Smoking is a major cause of cancer,heart disease and other afflictions that lead to early mortality.An effective smoking classification mechanism that provides insights into individual smoking habits would assist in i...Smoking is a major cause of cancer,heart disease and other afflictions that lead to early mortality.An effective smoking classification mechanism that provides insights into individual smoking habits would assist in implementing addiction treatment initiatives.Smoking activities often accompany other activities such as drinking or eating.Consequently,smoking activity recognition can be a challenging topic in human activity recognition(HAR).A deep learning framework for smoking activity recognition(SAR)employing smartwatch sensors was proposed together with a deep residual network combined with squeeze-and-excitation modules(ResNetSE)to increase the effectiveness of the SAR framework.The proposed model was tested against basic convolutional neural networks(CNNs)and recurrent neural networks(LSTM,BiLSTM,GRU and BiGRU)to recognize smoking and other similar activities such as drinking,eating and walking using the UT-Smoke dataset.Three different scenarios were investigated for their recognition performances using standard HAR metrics(accuracy,F1-score and the area under the ROC curve).Our proposed ResNetSE outperformed the other basic deep learning networks,with maximum accuracy of 98.63%.展开更多
Background: Young women of reproductive age experience various physiological changes, which they measure and track using various devices, including fitness trackers and smartwatches. However, fitness tracking assessme...Background: Young women of reproductive age experience various physiological changes, which they measure and track using various devices, including fitness trackers and smartwatches. However, fitness tracking assessment methods are ambiguous because they may differ from model to model. Objective: This study aimed to compare the stress level, heart rate, sleep time, number of steps, and distance traveled, which were calculated using fitness tracking methods for daily-life free activity installed in various smartwatches. Materials and Methodology: Healthy women in their 20s to 30s were recruited for this study, which was conducted from December 2021 to June 2022. The finalized participants wore three different smartwatch models (Mi smartband 6, vivosmart<sup>®</sup>4, and Band 6) simultaneously on their person for 48 hours and performed their daily activities and recorded them on an hour-based activity chart. Each smartwatch’s measured data (e.g., age, height, weight, and oral medications) were extracted into five datasets: heart rate, stress level, number of steps, distance, and sleep time. Data analyses were conducted using Spearman’s rank correlation coefficient ρ (for comparing heart rates) and Bland-Altman plots (for assessing heart rate agreement). The smartwatches’ fitness trackers were compared using the mean absolute percentage error. Results: The correlation coefficient showed that vivosmart<sup>®</sup>4 and Band 6 had a higher heart rate agreement (ρ = 0.684). The Bland-Altman plots showed high agreement between Band 6, Mi smartband 6, and vivosmart<sup>®</sup>4. The heart rate measurement method used under free movement was found to be consistent. The examined smartwatches were able to measure heart rate at the same level even under daily-life free movements. Conclusion: Several different smartwatches’ calculated measured values for heart rate had a high agreement. The smartwatches provided accurate heart rate measurements under daily-life free movement conditions. Furthermore, the calculation methods for stress level were found to differ in the fitness tracking of all the smartwatches. .展开更多
To assist with smoking cessation, wearable devices are used to detect the puff (hand-to-mouth gesture)recognition within the smoking activity in a ubiquitous manner. There is a strong assumption that smoking and weari...To assist with smoking cessation, wearable devices are used to detect the puff (hand-to-mouth gesture)recognition within the smoking activity in a ubiquitous manner. There is a strong assumption that smoking and wearing asmartwatch are usually with the same hand. It will certainly fail to detect smoking gesture with the opposite hand. In thiswork, we find an interesting phenomenon: smoking can cause a unique pattern of heart rate (HR) which is quite differentfrom other daily activities’ effects. Based on this psychophysiological response, we propose HeartIt, a just-in-time smokingdetection solution through measuring the HR by a smartwatch. HeartIt works well for the smoker wearing a smartwatchon either wrist. It can accurately distinguish smoking from other similar hand-to-mouth gestures (e.g., eating, drinking).Moreover, we design an adaptive tracker to trigger the HR sensor once the gesture of lighting a cigarette is detected bylow-cost accelerometers. It is robust for different people in various postures and scenarios. Our real-world experimentsshow that the precision and recall rate of HeartIt reaches 96.7% and 99.8%, respectively.展开更多
