Integrating Tiny Machine Learning(TinyML)with edge computing in remotely sensed images enhances the capabilities of road anomaly detection on a broader level.Constrained devices efficiently implement a Binary Neural N...Integrating Tiny Machine Learning(TinyML)with edge computing in remotely sensed images enhances the capabilities of road anomaly detection on a broader level.Constrained devices efficiently implement a Binary Neural Network(BNN)for road feature extraction,utilizing quantization and compression through a pruning strategy.The modifications resulted in a 28-fold decrease in memory usage and a 25%enhancement in inference speed while only experiencing a 2.5%decrease in accuracy.It showcases its superiority over conventional detection algorithms in different road image scenarios.Although constrained by computer resources and training datasets,our results indicate opportunities for future research,demonstrating that quantization and focused optimization can significantly improve machine learning models’accuracy and operational efficiency.ARM Cortex-M0 gives practical feasibility and substantial benefits while deploying our optimized BNN model on this low-power device:Advanced machine learning in edge computing.The analysis work delves into the educational significance of TinyML and its essential function in analyzing road networks using remote sensing,suggesting ways to improve smart city frameworks in road network assessment,traffic management,and autonomous vehicle navigation systems by emphasizing the importance of new technologies for maintaining and safeguarding road networks.展开更多
Recently, the development of the Internet of Things (IoT) hasenabled continuous and personal electrocardiogram (ECG) monitoring. In theECG monitoring system, classification plays an important role because it canselect...Recently, the development of the Internet of Things (IoT) hasenabled continuous and personal electrocardiogram (ECG) monitoring. In theECG monitoring system, classification plays an important role because it canselect useful data (i.e., reduce the size of the dataset) and identify abnormaldata that can be used to detect the clinical diagnosis and guide furthertreatment. Since the classification requires computing capability, the ECGdata are usually delivered to the gateway or the server where the classificationis performed based on its computing resource. However, real-time ECG datatransmission continuously consumes battery and network resources, whichare expensive and limited. To mitigate this problem, this paper proposes atiny machine learning (TinyML)-based classification (i.e., TinyCES), wherethe ECG monitoring device performs the classification by itself based onthe machine-learning model, which can reduce the memory and the networkresource usages for the classification. To demonstrate the feasibility, afterwe configure the convolutional neural networks (CNN)-based model usingECG data from the Massachusetts Institute of Technology (MIT)-Beth IsraelHospital (BIH) arrhythmia and the Physikalisch Technische Bundesanstalt(PTB) diagnostic ECG databases, TinyCES is validated using the TinyMLsupportedArduino prototype. The performance results show that TinyCEScan have an approximately 97% detection ratio, which means that it has greatpotential to be a lightweight and resource-efficient ECG monitoring system.展开更多
In the uncertainties within which the worldwide food security lies nowadays,the agricultural industry is raising a crucial need for being equipped with the state-of-the-art technologies for a more efficient,climate-re...In the uncertainties within which the worldwide food security lies nowadays,the agricultural industry is raising a crucial need for being equipped with the state-of-the-art technologies for a more efficient,climate-resilient and sustainable production.The traditional production methods have to be revisited,and opportunities should be given for the innovative solutions henceforth brought by big data analytics,cloud computing and internet of things(IoT).In this context,we develop an optimized tinyML-oriented model for an active machine learningbased greenhouse microclimate management to be integrated in an on-field microcontroller.We design an experimental strawberry greenhouse from which we collect multivariate climate data through installed sensors.The obtained values'combinations are labeled according to a five-action multi-label control strategy,then used to prepare a machine learning-ready dataset.The dataset is used to train and five-fold cross-validate 90 Multi-Layer Perceptrons(MLPs)with varied hyperparameters to select the most performant–yet optimized–model instance for the addressed task.Our multi-label control approach enables designing highly scalable models with reduced computational complexity,comprising only n control neurons instead of(1+∑n k=1Cn k)neurons(usually generated from a classic single-label approach from n input variables).Our final selected model incorporates 2 hidden layers with 7 and 8 neurons respectively and 151 parameters;it scored a mean accuracy of 97%during the cross-validation phase,then 96%on our supplementary test set.The model enables an intelligent and autonomous greenhouse management with the less required computations.It can be efficiently deployed in microcontrollers within real world operating conditions.展开更多
Forests promote the conservation of biodiversity and also play a crucial role in safeguarding theenvironment against erosion,landslides,and climate change.However,illegal logging remains a significant threatworldwide,...Forests promote the conservation of biodiversity and also play a crucial role in safeguarding theenvironment against erosion,landslides,and climate change.However,illegal logging remains a significant threatworldwide,necessitating the development of automatic logging detection systems in forests.This paper proposesthe use of long-range,low-powered,and smart Internet of Things(IoT)nodes to enhance forest monitoringcapabilities.The research framework involves developing IoT devices for forest sound classification andtransmitting each node’s status to a gateway at the forest base station,which further sends the obtained datathrough cellular connectivity to a cloud server.The key issues addressed in this work include sensor and boardselection,Machine Learning(ML)model development for audio classification,TinyML implementation on amicrocontroller,choice of communication protocol,gateway selection,and power consumption optimization.Unlike the existing solutions,the developed node prototype uses an array of two microphone sensors forredundancy,and an ensemble network consisting of Long Short-Term Memory(LSTM)and ConvolutionalNeural Network(CNN)models for improved classification accuracy.The model outperforms LSTM and CNNmodels when used independently and also gave 88%accuracy after quantization.Notably,this solutiondemonstrates cost efficiency and high potential for scalability.展开更多
基金supported by the National Natural Science Foundation of China(61170147)Scientific Research Project of Zhejiang Provincial Department of Education in China(Y202146796)+2 种基金Natural Science Foundation of Zhejiang Province in China(LTY22F020003)Wenzhou Major Scientific and Technological Innovation Project of China(ZG2021029)Scientific and Technological Projects of Henan Province in China(202102210172).
