A Comprehensive Survey on TinyML

Noninvasive Diabetes Detection through Human Breath Using TinyML-Powered E-Nose

“…The application of TensorFlow Lite or TinyML is not available for some machine learning models due to limitations in model conversion [ 52 , 53 , 54 ]. However, the performance of algorithms for detecting HI or DMI patients through new exhaled-breath tests was evaluated.…”

“…For the dataset used, the inferiority of KNN and Random Forest in detecting DMI is noticeable, with values of 85% and 90%, approaching false positives. Detecting as many true positives as possible while reducing the number of false positives is crucial [ 16 , 35 , 36 ], as well as understanding the approach of this research in implementing TinyML with TensorFlow Lite on a microcontroller for qualitatively predicting the health status of patients with diabetes mellitus based on ketones related to their BGL, without the need for pre-processing data or the use of the Internet of Things or cloud services [ 53 , 54 , 55 , 56 ]. The most accurate algorithm is XGBoost due to its superior conversion features to a TensorFlow Lite model, detailed in Section 3.4 .…”

“…These algorithms have proven effective in diabetes mellitus detection, as corroborated in previous studies in cloud-based systems or processing results on a computer [ 44 , 51 , 52 ]. While effective, limitations persist, notably with TinyML integration and the explainability of certain algorithms, hindering diagnosis interpretation in case of misdiagnosis [ 53 , 54 , 55 , 56 ]. In contrast, the XGBoost algorithm can be converted to these formats but with the disadvantage of losses in precision and recall metrics, making the process more complicated.…”

“…Integrating new breath samples into a trained algorithm requires a computer, analyzing differences between samples from sick and healthy individuals [ 44 , 51 , 52 ]. However, there is a solution to this limitation using TinyML, offering edge artificial intelligence (AI) capable of processing data locally, without the need for data transfer, preserving information, reducing latency, energy consumption, and enhancing data privacy/security [ 53 , 54 , 55 , 56 ].…”

Green IoT Event Detection for Carbon-Emission Monitoring in Sensor Networks

“…The overarching challenges associated with the current/traditional server/desktop-based computers approach for machine learning have been well recognized, primarily in terms of their energy consumption, carbon footprint, and operational costs, which has consequently given rise to a young but growing paradigm shift (deemed TinyML) involving utilizing microcontrollers for data analysis as an alternative/solution [ 31 , 32 , 33 , 34 , 35 ]. Some examples where AI/ML can complement the efficiency of microcontrollers without compromising environmental sustainability include life prediction of turbofan engines [ 36 ], gas leakage detection [ 37 ], driver drowsiness detector [ 38 ], water leak detection [ 35 ], or fruit variety classification [ 39 ].…”