Automatic and continuous blood pressure monitoring is important for preventing cardiovascular diseases such as hypertension.The evaluation of medication effects and the diagnosis of clinical hypertension can both bene...Automatic and continuous blood pressure monitoring is important for preventing cardiovascular diseases such as hypertension.The evaluation of medication effects and the diagnosis of clinical hypertension can both benefit from continuous monitoring.The current generation of wearable blood pressure monitors frequently encounters limitations with inadequate portability,electrical safety,limited accuracy,and precise position alignment.Here,we present an optical fiber sensor-assisted smartwatch for precise continuous blood pressure monitoring.A fiber adapter and a liquid capsule were used in the building of the blood pressure smartwatch based on an optical fiber sensor.The fiber adapter was used to detect the pulse wave signals,and the liquid capsule was used to expand the sensing area as well as the conformability to the body.The sensor holds a sensitivity of-213μw/kPa,a response time of 5 ms,and high reproducibility with 70,000 cycles.With the assistance of pulse wave signal feature extraction and a machine learning algorithm,the smartwatch can continuously and precisely monitor blood pressure.A wearable smartwatch featuring a signal processing chip,a Bluetooth transmission module,and a specially designed cellphone APP was also created for active health management.The performance in comparison with commercial sphygmomanometer reference measurements shows that the systolic pressure and diastolic pressure errors are-0.35±4.68 mmHg and-2.54±4.07 mmHg,respectively.These values are within the acceptable ranges for Grade A according to the British Hypertension Society(BHS)and the Association for the Advancement of Medical Instrumentation(AAMI).The smartwatch assisted with an optical fiber is expected to offer a practical paradigm in digital health.展开更多
This study proposes an intelligent data analysis model for finding optimal patterns in human activities on the basis of biometric features obtained from four sensors installed on smartphone and smartwatch devices. The...This study proposes an intelligent data analysis model for finding optimal patterns in human activities on the basis of biometric features obtained from four sensors installed on smartphone and smartwatch devices. The proposed model, referred to as Scheduling Activities of smartphone and smartwatch based on Optimal Pattern Model(SA-OPM), consists of four main stages. The first stage relates to the collection of data from four sensors in real time(i.e., two smartphone sensors called accelerometer and gyroscope and two smartwatch sensors of the same name).The second stage involves the preprocessing of the data by converting them into graphs. As graphs are difficult to deal with directly, a deterministic selection algorithm is proposed as a new method to find the optimal root to split the graphs into multiple subgraphs. The third stage entails determining the number of samples related to each subgraph by using the optimization technique called the lion optimization algorithm. The final stage involves the generation of patterns from the optimal subgraph by using the association pattern algorithm called g Span. The pattern finder based on Forward-Backward Rules(FBR) generates the optimal patterns and thus aids humans in organizing their activities. Results indicate that the proposed SA-OPM model generates robust and authentic patterns of human activities.展开更多
We measure and predict states of Activation and Happiness using a body sensing applicationconnected to smartwatches. Through the sensors of commercially available smartwatches we collectindividual mood states and corr...We measure and predict states of Activation and Happiness using a body sensing applicationconnected to smartwatches. Through the sensors of commercially available smartwatches we collectindividual mood states and correlate them with body sensing data such as acceleration, heart rate, lightlevel data, and location, through the GPS sensor built into the smartphone connected to the smartwatchWe polled users on the smartwatch for seven weeks four times per day asking for their mood state. Wefound that both Happiness and Activation are negatively correlated with heart beats and with the levelsof light. People tend to be happier when they are moving more intensely and are feeling less activatedduring weekends. We also found that people with a lower Conscientiousness and Neuroticism andhigher Agreeableness tend to be happy more frequently. In addition, more Activation can be predictedby lower Openness to experience and higher Agreeableness and Conscientiousness. Lastly, we find thattracking people＇s geographical coordinates might play an important role in predicting Happiness andActivation. The methodology we propose is a first step towards building an automated mood trackingsystem, to be used for better teamwork and in combination with social network analysis studies.展开更多