文摘Integrating Tiny Machine Learning(TinyML)with edge computing in remotely sensed images enhances the capabilities of road anomaly detection on a broader level.Constrained devices efficiently implement a Binary Neural Network(BNN)for road feature extraction,utilizing quantization and compression through a pruning strategy.The modifications resulted in a 28-fold decrease in memory usage and a 25%enhancement in inference speed while only experiencing a 2.5%decrease in accuracy.It showcases its superiority over conventional detection algorithms in different road image scenarios.Although constrained by computer resources and training datasets,our results indicate opportunities for future research,demonstrating that quantization and focused optimization can significantly improve machine learning models’accuracy and operational efficiency.ARM Cortex-M0 gives practical feasibility and substantial benefits while deploying our optimized BNN model on this low-power device:Advanced machine learning in edge computing.The analysis work delves into the educational significance of TinyML and its essential function in analyzing road networks using remote sensing,suggesting ways to improve smart city frameworks in road network assessment,traffic management,and autonomous vehicle navigation systems by emphasizing the importance of new technologies for maintaining and safeguarding road networks.
基金supported by National Research Foundation (NRF)of Korea Grant funded by the Korean Government (MSIP) (No.2022R1F1A1063183).
文摘Recently, the development of the Internet of Things (IoT) hasenabled continuous and personal electrocardiogram (ECG) monitoring. In theECG monitoring system, classification plays an important role because it canselect useful data (i.e., reduce the size of the dataset) and identify abnormaldata that can be used to detect the clinical diagnosis and guide furthertreatment. Since the classification requires computing capability, the ECGdata are usually delivered to the gateway or the server where the classificationis performed based on its computing resource. However, real-time ECG datatransmission continuously consumes battery and network resources, whichare expensive and limited. To mitigate this problem, this paper proposes atiny machine learning (TinyML)-based classification (i.e., TinyCES), wherethe ECG monitoring device performs the classification by itself based onthe machine-learning model, which can reduce the memory and the networkresource usages for the classification. To demonstrate the feasibility, afterwe configure the convolutional neural networks (CNN)-based model usingECG data from the Massachusetts Institute of Technology (MIT)-Beth IsraelHospital (BIH) arrhythmia and the Physikalisch Technische Bundesanstalt(PTB) diagnostic ECG databases, TinyCES is validated using the TinyMLsupportedArduino prototype. The performance results show that TinyCEScan have an approximately 97% detection ratio, which means that it has greatpotential to be a lightweight and resource-efficient ECG monitoring system.
文摘In the uncertainties within which the worldwide food security lies nowadays,the agricultural industry is raising a crucial need for being equipped with the state-of-the-art technologies for a more efficient,climate-resilient and sustainable production.The traditional production methods have to be revisited,and opportunities should be given for the innovative solutions henceforth brought by big data analytics,cloud computing and internet of things(IoT).In this context,we develop an optimized tinyML-oriented model for an active machine learningbased greenhouse microclimate management to be integrated in an on-field microcontroller.We design an experimental strawberry greenhouse from which we collect multivariate climate data through installed sensors.The obtained values'combinations are labeled according to a five-action multi-label control strategy,then used to prepare a machine learning-ready dataset.The dataset is used to train and five-fold cross-validate 90 Multi-Layer Perceptrons(MLPs)with varied hyperparameters to select the most performant–yet optimized–model instance for the addressed task.Our multi-label control approach enables designing highly scalable models with reduced computational complexity,comprising only n control neurons instead of(1+∑n k=1Cn k)neurons(usually generated from a classic single-label approach from n input variables).Our final selected model incorporates 2 hidden layers with 7 and 8 neurons respectively and 151 parameters;it scored a mean accuracy of 97%during the cross-validation phase,then 96%on our supplementary test set.The model enables an intelligent and autonomous greenhouse management with the less required computations.It can be efficiently deployed in microcontrollers within real world operating conditions.
基金funded by Climate Change AI(2023 innovation grant-https://www.climatechange.ai/innovation_grants).
文摘Forests promote the conservation of biodiversity and also play a crucial role in safeguarding theenvironment against erosion,landslides,and climate change.However,illegal logging remains a significant threatworldwide,necessitating the development of automatic logging detection systems in forests.This paper proposesthe use of long-range,low-powered,and smart Internet of Things(IoT)nodes to enhance forest monitoringcapabilities.The research framework involves developing IoT devices for forest sound classification andtransmitting each node’s status to a gateway at the forest base station,which further sends the obtained datathrough cellular connectivity to a cloud server.The key issues addressed in this work include sensor and boardselection,Machine Learning(ML)model development for audio classification,TinyML implementation on amicrocontroller,choice of communication protocol,gateway selection,and power consumption optimization.Unlike the existing solutions,the developed node prototype uses an array of two microphone sensors forredundancy,and an ensemble network consisting of Long Short-Term Memory(LSTM)and ConvolutionalNeural Network(CNN)models for improved classification accuracy.The model outperforms LSTM and CNNmodels when used independently and also gave 88%accuracy after quantization.Notably,this solutiondemonstrates cost efficiency and high potential for scalability.
