Monitoring blood pressure is a critical aspect of safeguarding an individual’s health,as early detection of abnormal blood pressure levels facilitates timely medical intervention,ultimately leading to a reduction in ...Monitoring blood pressure is a critical aspect of safeguarding an individual’s health,as early detection of abnormal blood pressure levels facilitates timely medical intervention,ultimately leading to a reduction in mortality rates associated with cardiovascular diseases.Consequently,the development of a robust and continuous blood pressure monitoring system holds paramount significance.In the context of this research paper,we introduce an innovative deep learning regression model that harnesses phonocardiogram(PCG)data to achieve precise blood pressure estimation.Our novel approach incorporates a convolutional neural network(CNN)-based regression model,which not only enhances its adaptability to spatial variations but also empowers it to capture intricate patterns within the PCG signals.These advancements contribute significantly to the overall accuracy of blood pressure estimation.To substantiate the effectiveness of our proposed method,we meticulously gathered PCG signal data from 78 volunteers,adhering to the ethical guidelines of Suranaree University of Technology(Human Research Ethics number EC-65-78).Subsequently,we rigorously preprocessed the dataset to ensure its integrity.We further employed a K-fold cross-validation procedure for data division and alignment,combining the resulting datasets with a CNNfor blood pressure estimation.The experimental results are highly promising,yielding aMeanAbsolute Error(MAE)and standard deviation(STD)of approximately 10.69±7.23 mmHg for systolic pressure and 6.89±5.22 mmHg for diastolic pressure.Our study underscores the potential for precise blood pressure estimation,particularly using PCG signals,paving the way for a practical,non-invasive method with broad applicability in the healthcare domain.Early detection of abnormal blood pressure levels can facilitate timely medical interventions,ultimately reducing cardiovascular disease-related mortality rates.展开更多
A brainwave classification,which does not involve any limb movement and stimulus for character-writing applications,benefits impaired people,in terms of practical communication,because it allows users to command a dev...A brainwave classification,which does not involve any limb movement and stimulus for character-writing applications,benefits impaired people,in terms of practical communication,because it allows users to command a device/computer directly via electroencephalogram signals.In this paper,we propose a new framework based on Empirical Mode Decomposition(EMD)features along with theGaussianMixtureModel(GMM)andKernel Extreme Learning Machine(KELM)-based classifiers.For this purpose,firstly,we introduce EMD to decompose EEG signals into Intrinsic Mode Functions(IMFs),which actually are used as the input features of the brainwave classification for the character-writing application.We hypothesize that EMD along with the appropriate IMF is quite powerful for the brainwave classification,in terms of character applications,because of the wavelet-like decomposition without any down sampling process.Secondly,by getting motivated with shallow learning classifiers,we can provide promising performance for the classification of binary classes,GMM and KELM,which are applied for the learning of features along with the brainwave classification.Lastly,we propose a new method by combining GMMand KELM to fuse the merits of different classifiers.Moreover,the proposed methods are validated by using the volunteer-independent 5-fold cross-validation and accuracy as a standard measurement.The experimental results showed that EMD with the proper IMF achieved better results than the conventional discrete wavelet transform(DWT)feature.Moreover,we found that the EMD feature along with the GMM/KELM-based classifier provides the average accuracy of 77.40%and 80.10%,respectively,which could perform better than the conventional methods where we use DWT along with the artificial neural network classifier in order to get the average accuracy of 80.60%.Furthermore,we obtained the improved performance by combining GMM and KELM,i.e.,average accuracy of 80.60%.These outcomes exhibit the usefulness of the EMD feature combining with GMMand KELM based classifiers for the brainwaveclassification in terms of the Character-Writing application,which do notrequire any limb movement and stimulus.展开更多
The patients with brain diseases(e.g.,Stroke and Amyotrophic Lateral Sclerosis(ALS))are often affected by the injury of motor cortex,which causes a muscular weakness.For this reason,they require rehabilitation with co...The patients with brain diseases(e.g.,Stroke and Amyotrophic Lateral Sclerosis(ALS))are often affected by the injury of motor cortex,which causes a muscular weakness.For this reason,they require rehabilitation with continuous physiotherapy as these diseases can be eased within the initial stages of the symptoms.So far,the popular control system for robot-assisted rehabilitation devices is only of two types which consist of passive and active devices.However,if there is a control system that can directly detect the motor functions,it will induce neuroplasticity to facilitate early motor recovery.In this paper,the control system,which is a motor recovery system with the intent of rehabilitation,focuses on the hand organs and utilizes a brain-computer interface(BCI)technology.The final results depict that the brainwave detection for controlling pneumatic glove in real-time has an accuracy up to 82%.Moreover,the motor recovery system enables the feasibility of brainwave classification from the motor cortex with Artificial Neural Networks(ANN).The overall model performance reveals an accuracy up to 96.56%with sensitivity of 94.22%and specificity of 98.8%.Therefore,the proposed system increases the efficiency of the traditional device control system and tends to provide a better rehabilitation than the traditional physiotherapy alone.展开更多