Sensors and physical activity evaluation are quite limited for motionbased commercial devices.Sometimes the accelerometer of the smartwatch is utilized;walking is investigated.The combination can perform better in ter...Sensors and physical activity evaluation are quite limited for motionbased commercial devices.Sometimes the accelerometer of the smartwatch is utilized;walking is investigated.The combination can perform better in terms of sensors and that can be determined by sensors on both the smartwatch and phones,i.e.,accelerometer and gyroscope.For biometric efficiency,some of the diverse activities of daily routine have been evaluated,also with biometric authentication.The result shows that using the different computing techniques in phones and watch for biometric can provide a suitable output based on the mentioned activities.This indicates that the high feasibility and results of continuous biometrics analysis in terms of average daily routine activities.In this research,the set of rules with the real-valued attributes are evolved with the use of a genetic algorithm.With the help of real value genes,the real value attributes cab be encoded,and presentation of new methods which are represents not to cares in the rules.The rule sets which help in maximizing the number of accurate classifications of inputs and supervise classifications are viewed as an optimization problem.The use of Pitt approach to the ML(Machine Learning)and Genetic based system that includes a resolution mechanism among rules that are competing within the same rule sets is utilized.This enhances the efficiency of the overall system,as shown in the research.展开更多
Sensors based Human Activity Recognition(HAR)have numerous applications in eHeath,sports,fitness assessments,ambient assisted living(AAL),human-computer interaction and many more.The human physical activity can be mon...Sensors based Human Activity Recognition(HAR)have numerous applications in eHeath,sports,fitness assessments,ambient assisted living(AAL),human-computer interaction and many more.The human physical activity can be monitored by using wearable sensors or external devices.The usage of external devices has disadvantages in terms of cost,hardware installation,storage,computational time and lighting conditions dependencies.Therefore,most of the researchers used smart devices like smart phones,smart bands and watches which contain various sensors like accelerometer,gyroscope,GPS etc.,and adequate processing capabilities.For the task of recognition,human activities can be broadly categorized as basic and complex human activities.Recognition of complex activities have received very less attention of researchers due to difficulty of problem by using either smart phones or smart watches.Other reasons include lack of sensor-based labeled dataset having several complex human daily life activities.Some of the researchers have worked on the smart phone’s inertial sensors to perform human activity recognition,whereas a few of them used both pocket and wrist positions.In this research,we have proposed a novel framework which is capable to recognize both basic and complex human activities using builtin-sensors of smart phone and smart watch.We have considered 25 physical activities,including 20 complex ones,using smart device’s built-in sensors.To the best of our knowledge,the existing literature consider only up to 15 activities of daily life.展开更多
基金support provided by Thammasat University Research fund under the TSRI,Contract No.TUFF19/2564 and TUFF24/2565,for the project of“AI Ready City Networking in RUN”,based on the RUN Digital Cluster collaboration schemeThis research project was also supported by the Thailand Science Research and Innonation fund,the University of Phayao(Grant No.FF65-RIM041)supported by King Mongkut’s University of Technology North Bangkok,Contract No.KMUTNB-65-KNOW-02.
文摘Smoking is a major cause of cancer,heart disease and other afflictions that lead to early mortality.An effective smoking classification mechanism that provides insights into individual smoking habits would assist in implementing addiction treatment initiatives.Smoking activities often accompany other activities such as drinking or eating.Consequently,smoking activity recognition can be a challenging topic in human activity recognition(HAR).A deep learning framework for smoking activity recognition(SAR)employing smartwatch sensors was proposed together with a deep residual network combined with squeeze-and-excitation modules(ResNetSE)to increase the effectiveness of the SAR framework.The proposed model was tested against basic convolutional neural networks(CNNs)and recurrent neural networks(LSTM,BiLSTM,GRU and BiGRU)to recognize smoking and other similar activities such as drinking,eating and walking using the UT-Smoke dataset.Three different scenarios were investigated for their recognition performances using standard HAR metrics(accuracy,F1-score and the area under the ROC curve).Our proposed ResNetSE outperformed the other basic deep learning networks,with maximum accuracy of 98.63%.
