Design and Implementation of a Smart Home System Using Multisensor Data Fusion Technology

Hsu, Yu-Liang; Chou, Po-Huan; Chang, Hsing−Cheng; Lin, Shyan-Lung; Yang, Shih-Chin; Su, Heng-Yi; Chang, Chih-Chien; Cheng, Yuansheng; Kuo, Yu-Chen

doi:10.3390/s17071631

Cited by 87 publications

(60 citation statements)

References 36 publications

(35 reference statements)

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…For example, Mathie et al [37] deployed a single waist-mounted accelerometer to find human activities with up to 94% accuracy. Hsu et al [38] and Jalal et al [39] created a wearable-device based smart home system to track people indoor with 92% and 74% accuracy, respectively. Hassan et al [40] used smartphone sensors to detect activities.…”

Section: Activity Detectionmentioning

confidence: 99%

Non-Intrusive Presence Detection and Position Tracking for Multiple People Using Low-Resolution Thermal Sensors

Singh

Akşanlı

2019

JSAN

View full text Add to dashboard Cite

This paper presents a framework to accurately and non-intrusively detect the number of people in an environment and track their positions. Different from most of the previous studies, our system setup uses only ambient thermal sensors with low-resolution, using no multimedia resources or wearable sensors. This preserves user privacy in the environment, and requires no active participation by the users, causing no discomfort. We first develop multiple methods to estimate the number of people in the environment. Our experiments demonstrate that algorithm selection is very important, but with careful selection, we can obtain up to 100% accuracy when detecting user presence. In addition, we prove that sensor placement plays a crucial role in the system performance, where placing the sensor on the room ceiling yields to the best results. After accurately finding the number of people in the environment, we perform position tracking on the collected ambient data, which are thermal images of the space where there are multiple people. We consider position tracking as static activity detection, where the user's position does not change while performing activities, such as sitting, standing, etc. We perform efficient pre-processing on the data, including normalization and resizing, and then feed the data into well-known machine learning methods. We tested the efficiency of our framework (including the hardware and software setup) by detecting four static activities. Our results show that we can achieved up to 97.5% accuracy when detecting these static activities, with up to 100% class-wise precision and recall rates. Our framework can be very beneficial to several applications such as health-care, surveillance, and home automation, without causing any discomfort or privacy issues for the users.

show abstract

Section: Activity Detectionmentioning

confidence: 99%

Non-Intrusive Presence Detection and Position Tracking for Multiple People Using Low-Resolution Thermal Sensors

Singh

Akşanlı

2019

JSAN

View full text Add to dashboard Cite

show abstract

“…Telah dilaksanakan penelitian sebelumnya mengenai pengamanan rumah menggunakan mikrokontroler yang menggunakan sensor PIR [6] dan multisensor [4], [7], [8]. Penelitian lainnya juga melakukan penerapan mikrokontroler dengan berbasis SMS [1], [5], [9], [10], [11], [12], [13], berbasis web [14], [15], [16], dan berbasis android [3].…”

Section: Pendahuluanunclassified

Prototipe Mikrokontroler Multisensor Menggunakan Arduino Uno Berbasis Web Sebagai Sistem Keamanan Rumah

Juniawan¹,

Sylfania²,

Adiputra³

2019

CogITo Smart Journal

View full text Add to dashboard Cite

AbstrakRumah adalah salah satu kebutuhan pokok manusia. Selain menjadi tempat berlindung dan beristirahat, terdapat banyak barang berharga yang disimpan di dalam rumah. Untuk itu keamanan rumah terus menjadi isu yang perlu dibahas. Seiring perkembangan zaman, teknologi dapat digunakan dalam pengamanan rumah, salah satunya adalah menggunakan mikrokontroler dan sensor. Penelitian ini menggunakan model penelitian Prototype dengan empat tahapan, yakni pengumpulan data, perancangan cepat prototipe, perancangan prototipe, dan pengujian prototipe. Juga digunakan berbagai sensor seperti sensor PIR untuk mendeteksi gerakan, MQ9 sensor untuk kebocoran gas, sensor LM35 untuk mendeteksi suhu, magnetik sensor untuk mendeteksi status pintu, dan sensor flame untuk mendeteksi api. Untuk menambah nilai mobilitasnya, maka dibuat agar keseluruhan kinerja sensor dapat dipantau menggunakan web. Dari tahapan pengujian kinerja sensor dan monitoring web didapat hasil sistem yang dibangun dapat bekerja dengan baik. Sensor PIR dapat mendeteksi gerakan terjauh 5 meter. Sensor MQ2 dapat mengidentifikasi gas dari jarak 2,5 meter. Sensor LM35 dapat mendeteksi suhu ruangan. Sensor magnetik dapat memberikan status pintu terbuka dengan jarak maksimal 1,9 sentimeter, dan sensor api dapat mendeteksi api dengan jarak terjauh 3 meter. AbstractHome is one of the basic human needs. Apart from being a place of refuge and rest, there are many valuables that we store inside the house. For this reason, home security continues to be an issue that needs to be discussed. Along with the times, technology can be used in home security. Microcontrollers, sensors, and the web can be combined to create the security system. This study uses a Prototype research model with four stages, data collection, rapid planning design, prototype design, and testing the prototypes. Also used are various sensors such as PIR sensors for motion detection, MQ9 sensors for gas leaks, LM35 sensors for temperature detection, magnetic sensors to detect the status from our doors, and flame sensors to detect fire. To add more value to mobility, it is made so that the overall performance of the sensor can be monitored by the user over the web. From the stages of sensor performance testing and web monitoring the results of the system built can work well. The PIR sensor can detect the furthest movement of 5 meters. The MQ2 sensor can identify gas from a distance of 2.5 meters. LM35 sensor can detect room temperature. The magnetic sensor can provide an open door status with a maximum