Smart electric motorcycle-sharing systems based on the digital platform are one of the public transportations that we use in daily lives when the sharing economy is considered.This transportation provides convenience ...Smart electric motorcycle-sharing systems based on the digital platform are one of the public transportations that we use in daily lives when the sharing economy is considered.This transportation provides convenience for users with low-cost systems while it also promotes an environmental conservation.Normally,users rent the vehicle to travel from the origin station to another station near their destination with a one-way trip in which the demand of renting and returning at each station is different.This leads to unbalanced vehicle rental systems.To avoid the full or empty inventory,the electric motorcycle-sharing rebalancing with the fleet optimization is employed to deliver the user experience and increase rental opportunities.In this paper,the authors propose a fleet optimization to manage the appropriate number of vehicles in each station by considering the cost of moving tasks and the rental opportunity to increase business return.Although the increasing number of service stations results in a large action space,the proposed routing algorithm is able filter the size of the action space to enable computing tasks.In this paper,a Deep Reinforcement Learning(DRL)creates the decisionmaking function to decide the appropriate action for fleet allocation from the last state of the number of vehicles at each station in the real environment at Suranaree University of Technology(SUT),Thailand.The obtained results indicate that the proposed concept can reduce the Operating Expenditure(OPEX).展开更多
Recently,the Muscle-Computer Interface(MCI)has been extensively popular for employing Electromyography(EMG)signals to help the development of various assistive devices.However,few studies have focused on ankle foot mo...Recently,the Muscle-Computer Interface(MCI)has been extensively popular for employing Electromyography(EMG)signals to help the development of various assistive devices.However,few studies have focused on ankle foot movement classification considering EMG signals at limb position.This work proposes a new framework considering two EMG signals at a lower-limb position to classify the ankle movement characteristics based on normal walking cycles.For this purpose,we introduce a human anklefoot movement classification method using a two-dimensional-convolutional neural network(2D-CNN)with low-cost EMG sensors based on lowerlimb motion.The time-domain signals of EMG obtained from two sensors belonging to Dorsiflexion,Neutral-position,and Plantarflexion are firstly converted into time-frequency spectrograms by short-time Fourier transform.Afterward,the spectrograms of the three ankle-foot movement types are used as input to the 2D-CNN such that the EMG foot movement types are finally classified.For the evaluation phase,the proposed method is investigated using the healthy volunteer for 5-fold cross-validation,and the accuracy is used as a standard evaluation.The results demonstrate that our approach provides an average accuracy of 99.34%.This exhibits the usefulness of 2D-CNN with low-cost EMG sensors in terms of ankle-foot movement classification at limb position,which offers feasibility for walking.However,the obtained EMG signal is not directly considered at the ankle position.展开更多
The number of accidents in the campus of Suranaree University of Technology(SUT)has increased due to increasing number of personal vehicles.In this paper,we focus on the development of public transportation system usi...The number of accidents in the campus of Suranaree University of Technology(SUT)has increased due to increasing number of personal vehicles.In this paper,we focus on the development of public transportation system using Intelligent Transportation System(ITS)along with the limitation of personal vehicles using sharing economy model.The SUT Smart Transit is utilized as a major public transportation system,while MoreSai@SUT(electric motorcycle services)is a minor public transportation system in this work.They are called Multi-Mode Transportation system as a combination.Moreover,a Vehicle toNetwork(V2N)is used for developing theMulti-Mode Transportation system in the campus.Due to equipping vehicles with On Board Unit(OBU)and 4G LTE modules,the real time speed and locations are transmitted to the cloud.The data is then applied in the proposed mathematical model for the estimation of Estimated Time of Arrival(ETA).In terms of vehicle classifications and counts,we deployed CCTV cameras,and the recorded videos are analyzed by using You Only Look Once(YOLO)algorithm.The simulation and measurement results of SUT Smart Transit and MoreSai@SUT before the covid-19 pandemic are discussed.Contrary to the existing researches,the proposed system is implemented in the real environment.The final results unveil the attractiveness and satisfaction of users.Also,due to the proposed system,the CO_(2) gas gets reduced when Multi-Mode Transportation is implemented practically in the campus.展开更多
