 2021. Machine learning and deep learning. Electronic Markets. [online] 31(3), pp.685–695. https://doi.org/10.1007/s12525-021-00475-2
Staudemeyer, R.C. and Morris, E.R., 2019. Understanding LSTM -- a tutorial into Long Short-Term Memory Recurrent Neural Networks. arXiv (Cornell University). [online] https://doi.org/10.48550/arxiv.1909.09586.
Unduhan
Diterbitkan
Cara Mengutip
Terbitan
Bagian
Lisensi
Hak Cipta (c) 2025 Jurnal Pengembangan Teknologi Informasi dan Ilmu Komputer
Artikel ini berlisensiCreative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
