ABSTRAKBanyak orang memasang kamera pengawas di rumah untuk memantau rumah ketika dalam keadaan kosong. Namun tidak ada pemberitahuan secara langsung kepada pemilik rumah ketika ada orang yang tidak dikehendaki terdeteksi oleh sistem kamera pengawas. Kekurangan lainnya adalah kamera tetap merekam video meskipun tidak ada aktifitas yang terdeteksi. Penelitian ini merancang sistem keamanan rumah berbasis Internet of Things (IoT) memanfaatkan Telegram Messenger. Ketika sensor PIR (Passive Infra Red) mendeteksi gerak manusia, maka kamera Raspberry Pi akan mengambil foto dan mengirimkan hasilnya kepada pengguna melalui Telegram Messenger. Bot pada Telegram Messenger akan menawarkan 2 fitur yang dapat dipilih oleh pemilik rumah, yaitu mengambil foto atau video. Dari hasil pengujian yang dilakukan, didapatkan hasil berupa jarak maksimum deteksi obyek terhadap sensor adalah 6 meter. Dari Pengujian yang dilakukan terbukti sistem mampu bekerja mendeteksi, merekam dan mengirim hasilnya ke pengguna. Waktu yang dibutuhkan untuk pegiriman pesan deteksi obyek sebesar 4.73 detik. Untuk request foto sampai dengan foto diterima membutuhkan waktu 5.73 detik dan untuk video membutuhkan waktu 14.86 detik. ABSTRACTMany people install surveillance system at home to monitor when the house is empty. But there is no direct notification to the homeowner when unwanted person is detected by the surveillance system. Another drawback is that the camera remains a video recording even though no activity is detected. These research designs home security systems based on the IoT using Telegram Messenger. The way the system works is when the PIR sensor detects the presence of human being objects, the Raspberry Pi camera will take photos and send the results to the user via the Telegram Messenger. The bot on the Telegram Messenger will offer 2 features that can be selected by users, which are taking photos or videos. The results of performance test of the system, show that the maximum distance of the object against the sensor that can be detected is 6 meters. The system proved able to work to detect, record and send the results to the user. Average time for the delivery of alert messages is 4.73 seconds. Time needed to process photo request until received by users are 5.73 seconds and 14.86 seconds respectively.

Sleep scoring is the first step for diagnosing sleep disorders. A variety of chronic diseases related to sleep disorders could be identified using sleep-state estimation. This paper presents an end-to-end deep learning architecture using wrist actigraphy, called Deep-ACTINet, for automatic sleep-wake detection using only noise canceled raw activity signals recorded during sleep and without a feature engineering method. As a benchmark test, the proposed Deep-ACTINet is compared with two conventional fixed model based sleep-wake scoring algorithms and four feature engineering based machine learning algorithms. The datasets were recorded from 10 subjects using three-axis accelerometer wristband sensors for eight hours in bed. The sleep recordings were analyzed using Deep-ACTINet and conventional approaches, and the suggested end-to-end deep learning model gained the highest accuracy of 89.65%, recall of 92.99%, and precision of 92.09% on average. These values were approximately 4.74% and 4.05% higher than those for the traditional model based and feature based machine learning algorithms, respectively. In addition, the neuron outputs of Deep-ACTINet contained the most significant information for separating the asleep and awake states, which was demonstrated by their high correlations with conventional significant features. Deep-ACTINet was designed to be a general model and thus has the potential to replace current actigraphy algorithms equipped in wristband wearable devices.

Abstract

Gait analysis is commonly used to detect foot disorders and abnormalities such as supination, pronation, unstable left foot and unstable right foot. Early detection of these abnormalities could help us to correct the walking posture and avoid getting injuries. This paper presents extensive feature analyses on smart shoes sensor data, including pressure sensors, accelerometer and gyroscope signals, to obtain the optimum combination of the sensors for gait classification, which is crucial to implement a power-efficient mobile smart shoes system. In addition, we investigated the optimal length of data segmentation based on the gait cycle parameters, reduction of the feature dimensions and feature selection for the classification of the gait patterns. Benchmark tests among several machine learning algorithms were conducted using random forest, k-nearest neighbor (KNN), logistic regression and support vector machine (SVM) algorithms for the classification task. Our experiments demonstrated the combination of accelerometer and gyroscope sensor features with SVM achieved the best performance with 89.36% accuracy, 89.76% precision and 88.44% recall. This research suggests a new state-of-the-art gait classification approach, specifically on detecting human gait abnormalities.