Precoding is a beamforming technique that supports multi-streamtransmission in which the RF chain plays a significant role as a digital precoding at the receiver for wireless communication. The traditional precodingco...Precoding is a beamforming technique that supports multi-streamtransmission in which the RF chain plays a significant role as a digital precoding at the receiver for wireless communication. The traditional precodingcontains only digital signal processing and each antenna connects to each RFchain, which provides high transmission efficiency but high cost and hardwarecomplexity. Hybrid precoding is one of the most popular massive multipleinput multiple output (MIMO) techniques that can save costs and avoid usingcomplex hardware. At present, network services are currently in focus with awide range of traffic volumes. In terms of the Quality of Service (QoS), it iscritical that service providers pay a lot of attention to this parameter and itsrelationship to Quality of Experience (QoE) which is the measurement of theoverall level of user satisfaction. Therefore, this paper proposes hybrid precoding of a partially structured system to improve transmission efficiency andallocate resources to provide network services to users for increasing the usersatisfaction under power constraints that optimize the quality of basebandprecoding and radio frequency (RF) precoding by minimizing alternatingalgorithms. We focus on the web browsing, video, and Voice over IP (VOIP)services. Also, a Mean Opinion Score (MOS) is employed to measure thelevel of user satisfaction. The results show that the partially structured systemprovides a good user satisfaction with the network’s services. The partiallystructured system provides high energy efficiency up to 85%. Considering webservice, the partially structured system for 10 users provides MOS at 3.21 whichis higher than 1.75 of fully structured system.展开更多
The shortcoming of Wi-Fi networks is that one user can access the router at a time.This drawback limits the system throughput and delay.This paper proposes a concept of Simultaneously Different Tx/Rx(SDTR)radiation pa...The shortcoming of Wi-Fi networks is that one user can access the router at a time.This drawback limits the system throughput and delay.This paper proposes a concept of Simultaneously Different Tx/Rx(SDTR)radiation patterns with only one antenna set at the router.Furthermore,these two patterns have to be simultaneously operated at the same time so that the system delay can be eased.An omni-directional pattern is employed at router for receiving mode so that the router can sense carrier signal from all directions.At the same time,the router launches a directional beam pointed to another user.A proposed circuit allows these two modes to be able to operate the same time.To evaluate the SDTR concept,a prototype is constructed for testing in real circumstance comparing to computer simulation.As a result,the SDTR concept can improve the system throughput while decreasing the system delay comparing to conventional system.展开更多
Nowadays, Visible Light Communication (VLC) is an attractivealternative technology for wireless communication because it can use somesimple Light Emitting Diodes (LEDs) instead of antennas. Typically, indoorVLC is des...Nowadays, Visible Light Communication (VLC) is an attractivealternative technology for wireless communication because it can use somesimple Light Emitting Diodes (LEDs) instead of antennas. Typically, indoorVLC is designed to transmit only one dataset through multiple LED beams at atime. As a result, the number of users per unit of time (throughput) is relativelylow. Therefore, this paper proposes the design of an indoor VLC system usingswitched-beam technique through computer simulation. The LED lamps aredesigned to be arranged in a circular array and the signal can be transmittedthrough the beam of each LED lamp with the method of separating the datasetto increase the number of simultaneous users for enhancing the indoor VLC.The coverage area is determined from the area where the communication canbe performed at a location on the receiving plane with a Bit Error Rate lessthan or equal to the specified value based on coverage illuminance accordingto International Commission on Illumination (CIE) standards. In this paper,Genetic Algorithm is used to find the suitable solution for designing parameters to achieve maximum coverage area. The results show that a GeneticAlgorithm can be used to find a suitable solution and reduce the computationaltime approximately 382 min in proposed scenarios.展开更多
基金Suranaree University of Technology,Thailand Science Research and Innovation(TSRI)National Science,Research,and Innovation Fund(NSRF)(NRIIS Number 179292).
