Implementation of IoT Device on Public Fitness Equipment for Health Physical Fitness Improvement

Hsu, Ching-Ting; Chang, Yang-Hung; Chen, Jen‐Shi; Lin, Hau-Han; Chou, Jo-Yin

doi:10.1109/macise49704.2020.00050

Cited by 8 publications

(4 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The authors in ref. [12] described a method for providing exercise recommendations to clients. The wearable device utilizes reed switches as placement sensors to measure step length and frequency and incorporates Arduino, ESP8266, and Bluetooth technologies.…”

Section: Related Workmentioning

confidence: 99%

An IoT-Based Framework for Personalized Health Assessment and Recommendations Using Machine Learning

Jagatheesaperumal¹,

Sujatha²,

Suresh³

et al. 2023

Mathematics

View full text Add to dashboard Cite

To promote a healthy lifestyle, it is essential for individuals to maintain a well-balanced diet and engage in customized workouts tailored to their specific body conditions and health concerns. In this study, we present a framework that assesses an individual’s existing health conditions, enabling people to evaluate their well-being conveniently without the need for a doctor’s consultation. The framework includes a kit that measures various health indicators, such as body temperature, pulse rate, blood oxygen level, and body mass index (BMI), requiring minimal effort from nurses. To analyze the health parameters, we collected data from a diverse group of individuals aged 17–24, including both men and women. The dataset consists of pulse rate (BPM), blood oxygen level (SpO2), BMI, and body temperature, obtained through an integrated Internet of Things (IoT) unit. Prior to analysis, the data was augmented and balanced using machine learning algorithms. Our framework employs a two-stage classifier system to recommend a balanced diet and exercise based on the analyzed data. In this work, machine learning models are utilized to analyze specifically designed datasets for adult healthcare frameworks. Various techniques, including Random Forest, CatBoost classifier, Logistic Regression, and MLP classifier, are employed for this analysis. The algorithm demonstrates its highest accuracy when the training and testing datasets are divided in a 70:30 ratio, resulting in an average accuracy rate of approximately 99% for the mentioned algorithms. Through experimental analysis, we discovered that the CatBoost algorithm outperforms other approaches in terms of achieving maximum prediction accuracy. Additionally, we have developed an interactive web platform that facilitates easy interaction with the implemented framework, enhancing the user experience and accessibility.

show abstract

Section: Related Workmentioning

confidence: 99%

An IoT-Based Framework for Personalized Health Assessment and Recommendations Using Machine Learning

Jagatheesaperumal¹,

Sujatha²,

Suresh³

et al. 2023

Mathematics

View full text Add to dashboard Cite

show abstract

“…This condition holds for all t equal to T DHL , specifically at its optimal value. From the equation of I Lpeak in (7), the optimal deadtime is given by…”

Section: Optimal Deadtime Mathematical Analysismentioning

confidence: 99%

“…Power converters are ubiquitous in industrial and consumer electronics. They are employed in so many applications, from smartphones, tablets, and headphones [3], [4], to TV sets, car electronics, wireless power chargers for electric vehicle [5], [6], public fitness equipment [7], and wearable medical devices [8]. Power converters, such as DC-DC converters, bridges (half and full), and class-D power amplifiers, must present high efficiency and power density [9]- [12].…”

Section: Introductionmentioning

confidence: 99%

A 9.2-ns to 1-s Digitally Controlled Multituned Deadtime Optimization for Efficient GaN HEMT Power Converters

Karimi
¹
,

Ali
²
,

Aghajani
³

et al. 2022

IEEE Trans. Circuits Syst. I

5
0
0
0

View full text Add to dashboard Cite

This paper presents a tunable new deadtime control circuit providing an optimal delay for power converter optimization. Our method can reduce the deadtime loss while improving the efficiency and power density of a given power converter. The circuit presents a reconfigurable delay element to generate a wide range of deadtime for different power conversion applications with varying loads and input voltages. The optimal deadtime equation for buck converters is derived, and its dependency on the input voltage and load is discussed. Experimental results show that the presented circuit can provide a wide range of deadtime delays, ranging from 9.2 ns to 1000 ns. The power consumption of the presented circuit is measured for different capacitive loads (C L ) and operating frequencies ( f s ). The circuit consumed a power between 610 µW and 850 µW across the measured deadtime ranges while C L = 12 pF, V dd = 3.3 V, and f s = 200 kHz. The proposed deadtime generator can operate up to 18 MHz when the minimum deadtime of 9.2 ns is selected. The presented circuit occupies an area of 150µ m × 260µm. The fabricated chip is connected to a buck converter to validate the operation of the proposed circuit. The efficiency of a typical buck converter with minimum T DLH and optimal T DHL at I Load = 25 mA is improved by 12% compared to a converter with a fixed deadtime of T DLH = T DHL = 12 ns.

show abstract

“…The main purpose of this research is not only to predict using running time and distance, but also to use smart wearable technology to record running training process data, and to integrate more running-related feature value data through Recurrent Neural Network (RNN) [2], Long and short-term memory (LSTM) and gate recursive unit (GRU) models are used to analyze and predict the next road running event to achieve whether it can be completed within the closing time of the conference and break through individual road running results, and predict running techniques (step frequency, pace). To analyze and adjust the most suitable mechanical bene ts for running, or by predicting the heart rate, plan the next pace training intensity and weight loss effect [3] [4].…”

Section: Introductionmentioning
confidence: 99%

Research on intelligent analysis of running sports training performance based on artificial intelligence
Yang
¹
,
Liu
²
,
Xu-zhong³
2021
Preprint
1
0
0
0
View full text Add to dashboard Cite

With the increasing awareness of human beings in the pursuit of human health, running in sports has become a fashionable and healthy first choice. The research uses artificial intelligence technology to conduct intelligent analysis when running training, and aims at the use of artificial intelligence technology. Artificial intelligence technology can accurately analyze and predict the application requirements of sports training postures. We proposed a set of sports posture analysis and predict system to design in this paper. It uses the running training record data in the watch heart rate and GPS smart sports watch, and uses Recurrent Neural Network (RNN), Long and short-term memory (LSTM) and Gate recursive unit (GRU) that three types of neural network models to predict whether the road race can be in the conference. And confirm it will be completed within the scheduled closing time, and it will also perform intelligent analysis of physical fitness (heart rate, pace) and running technology (cadence, pace). The training and test data for this study are the running training records from (Running distance, time, heart rate, stride frequency, stride length, pace, calories, altitude and other characteristic values) as input parameters to test and compare the running completion time trend of RNN, LSTM, GRU neural network models in the exercise table predictive power. The results show predict accuracy is the best is GRU method, and the worst is LSTM method. After the hidden layers are added to the three predict models, RNN is slightly regressive, LSTM has a significant trend of improvement, and GRU is less obvious.

show abstract

Implementation of IoT Device on Public Fitness Equipment for Health Physical Fitness Improvement

Cited by 8 publications

References 7 publications

An IoT-Based Framework for Personalized Health Assessment and Recommendations Using Machine Learning

An IoT-Based Framework for Personalized Health Assessment and Recommendations Using Machine Learning

A 9.2-ns to 1-s Digitally Controlled Multituned Deadtime Optimization for Efficient GaN HEMT Power Converters

Research on intelligent analysis of running sports training performance based on artificial intelligence

Contact Info

Product

Resources

About