Smoking Activity Recognition Using a Single Wrist IMU and Deep Learning Light

Añazco, Edwin Valarezo; Lopez, Patricio Rivera; Lee, Sangmin; Byun, Kyungmin; Kim, Tae‐Seong

doi:10.1145/3193025.3193028

Cited by 20 publications

(12 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In the work by Shoaib et al [67], the 6D IMU of a smart watch (LG Watch R). and by Añazco et al in [68] a 6D IMU of MbientLab, were paired with smartphones and developed smoking detection applications. SmokeBeat is a similar commercial platform [69].…”

Section: Evaluation Of Sensing Methodologiesmentioning

confidence: 99%

Wearable Sensors for Monitoring of Cigarette Smoking in Free-Living: A Systematic Review

Imtiaz

Ramos-Garcia

Wattal

et al. 2019

Sensors

View full text Add to dashboard Cite

Globally, cigarette smoking is widespread among all ages, and smokers struggle to quit. The design of effective cessation interventions requires an accurate and objective assessment of smoking frequency and smoke exposure metrics. Recently, wearable devices have emerged as a means of assessing cigarette use. However, wearable technologies have inherent limitations, and their sensor responses are often influenced by wearers’ behavior, motion and environmental factors. This paper presents a systematic review of current and forthcoming wearable technologies, with a focus on sensing elements, body placement, detection accuracy, underlying algorithms and applications. Full-texts of 86 scientific articles were reviewed in accordance with the Preferred Reporting Items for Systematic Review and Meta-Analyses (PRISMA) guidelines to address three research questions oriented to cigarette smoking, in order to: (1) Investigate the behavioral and physiological manifestations of cigarette smoking targeted by wearable sensors for smoking detection; (2) explore sensor modalities employed for detecting these manifestations; (3) evaluate underlying signal processing and pattern recognition methodologies and key performance metrics. The review identified five specific smoking manifestations targeted by sensors. The results suggested that no system reached 100% accuracy in the detection or evaluation of smoking-related features. Also, the testing of these sensors was mostly limited to laboratory settings. For a realistic evaluation of accuracy metrics, wearable devices require thorough testing under free-living conditions.

show abstract

Section: Evaluation Of Sensing Methodologiesmentioning

confidence: 99%

Wearable Sensors for Monitoring of Cigarette Smoking in Free-Living: A Systematic Review

Imtiaz

Ramos-Garcia

Wattal

et al. 2019

Sensors

View full text Add to dashboard Cite

show abstract

“…For example, Cole et al [9] introduced methods to implement real-time detection algorithms in a smartphone using the 3D accelerometer of an Apple watch. Similarly, Añazco et al [1] proposed a smart and proactive system using a wristband housing a 6D motion sensor and a smartphone application housing an RNN-based algorithm to detect smoking puffs. Although a smartwatch and smartphone are both involved, these two studies only used motion sensors from the smartwatch.…”

Section: Related Workmentioning

confidence: 99%

“…By fusing motion sensors in both the wristworn device and the smartphone, we can go a step further and improve the detection performance more. For the smoking event detection task, most previous studies [1,12,15,16,23] used only motion sensors on the wrist. The results in Figures 16~18 show us that it is reasonable and advisable to use the supplementary motion data from the smartphone, especially when smoking is performed in different postures since it increased the f1-score nearly by 2%.…”

Section: G Impact Of Sensor Combinationsmentioning

confidence: 99%

“…Therefore, it causes both medical and financial problems. First, according to a report by the World Health Organization, more than 6 million active smokers and approximately 890,000 nonsmokers exposed to second-hand smoke are killed by tobacco [1]. Second, a report by the U.S. Fire Administration notes that approximately 7,800 smokingrelated fires occurred in homes in 2017, causing 300 deaths, 700 injuries and more than 300 million dollars in losses.…”

Section: Introductionmentioning

confidence: 99%

“…Due to the convenience of capturing hand gestures using a smartwatch, some research uses motion sensor data from a smartwatch to detect smoking-related hand gestures and recognize high-level activities on its Android-based system [7,8]. Other works employ motion sensors embedded in a smartwatch to detect smoking events by pairing the smartwatch with a smartphone and running the detection algorithms on the phone [1,9], and several other studies use only smartphone sensor data to detect smoking events [10,11]. In these related works, the motion context information from a smartwatch and smartphone is mainly used in isolation, and the efficiency of online smoking prediction on the mobile device is rarely evaluated.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

A New Approach for Smoking Event Detection Using a Variational Autoencoder and Neural Decision Forest

Fan

Gao

2020

IEEE Access

View full text Add to dashboard Cite

Smoking is associated with cancer, cardiovascular disease and premature death and can cause severe fire hazards. To assist with smoking cessation, this paper presents a wireless body area networkbased system consisting of two off-the-shelf devices, one smartphone and one smartwatch, to detect smoking events by mining the inertial sensor data from both devices. In the system, an end-to-end trainable unified model is implemented by combining a variational autoencoder with a random forest to classify the collected data into smoking and nonsmoking after data preprocessing. The variational autoencoder is adopted to learn the feature representation and deal with the class imbalance problem, and the stochastic decision forest is adopted to guide the global optimization of the parameter learning process. Extensive validation of our scheme is performed on a large dataset we collected, and our scheme yields quite promising results in terms of accuracy and efficiency.

show abstract

Region Extraction Based Approach for Cigarette Usage Classification Using Deep Learning

Pundhir

Verma

Kumar

et al. 2022

Communications in Computer and Information Science

View full text Add to dashboard Cite

Smoking Activity Recognition Using a Single Wrist IMU and Deep Learning Light

Cited by 20 publications

References 9 publications

Wearable Sensors for Monitoring of Cigarette Smoking in Free-Living: A Systematic Review

Wearable Sensors for Monitoring of Cigarette Smoking in Free-Living: A Systematic Review

A New Approach for Smoking Event Detection Using a Variational Autoencoder and Neural Decision Forest

Region Extraction Based Approach for Cigarette Usage Classification Using Deep Learning

Contact Info

Product

Resources

About