文摘Background: Young women of reproductive age experience various physiological changes, which they measure and track using various devices, including fitness trackers and smartwatches. However, fitness tracking assessment methods are ambiguous because they may differ from model to model. Objective: This study aimed to compare the stress level, heart rate, sleep time, number of steps, and distance traveled, which were calculated using fitness tracking methods for daily-life free activity installed in various smartwatches. Materials and Methodology: Healthy women in their 20s to 30s were recruited for this study, which was conducted from December 2021 to June 2022. The finalized participants wore three different smartwatch models (Mi smartband 6, vivosmart<sup>®</sup>4, and Band 6) simultaneously on their person for 48 hours and performed their daily activities and recorded them on an hour-based activity chart. Each smartwatch’s measured data (e.g., age, height, weight, and oral medications) were extracted into five datasets: heart rate, stress level, number of steps, distance, and sleep time. Data analyses were conducted using Spearman’s rank correlation coefficient ρ (for comparing heart rates) and Bland-Altman plots (for assessing heart rate agreement). The smartwatches’ fitness trackers were compared using the mean absolute percentage error. Results: The correlation coefficient showed that vivosmart<sup>®</sup>4 and Band 6 had a higher heart rate agreement (ρ = 0.684). The Bland-Altman plots showed high agreement between Band 6, Mi smartband 6, and vivosmart<sup>®</sup>4. The heart rate measurement method used under free movement was found to be consistent. The examined smartwatches were able to measure heart rate at the same level even under daily-life free movements. Conclusion: Several different smartwatches’ calculated measured values for heart rate had a high agreement. The smartwatches provided accurate heart rate measurements under daily-life free movement conditions. Furthermore, the calculation methods for stress level were found to differ in the fitness tracking of all the smartwatches. .
基金supported by the National Key Research and Development Program of China under Grant No.2018AAA0101100the National Natural Science Foundation of China under Grant No.62061146001the International Cooperation Project of Shaanxi Province of China under Grant Nos.2019KWZ-05 and 2020KW-004。
文摘To assist with smoking cessation, wearable devices are used to detect the puff (hand-to-mouth gesture)recognition within the smoking activity in a ubiquitous manner. There is a strong assumption that smoking and wearing asmartwatch are usually with the same hand. It will certainly fail to detect smoking gesture with the opposite hand. In thiswork, we find an interesting phenomenon: smoking can cause a unique pattern of heart rate (HR) which is quite differentfrom other daily activities’ effects. Based on this psychophysiological response, we propose HeartIt, a just-in-time smokingdetection solution through measuring the HR by a smartwatch. HeartIt works well for the smoker wearing a smartwatchon either wrist. It can accurately distinguish smoking from other similar hand-to-mouth gestures (e.g., eating, drinking).Moreover, we design an adaptive tracker to trigger the HR sensor once the gesture of lighting a cigarette is detected bylow-cost accelerometers. It is robust for different people in various postures and scenarios. Our real-world experimentsshow that the precision and recall rate of HeartIt reaches 96.7% and 99.8%, respectively.
基金National Science Fund of China for Excellent Young Scholars(No.61922033)Fundamental Research Funds for the Central Universities(HUST:YCJJ202201002).
文摘Automatic and continuous blood pressure monitoring is important for preventing cardiovascular diseases such as hypertension.The evaluation of medication effects and the diagnosis of clinical hypertension can both benefit from continuous monitoring.The current generation of wearable blood pressure monitors frequently encounters limitations with inadequate portability,electrical safety,limited accuracy,and precise position alignment.Here,we present an optical fiber sensor-assisted smartwatch for precise continuous blood pressure monitoring.A fiber adapter and a liquid capsule were used in the building of the blood pressure smartwatch based on an optical fiber sensor.The fiber adapter was used to detect the pulse wave signals,and the liquid capsule was used to expand the sensing area as well as the conformability to the body.The sensor holds a sensitivity of-213μw/kPa,a response time of 5 ms,and high reproducibility with 70,000 cycles.With the assistance of pulse wave signal feature extraction and a machine learning algorithm,the smartwatch can continuously and precisely monitor blood pressure.A wearable smartwatch featuring a signal processing chip,a Bluetooth transmission module,and a specially designed cellphone APP was also created for active health management.The performance in comparison with commercial sphygmomanometer reference measurements shows that the systolic pressure and diastolic pressure errors are-0.35±4.68 mmHg and-2.54±4.07 mmHg,respectively.These values are within the acceptable ranges for Grade A according to the British Hypertension Society(BHS)and the Association for the Advancement of Medical Instrumentation(AAMI).The smartwatch assisted with an optical fiber is expected to offer a practical paradigm in digital health.