show abstract

“…In the work of Hsu et al, 18 a multisensor data fusion (MSDF) technique has been proposed for a smart home system using the IoT oriented WSN.…”

Section: Related Workmentioning

confidence: 99%

A multisensor data fusion strategy for path selection in Internet‐of‐Things oriented wireless sensor network (WSN)

Kumar

Chaurasiya

2018

Concurrency and Computation

View full text Add to dashboard Cite

To give the complete description of an environment or to take a robust decision, a number of observations are collected and combined from multiple sensor nodes. The process of combining and analyzing the observations is called multisensor data fusion. The fusion is used to produce more consistent, accurate, and useful information rather than provided by any individual sensor node. Data fusion finds wide application in many areas of such as object recognition, wireless sensor network, image processing, environment mapping, and localization. Nowadays, the Internet of Things (IoT) utilizes wireless sensor network (WSN) as a necessary platform for data sensing and communication. For efficiency, data fusion is performed on the sensed sample collected by the sensor nodes. However, fusion of the network parameters is also essential to select an appropriate sensor node for the forwarding of data. Therefore, in this paper, we propose a multisensor data fusion (MDF) strategy that performs fusion of the collected network parameters like bandwidth and centrality for the selection of an appropriate path. Extensive simulations were made, and related results showed that our proposed scheme has a better performance compared with other schemes in our simulated scenarios. KEYWORDS data fusion, Internet-of-Things, performance analysis, wireless sensor network INTRODUCTIONA wireless sensor network (WSN) is a type of network that contains large number of nodes having sensing capability such that they can easily detect any changes in the surrounding real-world environment. The nodes in WSN are used to carry sensed information from one to another desired location for further processing. 1,2 Technological advances are being developed daily, and a WSN plays a rapid contribution for providing smart communication with the use of smart devices. These smart devices perform communication at the different locations by providing a level of transparency among users and maintained an interconnected smart network. A number of sensor nodes are constituted by the smart network, which is used to send sensed information and termed as the Internet of Things (IoT). 3 In this paper, we called this network as an IoT oriented WSN. In this network, the users communicate with each other by exchanging of sensed data, monitoring of events, and surrounding and reacting autonomously. 4 The difference between the WSN and IoT oriented WSN is only the few sensors are deployed in WSN rather than along with smart devices for applications.However, the IoT oriented WSN consists of devices having sensors with full network connectivity. The network of IoT oriented WSN is concerned with the loss of packets and performance of the links for achieving high throughput in less delay.The services of IoT oriented WSN are provided by using a standard interface such that users can create a query, retrieve information, and change their states accordingly. An Internet link is used to provide the standard interface between users and IoT devices. The hardware components of a sensor no...

show abstract

Design and Implementation of a Smart Home System Using Multisensor Data Fusion Technology

Cited by 87 publications

References 36 publications

Non-Intrusive Presence Detection and Position Tracking for Multiple People Using Low-Resolution Thermal Sensors

Non-Intrusive Presence Detection and Position Tracking for Multiple People Using Low-Resolution Thermal Sensors

Prototipe Mikrokontroler Multisensor Menggunakan Arduino Uno Berbasis Web Sebagai Sistem Keamanan Rumah

A multisensor data fusion strategy for path selection in Internet‐of‐Things oriented wireless sensor network (WSN)

Contact Info

Product

Resources

About