Van Thanh Pham

Mr. Van Thanh Pham

orcid

Research Focus & Metrics

Academic Career Length

15Years (2012-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
14 August 2018 in Arabian Journal for Science and Engineering
Verified
Journal Article
Closed access
PDF file
VPVan Thanh Pham
Van Thanh Pham
DTDuc-Tan Tran
Duc-Tan Tran
DNDinh-Chinh Nguyen
Dinh-Chinh Nguyen
NANguyen Duc Anh
Nguyen Duc Anh
DDDang Nhu Dinh
Dang Nhu Dinh
KSKumbesan Sandrasegaran
Kumbesan Sandrasegaran

20 September 2018 in Sensors
Verified
Journal Article
Open access
PDF file
VPVan Thanh Pham
Van Thanh Pham
DNDuc Anh Nguyen
Duc Anh Nguyen
NDNhu Dinh Dang
Nhu Dinh Dang
HPHong Hai Pham
Hong Hai Pham
VTVan An Tran
Van An Tran
DTDuc-Tan Tran
Duc-Tan Tran
Accurate step counting is essential for indoor positioning, health monitoring systems, and other indoor positioning services. There are several publications and commercial applications in step counting. Nevertheless, over-counting, under-counting, and false walking problems are still encountered in these methods. In this paper, we propose to develop a highly accurate step counting method to solve these limitations by proposing four features: Minimal peak distance, minimal peak prominence, dynamic thresholding, and vibration elimination, and these features are adaptive with the user’s states. Our proposed features are combined with periodicity and similarity features to solve false walking problem. The proposed method shows a significant improvement of 99.42% and 96.47% of the average of accuracy in free walking and false walking problems, respectively, on our datasets. Furthermore, our proposed method also achieves the average accuracy of 97.04% on public datasets and better accuracy in comparison with three commercial step counting applications: Pedometer and Weight Loss Coach installed on Lenovo P780, Health apps in iPhone 5s (iOS 10.3.3), and S-health in Samsung Galaxy S5 (Android 6.01).

1 November 2019 in Sensors
Verified
Journal Article
Open access
PDF file
VPVan Thanh Pham
Van Thanh Pham
QLQuang Bon Le
Quang Bon Le
DNDuc Anh Nguyen
Duc Anh Nguyen
NDNhu Dinh Dang
Nhu Dinh Dang
HHHuu Tue Huynh
Huu Tue Huynh
DTDuc-Tan Tran
Duc-Tan Tran
While working on fire ground, firefighters risk their well-being in a state where any incident might cause not only injuries, but also fatality. They may be incapacitated by unpredicted falls due to floor cracks, holes, structure failure, gas explosion, exposure to toxic gases, or being stuck in narrow path, etc. Having acknowledged this need, in this study, we focus on developing an efficient portable system to detect firefighter’s falls, loss of physical performance, and alert high CO level by using a microcontroller carried by a firefighter with data fusion from a 3-DOF (degrees of freedom) accelerometer, 3-DOF gyroscope, 3-DOF magnetometer, barometer, and a MQ7 sensor using our proposed fall detection, loss of physical performance detection, and CO monitoring algorithms. By the combination of five sensors and highly efficient data fusion algorithms to observe the fall event, loss of physical performance, and detect high CO level, we can distinguish among falling, loss of physical performance, and the other on-duty activities (ODAs) such as standing, walking, running, jogging, crawling, climbing up/down stairs, and moving up/down in elevators. Signals from these sensors are sent to the microcontroller to detect fall, loss of physical performance, and alert high CO level. The proposed algorithms can achieve 100% of accuracy, specificity, and sensitivity in our experimental datasets and 97.96%, 100%, and 95.89% in public datasets in distinguishing between falls and ODAs activities, respectively. Furthermore, the proposed algorithm perfectly distinguishes between loss of physical performance and up/down movement in the elevator based on barometric data fusion. If a firefighter is unconscious following the fall or loss of physical performance, an alert message will be sent to their incident commander (IC) via the nRF224L01 module.

27 February 2017 in Journal of Electronic Materials
Verified
Journal Article
Closed access
PDF file
VPVan Thanh Pham
Van Thanh Pham
LNLe Thi Quynh Nhu
Le Thi Quynh Nhu
HMHong Hanh Mai
Hong Hanh Mai
NTNguyen Viet Tuyen
Nguyen Viet Tuyen
SDSai Cong Doanh
Sai Cong Doanh
DKDo Trung Kien
Do Trung Kien


4 August 2025 in IEEE Sensors Journal
Verified
Journal Article
Closed access
TDTo-Hieu Dao
To-Hieu Dao
DTDuc-Tan Tran
Duc-Tan Tran
VBViet-Hoan Bui
Viet-Hoan Bui
VNVan Son Nguyen
Van Son Nguyen
DHDang Khanh Hoa
Dang Khanh Hoa
DTDuc-Tan Tran
Duc-Tan Tran
Human activity recognition (HAR) presents significant challenges. Although HAR is mainly used for elderly care, it holds significant potential for supporting firefighter operations. The main challenge of HAR is the recognition of complex actions and continuous transitions from real-time data. This study proposes a real-time firefighter activity recognition (RFAR) system that accurately recognizes 11 activities. The proposed system is based on a wearable device with an integrated accelerometer, ensuring compactness and energy efficiency. It can optimize parameters for deploying the random forest (RF) model on performance-constrained microcontrollers. A new data processing pipeline that integrates a sliding window technique with an abnormality index (AIx) detection technique is proposed. This method achieves an ${F}1$ -score of 96.1% on a private dataset. Real-time experiments with a waist-mounted accelerometer achieved an ${F}1$ -score of 96.2% in rescue simulations conducted by volunteers at a firefighting training facility in Vietnam. To validate, the method is performed on three public datasets: achieving an ${F}1$ -score of 96.6% on SFDLA, 96.6% on MobiFall, and 78.2% on UniMiB-SHAR. Another contribution of this study is the development of a specialized dataset that comprehensively represents fundamental and unique firefighter activities in realistic scenarios.