文摘This study proposes an intelligent data analysis model for finding optimal patterns in human activities on the basis of biometric features obtained from four sensors installed on smartphone and smartwatch devices. The proposed model, referred to as Scheduling Activities of smartphone and smartwatch based on Optimal Pattern Model(SA-OPM), consists of four main stages. The first stage relates to the collection of data from four sensors in real time(i.e., two smartphone sensors called accelerometer and gyroscope and two smartwatch sensors of the same name).The second stage involves the preprocessing of the data by converting them into graphs. As graphs are difficult to deal with directly, a deterministic selection algorithm is proposed as a new method to find the optimal root to split the graphs into multiple subgraphs. The third stage entails determining the number of samples related to each subgraph by using the optimization technique called the lion optimization algorithm. The final stage involves the generation of patterns from the optimal subgraph by using the association pattern algorithm called g Span. The pattern finder based on Forward-Backward Rules(FBR) generates the optimal patterns and thus aids humans in organizing their activities. Results indicate that the proposed SA-OPM model generates robust and authentic patterns of human activities.
文摘We measure and predict states of Activation and Happiness using a body sensing applicationconnected to smartwatches. Through the sensors of commercially available smartwatches we collectindividual mood states and correlate them with body sensing data such as acceleration, heart rate, lightlevel data, and location, through the GPS sensor built into the smartphone connected to the smartwatchWe polled users on the smartwatch for seven weeks four times per day asking for their mood state. Wefound that both Happiness and Activation are negatively correlated with heart beats and with the levelsof light. People tend to be happier when they are moving more intensely and are feeling less activatedduring weekends. We also found that people with a lower Conscientiousness and Neuroticism andhigher Agreeableness tend to be happy more frequently. In addition, more Activation can be predictedby lower Openness to experience and higher Agreeableness and Conscientiousness. Lastly, we find thattracking people＇s geographical coordinates might play an important role in predicting Happiness andActivation. The methodology we propose is a first step towards building an automated mood trackingsystem, to be used for better teamwork and in combination with social network analysis studies.
基金Deanship of Scientific Research at Majmaah University for supporting this work under Project Number No.RGP-2019-26.
文摘Sensors and physical activity evaluation are quite limited for motionbased commercial devices.Sometimes the accelerometer of the smartwatch is utilized;walking is investigated.The combination can perform better in terms of sensors and that can be determined by sensors on both the smartwatch and phones,i.e.,accelerometer and gyroscope.For biometric efficiency,some of the diverse activities of daily routine have been evaluated,also with biometric authentication.The result shows that using the different computing techniques in phones and watch for biometric can provide a suitable output based on the mentioned activities.This indicates that the high feasibility and results of continuous biometrics analysis in terms of average daily routine activities.In this research,the set of rules with the real-valued attributes are evolved with the use of a genetic algorithm.With the help of real value genes,the real value attributes cab be encoded,and presentation of new methods which are represents not to cares in the rules.The rule sets which help in maximizing the number of accurate classifications of inputs and supervise classifications are viewed as an optimization problem.The use of Pitt approach to the ML(Machine Learning)and Genetic based system that includes a resolution mechanism among rules that are competing within the same rule sets is utilized.This enhances the efficiency of the overall system,as shown in the research.
基金This research was supported by Basic Science Research Program through the National Research Foundation of Korea(NRF)funded by the Ministry of Education(2018R1D1A1B07042967)and the Soonchunhyang University Research Fund.
文摘Sensors based Human Activity Recognition(HAR)have numerous applications in eHeath,sports,fitness assessments,ambient assisted living(AAL),human-computer interaction and many more.The human physical activity can be monitored by using wearable sensors or external devices.The usage of external devices has disadvantages in terms of cost,hardware installation,storage,computational time and lighting conditions dependencies.Therefore,most of the researchers used smart devices like smart phones,smart bands and watches which contain various sensors like accelerometer,gyroscope,GPS etc.,and adequate processing capabilities.For the task of recognition,human activities can be broadly categorized as basic and complex human activities.Recognition of complex activities have received very less attention of researchers due to difficulty of problem by using either smart phones or smart watches.Other reasons include lack of sensor-based labeled dataset having several complex human daily life activities.Some of the researchers have worked on the smart phone’s inertial sensors to perform human activity recognition,whereas a few of them used both pocket and wrist positions.In this research,we have proposed a novel framework which is capable to recognize both basic and complex human activities using builtin-sensors of smart phone and smart watch.We have considered 25 physical activities,including 20 complex ones,using smart device’s built-in sensors.To the best of our knowledge,the existing literature consider only up to 15 activities of daily life.
