Internet of Things (IoT) Based Activity Recognition Strategies in Smart Homes: A Review

Babangida, Lawal; Perumal, Thinagaran; Mustapha, Norwati; Yaakob, Razali

doi:10.1109/jsen.2022.3161797

Cited by 56 publications

(16 citation statements)

References 96 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It is because, day-to-day human surveillance in the context of medical conditions, military areas, domestic areas, industrial areas, etc. are increasing [28]. Below section deals with different aspects of the 4 HAR system along with different hardware and software available for such study.…”

Section: Stm8l101 Microcontroller and Cc1101 Radio Frequency Module T...mentioning

confidence: 99%

A Survey on Different Application Areas based on RSS (Received Signal Strength) and Possible Hardware and Software Tools for the Collection of RSS

Sarsodia

Bhatt

Upadhyay

et al. 2022

2022 IEEE International Conference on Current Development in Engineering and Technology (CCET)

View full text Add to dashboard Cite

Apart from serving basic communication to users, reach of wireless networks to users has been facilitating various applications and mechanisms which can add on multiple functionality of networks. Received signal strength Indicator (RSSI)/ Channel state Information (CSI) is one such statistics available on user device, which can be used to achieve multiple adjuncts network functionalities and few applications. This paper focuses mainly on RSSI based Human activity recognition (HAR), Node identification as applications and Physical layer key generation (PLKG) as security mechanism. HAR utilizes variations in RSSI values to detect presence of human or their activities. Similarly in node identification, on the basis of RSSI and environment between Access point and nodes, access point predicts the node location. Further, one of the emerging research areas PLKG, also uses RSSI preprocessing to achieve better network performance. The paper also presents comprehensive survey on hardware cards installed in user devices and software tools used to quantify RSSI in HAR applications.

show abstract

Section: Stm8l101 Microcontroller and Cc1101 Radio Frequency Module T...mentioning

confidence: 99%

A Survey on Different Application Areas based on RSS (Received Signal Strength) and Possible Hardware and Software Tools for the Collection of RSS

Sarsodia

Bhatt

Upadhyay

et al. 2022

2022 IEEE International Conference on Current Development in Engineering and Technology (CCET)

View full text Add to dashboard Cite

show abstract

“…In addition, a variety of novel IoT applications need ultra‐reliable and low‐latency communication (URLLC), with latency as low as a few milliseconds and packet loss less than

1{0}^{-4}

3,4 . Therefore, QoS‐enabled energy‐efficient communication is necessary for the smooth integration of massive MTC (mMTC) and M2M communication with a wide range of IoT applications 5 . Regardless of the fact that it helps achieve QoS‐enabled energy‐efficient M2M communication, performance metrics like Shannon capacity and ergodic capacity provide an imperfect benchmark when stringent QoS guarantees are associated with transmitted packets, necessitating the development of new performance metric techniques 6,7 …”

Section: Introductionmentioning

confidence: 99%

Energy‐efficient machine type communication in HetNets under statistical QoS guarantees

Waqas Haider Shah,

Qaraqe

2023

Trans Emerging Tel Tech

View full text Add to dashboard Cite

There has been an unprecedented rise in the Internet‐of‐Things (IoT) in the past decade. One of the underlying reasons for this exponential growth is that IoT allows for massive machine‐type communication (mMTC), which facilities machine‐to‐machine (M2M) communication with minimal human intervention. However, mMTC devices are characterized by resource and energy limitations, and thus require powerful and efficient power allocation methods that do not jeopardize quality‐of‐service (QoS) performance. In this work, a statistical QoS analysis of M2M communication in heterogeneous wireless networks is performed. We propose a communication mode selection (CMS) scheme that selects an uplink transmission link from the available candidate links based on pathloss criteria. The closed‐form expressions for the Effective Capacity and effective energy efficiency (Effective‐EE) of the M2M communication in the heterogeneous wireless network are derived and verified via simulations. The optimal fixed transmission rate that maximizes the Effective Capacity and Effective‐EE is also analytically analyzed. Furthermore, four scenarios are adopted to study the overall Effective Capacity and Effective‐EE of a two‐hop M2M communication link where the transmitter and access point operate under independent and identical QoS constraints. This article also investigates the impact of circuit power and the efficiency of the power amplifier on the achievable Effective‐EE of the communication link.

show abstract

“…With the low birthrate and aging population, one of the social issues related to safety and security is the use of monitoring networks for solitary elderly or people living alone in remote areas. The recent progress in situational recognition technologies 1,2 has given impetus to research on activity recognition combining IoT and machine learning 3–7 . Direct situational recognition techniques to watch over people are based on camera images, speech, etc.…”

Section: Introductionmentioning

confidence: 99%

“…In addition, recognition of daily activities is impossible when the user forgets to put on the wearable sensor or attaches it in a wrong way, when the battery runs out, etc. There is a survey 6 that sums up various schemes of IoT based activity recognition (including the four mentioned ideas) using camera images, acceleration sensors, pressure sensors, proximity sensors, magnetic sensors, temperature sensors, etc.…”

Section: Introductionmentioning

confidence: 99%

An activity recognition system at home based on illuminance sensors

Matsubara

2023

Elect Comm in Japan

View full text Add to dashboard Cite

A social issue that leads to the safety and security of people is the network that monitors the safety of people living alone in remote areas. Various research and developments of indoor human activity recognition using IoT sensor nodes have been conducted in recent years. In this research, we focus on turning on and off indoor lighting and propose an activity recognition system at home using an illuminance sensor. An IoT sensor node with a built‐in illuminance sensor is attached to the wall near the indoor lighting equipment. The living activities of people in the room are estimated from changes in the illuminance. We assume a significant change in the illuminance of the indoor lighting is observed at least once a day at the sampling interval of the IoT sensor node. In that case, it is possible to estimate the operation of the indoor lighting due to daily activities and to confirm the safety of people living alone in remote areas. The activity recognition system was evaluated for a total of 380 days, excluding the missing period. The estimation of indoor lighting manipulation by daily activities was accurate for 376 days. Precision, Recall, and F‐measure score values, which are evaluation indices for activity estimation, were 94.9%, 98.2%, and 96.5%, respectively.

show abstract

Internet of Things (IoT) Based Activity Recognition Strategies in Smart Homes: A Review

Cited by 56 publications

References 96 publications

A Survey on Different Application Areas based on RSS (Received Signal Strength) and Possible Hardware and Software Tools for the Collection of RSS

A Survey on Different Application Areas based on RSS (Received Signal Strength) and Possible Hardware and Software Tools for the Collection of RSS

Energy‐efficient machine type communication in HetNets under statistical QoS guarantees

An activity recognition system at home based on illuminance sensors

Contact Info

Product

Resources

About