文摘Monitoring blood pressure is a critical aspect of safeguarding an individual’s health,as early detection of abnormal blood pressure levels facilitates timely medical intervention,ultimately leading to a reduction in mortality rates associated with cardiovascular diseases.Consequently,the development of a robust and continuous blood pressure monitoring system holds paramount significance.In the context of this research paper,we introduce an innovative deep learning regression model that harnesses phonocardiogram(PCG)data to achieve precise blood pressure estimation.Our novel approach incorporates a convolutional neural network(CNN)-based regression model,which not only enhances its adaptability to spatial variations but also empowers it to capture intricate patterns within the PCG signals.These advancements contribute significantly to the overall accuracy of blood pressure estimation.To substantiate the effectiveness of our proposed method,we meticulously gathered PCG signal data from 78 volunteers,adhering to the ethical guidelines of Suranaree University of Technology(Human Research Ethics number EC-65-78).Subsequently,we rigorously preprocessed the dataset to ensure its integrity.We further employed a K-fold cross-validation procedure for data division and alignment,combining the resulting datasets with a CNNfor blood pressure estimation.The experimental results are highly promising,yielding aMeanAbsolute Error(MAE)and standard deviation(STD)of approximately 10.69±7.23 mmHg for systolic pressure and 6.89±5.22 mmHg for diastolic pressure.Our study underscores the potential for precise blood pressure estimation,particularly using PCG signals,paving the way for a practical,non-invasive method with broad applicability in the healthcare domain.Early detection of abnormal blood pressure levels can facilitate timely medical interventions,ultimately reducing cardiovascular disease-related mortality rates.
基金the SUT research and development fund,and in part by the National Natural Science Foundation of China under Grant 61771333All subjects gave their informed consent for inclusion before they participated in the study.The study was conducted in accordance with the Declaration of Helsinki and the protocol was approved by the Ethics Committee of Suranaree University of Technology(License EC-61-14 COA No.16/2561).
文摘A brainwave classification,which does not involve any limb movement and stimulus for character-writing applications,benefits impaired people,in terms of practical communication,because it allows users to command a device/computer directly via electroencephalogram signals.In this paper,we propose a new framework based on Empirical Mode Decomposition(EMD)features along with theGaussianMixtureModel(GMM)andKernel Extreme Learning Machine(KELM)-based classifiers.For this purpose,firstly,we introduce EMD to decompose EEG signals into Intrinsic Mode Functions(IMFs),which actually are used as the input features of the brainwave classification for the character-writing application.We hypothesize that EMD along with the appropriate IMF is quite powerful for the brainwave classification,in terms of character applications,because of the wavelet-like decomposition without any down sampling process.Secondly,by getting motivated with shallow learning classifiers,we can provide promising performance for the classification of binary classes,GMM and KELM,which are applied for the learning of features along with the brainwave classification.Lastly,we propose a new method by combining GMMand KELM to fuse the merits of different classifiers.Moreover,the proposed methods are validated by using the volunteer-independent 5-fold cross-validation and accuracy as a standard measurement.The experimental results showed that EMD with the proper IMF achieved better results than the conventional discrete wavelet transform(DWT)feature.Moreover,we found that the EMD feature along with the GMM/KELM-based classifier provides the average accuracy of 77.40%and 80.10%,respectively,which could perform better than the conventional methods where we use DWT along with the artificial neural network classifier in order to get the average accuracy of 80.60%.Furthermore,we obtained the improved performance by combining GMM and KELM,i.e.,average accuracy of 80.60%.These outcomes exhibit the usefulness of the EMD feature combining with GMMand KELM based classifiers for the brainwaveclassification in terms of the Character-Writing application,which do notrequire any limb movement and stimulus.
基金the Declaration of Helsinki,and the protocol was approved by the Ethics Committee of Suranaree University of Technology(License EC-61-14 COA No.16/2561)the Thailand Research Fund through the RoyalGolden Jubilee Ph.D.Program(Grant No.PHD/0148/2557).
