02089nas a2200265 a 450000500170000000800410001703500150005810000240007324500610009726000670015830000220022549000290024750001880027650200590046452008490052365000420137265000450141465000370145970000370149670000480153370000510158171000570163281000610168985600730175020260817162740.0240229s2022    th u  m  tt   000 a eng d  a.b124216490 aSiraphat Boonchan  10aAnomaly detection in the home with seismic sensors        aPathum Thani, Thailand :bAsian Institute of Technology,c2022  a81 leaves :bill.1 aThesis ;vno. DSAI-22-02  aA thesis submitted in partial fulfillment of the requirements for the  degree of Master of Engineering in Data Science and Artificial Intelligence, School of Engineeing and Technology  aThesis (M. Eng.) - Asian Institute of Technology, 2022  aFalls are a global public health problem. Falls happen to people of all ages, especially on the elderly. Throughout the last decade, we have seen improvements in fall detection system due to technology development and the revolution of deep learning. However, using vibration signal analysis can compensate the weakness and also overcomes the drawbacks associated with the traditional system, and this is a novel idea that needs to be studied further. This thesis studies the embedded system and design space for unsupervised anomaly detection model using modern deep learning best practices. The performance and effectiveness of this system to immediately send alert message to user via LINE apllication when abnormal events occur. Accordingly, this study can help the home residents when an anomolous event or falling down event is occurring. 0aAnomaly detection (Computer security) 0aArtificial intelligencexData processing 0aDeep learning (Machine learning)1 aDailey, Matthew N.,eChairperson0 aMongkol Ekpanyapong,eExamination Committee0 aChaklam Silpasuwanchai,eExamination Committee2 aRoyal Thai Government Fellowship,eScholarship Donor2 aAsian Institute of Technology.tThesis ;vno. DSAI-22-02403Full-Textuhttp://203.159.5.9/ait-thesis/Viewer/viewer.php?id=B20415