Machine Learning-Aided All-Organic Air-Permeable Piezoelectric Nanogenerator

Abstract

All-organic piezoelectric mechanical energy harvesters display an excellent electrical output with higher sensitivity due to the superior electrode compatibility between active materials and organic electrodes in comparison to that of metal electrodes. Herein, a stretchable, breathable, and flexible all-organic piezoelectric nanogenerator, made up of PVDF nanofibers and δ-PVDF nanoparticles, fabricated through the electrospinning process in a single step, has been demonstrated for prospective machine learning applications. The δphase PVDF nanoparticles serve as efficient active piezoelectric and ferroelectric components with a piezoelectric coefficient of ∼13 pm/V. In terms of electrical response, a peak-to-peak ∼V OC of 4 V, I SC of 1.8 μA, and maximum power density of ∼1600 μW/m 2 were obtained. The fabricated device also exhibits excellent stretchability and air permeability, enabling the properties of robust wearable devices with a water vapor transmission rate of ∼250 g m −2 day −1 . Here, we have shown that a machine learning algorithm proposed for the different finger motion responses can predict with 94.6% accuracy. Thus, it could recognize different finger gestures efficiently with the highest possible accuracy and predict the possible source point. This feature could be advantageous for prospective health care and security purposes apart from the device and sensor applications.

On-Demand MXene-Coupled Pyroelectricity for Advanced Breathing Sensors and IR Data Receivers

“…To further develop the machine learning (ML) algorithm, numerous data sets of sensor data were generated and then preprocessed to predict the breathing phenomenon. After preprocessing the data sets, they were separated into training and test data and thereafter the models were trained with 4 types of algorithms (Supporting Information, associate discussion S3). − The performance of these ML modes was evaluated using four different metrics: recall, precision, F1 score, and accuracy. These metrics were used to predict how well each model could classify between normal and exhausted breathing based on the input features.…”

“…It can be helpful to draw very effective conclusions from its remarkable visualization technique and to study the data in an effective manner. − For the same reason, we have also utilized supervised machine learning to identify the breathing patterns from a pyroelectric sensor that can be beneficial for human healthcare to identify the symptoms and preliminary problems related to breathing at an earlier stage. These machine learning applications with the pyroelectric sensor could provide us the edge in security applications, IoT-based health monitoring, surveillance, and effective data transmission tools as strong prospective applications. − …”

Roadmap to Human–Machine Interaction through Triboelectric Nanogenerator and Machine Learning Convergence

“…Algorithms can adaptively adjust the TENG’s operating parameters, such as resonance frequency or contact area, to maximize energy generation based on real-time environmental conditions. Through advanced machine learning algorithms, AI contributes to the development of smart energy-harvesting solutions, enhancing the autonomy and sustainability of self-powered systems across various applications. , The integration of AI with self-powered energy harvesting technologies including triboelectric and piezoelectric nanogenerators not only maximizes energy extraction from the environment but also facilitates adaptive and self-aware systems capable of dynamically adjusting their energy usage for prolonged and autonomous operation. , It also plays a pivotal role in optimizing energy harvesting processes, enabling self-powered systems to intelligently capture and utilize ambient energy sources efficiently. , …”