文摘The patients with brain diseases(e.g.,Stroke and Amyotrophic Lateral Sclerosis(ALS))are often affected by the injury of motor cortex,which causes a muscular weakness.For this reason,they require rehabilitation with continuous physiotherapy as these diseases can be eased within the initial stages of the symptoms.So far,the popular control system for robot-assisted rehabilitation devices is only of two types which consist of passive and active devices.However,if there is a control system that can directly detect the motor functions,it will induce neuroplasticity to facilitate early motor recovery.In this paper,the control system,which is a motor recovery system with the intent of rehabilitation,focuses on the hand organs and utilizes a brain-computer interface(BCI)technology.The final results depict that the brainwave detection for controlling pneumatic glove in real-time has an accuracy up to 82%.Moreover,the motor recovery system enables the feasibility of brainwave classification from the motor cortex with Artificial Neural Networks(ANN).The overall model performance reveals an accuracy up to 96.56%with sensitivity of 94.22%and specificity of 98.8%.Therefore,the proposed system increases the efficiency of the traditional device control system and tends to provide a better rehabilitation than the traditional physiotherapy alone.
文摘Smart electric motorcycle-sharing systems based on the digital platform are one of the public transportations that we use in daily lives when the sharing economy is considered.This transportation provides convenience for users with low-cost systems while it also promotes an environmental conservation.Normally,users rent the vehicle to travel from the origin station to another station near their destination with a one-way trip in which the demand of renting and returning at each station is different.This leads to unbalanced vehicle rental systems.To avoid the full or empty inventory,the electric motorcycle-sharing rebalancing with the fleet optimization is employed to deliver the user experience and increase rental opportunities.In this paper,the authors propose a fleet optimization to manage the appropriate number of vehicles in each station by considering the cost of moving tasks and the rental opportunity to increase business return.Although the increasing number of service stations results in a large action space,the proposed routing algorithm is able filter the size of the action space to enable computing tasks.In this paper,a Deep Reinforcement Learning(DRL)creates the decisionmaking function to decide the appropriate action for fleet allocation from the last state of the number of vehicles at each station in the real environment at Suranaree University of Technology(SUT),Thailand.The obtained results indicate that the proposed concept can reduce the Operating Expenditure(OPEX).
基金This work was supported by Suranaree University of Technology(SUT),Thailand Science Research and Innovation(TSRI),and National Science Research and Innovation Fund(NSRF)(NRIIS no.42852).
文摘Recently,the Muscle-Computer Interface(MCI)has been extensively popular for employing Electromyography(EMG)signals to help the development of various assistive devices.However,few studies have focused on ankle foot movement classification considering EMG signals at limb position.This work proposes a new framework considering two EMG signals at a lower-limb position to classify the ankle movement characteristics based on normal walking cycles.For this purpose,we introduce a human anklefoot movement classification method using a two-dimensional-convolutional neural network(2D-CNN)with low-cost EMG sensors based on lowerlimb motion.The time-domain signals of EMG obtained from two sensors belonging to Dorsiflexion,Neutral-position,and Plantarflexion are firstly converted into time-frequency spectrograms by short-time Fourier transform.Afterward,the spectrograms of the three ankle-foot movement types are used as input to the 2D-CNN such that the EMG foot movement types are finally classified.For the evaluation phase,the proposed method is investigated using the healthy volunteer for 5-fold cross-validation,and the accuracy is used as a standard evaluation.The results demonstrate that our approach provides an average accuracy of 99.34%.This exhibits the usefulness of 2D-CNN with low-cost EMG sensors in terms of ankle-foot movement classification at limb position,which offers feasibility for walking.However,the obtained EMG signal is not directly considered at the ankle position.
基金This work was supported by Suranaree University of Technology(SUT).The authors would also like to thank SUT Smart Transit and Thai AI for supporting the experimental and datasets.
文摘The number of accidents in the campus of Suranaree University of Technology(SUT)has increased due to increasing number of personal vehicles.In this paper,we focus on the development of public transportation system using Intelligent Transportation System(ITS)along with the limitation of personal vehicles using sharing economy model.The SUT Smart Transit is utilized as a major public transportation system,while MoreSai@SUT(electric motorcycle services)is a minor public transportation system in this work.They are called Multi-Mode Transportation system as a combination.Moreover,a Vehicle toNetwork(V2N)is used for developing theMulti-Mode Transportation system in the campus.Due to equipping vehicles with On Board Unit(OBU)and 4G LTE modules,the real time speed and locations are transmitted to the cloud.The data is then applied in the proposed mathematical model for the estimation of Estimated Time of Arrival(ETA).In terms of vehicle classifications and counts,we deployed CCTV cameras,and the recorded videos are analyzed by using You Only Look Once(YOLO)algorithm.The simulation and measurement results of SUT Smart Transit and MoreSai@SUT before the covid-19 pandemic are discussed.Contrary to the existing researches,the proposed system is implemented in the real environment.The final results unveil the attractiveness and satisfaction of users.Also,due to the proposed system,the CO_(2) gas gets reduced when Multi-Mode Transportation is implemented practically in the campus.
文摘Precoding is a beamforming technique that supports multi-streamtransmission in which the RF chain plays a significant role as a digital precoding at the receiver for wireless communication. The traditional precodingcontains only digital signal processing and each antenna connects to each RFchain, which provides high transmission efficiency but high cost and hardwarecomplexity. Hybrid precoding is one of the most popular massive multipleinput multiple output (MIMO) techniques that can save costs and avoid usingcomplex hardware. At present, network services are currently in focus with awide range of traffic volumes. In terms of the Quality of Service (QoS), it iscritical that service providers pay a lot of attention to this parameter and itsrelationship to Quality of Experience (QoE) which is the measurement of theoverall level of user satisfaction. Therefore, this paper proposes hybrid precoding of a partially structured system to improve transmission efficiency andallocate resources to provide network services to users for increasing the usersatisfaction under power constraints that optimize the quality of basebandprecoding and radio frequency (RF) precoding by minimizing alternatingalgorithms. We focus on the web browsing, video, and Voice over IP (VOIP)services. Also, a Mean Opinion Score (MOS) is employed to measure thelevel of user satisfaction. The results show that the partially structured systemprovides a good user satisfaction with the network’s services. The partiallystructured system provides high energy efficiency up to 85%. Considering webservice, the partially structured system for 10 users provides MOS at 3.21 whichis higher than 1.75 of fully structured system.
基金This work is financially supported from the Thailand Research Fund through the Royal Golden Jubilee Ph.D.program(Grant No.PHD/0118/2558)。
文摘The shortcoming of Wi-Fi networks is that one user can access the router at a time.This drawback limits the system throughput and delay.This paper proposes a concept of Simultaneously Different Tx/Rx(SDTR)radiation patterns with only one antenna set at the router.Furthermore,these two patterns have to be simultaneously operated at the same time so that the system delay can be eased.An omni-directional pattern is employed at router for receiving mode so that the router can sense carrier signal from all directions.At the same time,the router launches a directional beam pointed to another user.A proposed circuit allows these two modes to be able to operate the same time.To evaluate the SDTR concept,a prototype is constructed for testing in real circumstance comparing to computer simulation.As a result,the SDTR concept can improve the system throughput while decreasing the system delay comparing to conventional system.
文摘Nowadays, Visible Light Communication (VLC) is an attractivealternative technology for wireless communication because it can use somesimple Light Emitting Diodes (LEDs) instead of antennas. Typically, indoorVLC is designed to transmit only one dataset through multiple LED beams at atime. As a result, the number of users per unit of time (throughput) is relativelylow. Therefore, this paper proposes the design of an indoor VLC system usingswitched-beam technique through computer simulation. The LED lamps aredesigned to be arranged in a circular array and the signal can be transmittedthrough the beam of each LED lamp with the method of separating the datasetto increase the number of simultaneous users for enhancing the indoor VLC.The coverage area is determined from the area where the communication canbe performed at a location on the receiving plane with a Bit Error Rate lessthan or equal to the specified value based on coverage illuminance accordingto International Commission on Illumination (CIE) standards. In this paper,Genetic Algorithm is used to find the suitable solution for designing parameters to achieve maximum coverage area. The results show that a GeneticAlgorithm can be used to find a suitable solution and reduce the computationaltime approximately 382 min in proposed scenarios.
