Explore the vast range of titles available.

The Convolutional Neural Network (CNN) has demonstrated excellent performance in image recognition and has brought new opportunities for sign language recognition. However, the features undergo many nonlinear transformations while performing the convolutional operation and the traditional CNN models are insufficient in dealing with the correlation between images. In American Sign Language (ASL) recognition, J and Z with moving gestures bring recognition challenges. This paper proposes a novel Two-Stream Mixed (TSM) method with feature extraction and fusion operation to improve the correlation of feature expression between two time-consecutive images for the dynamic gestures. The proposed TSM-CNN system is composed of preprocessing, the TSM block, and CNN classifiers. Two consecutive images in the dynamic gesture are used as inputs of streams, and resizing, transformation, and augmentation are carried out in the preprocessing stage. The fusion feature map obtained by addition and concatenation in the TSM block is used as inputs of the classifiers. Finally, a classifier classifies images. The TSM-CNN model with the highest performance scores depending on three concatenation methods is selected as the definitive recognition model for ASL recognition. We design 4 CNN models with TSM: TSM-LeNet, TSM-AlexNet, TSM-ResNet18, and TSM-ResNet50. The experimental results show that the CNN models with the TSM are better than models without TSM. The TSM-ResNet50 has the best accuracy of 97.57% for MNIST and ASL datasets and is able to be applied to a RGB image sensing system for hearing-impaired people.

In recent years, the telecom market has been very competitive. The cost of retaining existing telecom customers is lower than attracting new customers. It is necessary for a telecom company to understand customer churn through customer relationship management (CRM). Therefore, CRM analyzers are required to predict which customers will churn. This study proposes a customer-churn prediction system that uses an ensemble-learning technique consisting of stacking models and soft voting. Xgboost, Logistic regression, Decision tree, and Naïve Bayes machine-learning algorithms are selected to build a stacking model with two levels, and the three outputs of the second level are used for soft voting. Feature construction of the churn dataset includes equidistant grouping of customer behavior features to expand the space of features and discover latent information from the churn dataset. The original and new churn datasets are analyzed in the stacking ensemble model with four evaluation metrics. The experimental results show that the proposed customer churn predictions have accuracies of 96.12% and 98.09% for the original and new churn datasets, respectively. These results are better than state-of-the-art churn recognition systems.

Piezoelectric electronics possess great potential in flexible sensing and energy harvesting applications. However, they suffer from low electromechanical performance in all-organic piezoelectric systems due to the disordered and weakly-polarized interfaces. Here, we demonstrated an all-polymer piezo-ionic-electric electronics with PVDF/Nafion/PVDF (polyvinylidene difluoride) sandwich structure and regularized ion-electron interfaces. The piezoelectric effect and piezoionic effect mutually couple based on such ion-electron interfaces, endowing this electronics with the unique piezo-ionic-electric working mechanism. Further, owing to the massive interfacial accumulation of ion and electron charges, the electronics obtains a remarkable force-electric coupling enhancement. Experiments show that the electronics presents a high d 33 of ~80.70 pC N −1 , a pressure sensitivity of 51.50 mV kPa −1 and a maximum peak power of 34.66 mW m −2 . It is applicable to be a transducer to light LEDs, and a sensor to detect weak physiological signals or mechanical vibration. This work shows the piezo-ionic-electric electronics as a paradigm of highly-optimized all-polymer piezo-generators. Low electromechanical performance is a limiting factor for all-organic piezoelectric systems. Here, Xu et al. report an all-polymer piezo-ionic-electric electronics, coupling the piezoelectric effect with the piezoionic effect for enhanced performance.

More than four million people worldwide suffer from hearing loss. Recently, new CNNs and deep ensemble-learning technologies have brought promising opportunities to the image-recognition field, so many studies aiming to recognize American Sign Language (ASL) have been conducted to help these people express their thoughts. This paper proposes an ASL Recognition System using Multiple deep CNNs and accuracy-based weighted voting (ARS-MA) composed of three parts: data preprocessing, feature extraction, and classification. Ensemble learning using multiple deep CNNs based on LeNet, AlexNet, VGGNet, GoogleNet, and ResNet were set up for the feature extraction and their results were used to create three new datasets for classification. The proposed accuracy-based weighted voting (AWV) algorithm and four existing machine algorithms were compared for the classification. Two parameters, α and λ, are introduced to increase the accuracy and reduce the testing time in AWV. The experimental results show that the proposed ARS-MA achieved 98.83% and 98.79% accuracy on the ASL Alphabet and ASLA datasets, respectively.

Highlights The underlying mechanism improving piezoelectricity via interfacial polarization is elucidated through combining the experimental results, molecular dynamics simulations and density functional theory calculations. The piezoelectric performance of the nanocomposite is improved based on the successful construction of dual-structure. The piezoelectric sensor and array are capable of identifying human physiological signals and monitoring the distribution of pressure. The emerging interfacial polarization strategy exhibits applicative potential in piezoelectric enhancement. However, there is an ongoing effort to address the inherent limitations arising from charge bridging phenomena and stochastic interface disorder that plague the improvement of piezoelectric performance. Here, we report a dual structure reinforced MXene/PVDF-TrFE piezoelectric composite, whose piezoelectricity is enhanced under the coupling effect of interfacial polarization and structural design. Synergistically, molecular dynamics simulations, density functional theory calculations and experimental validation revealed the details of interfacial interactions, which promotes the net spontaneous polarization of PVDF-TrFE from the 0.56 to 31.41 Debye. The oriented MXene distribution and porous structure not only tripled the piezoelectric response but also achieved an eightfold increase in sensitivity within the low-pressure region, along with demonstrating cyclic stability exceeding 20,000 cycles. The properties reinforcement originating from dual structure is elucidated through the finite element simulation and experimental validation. Attributed to the excellent piezoelectric response and deep learning algorithm, the sensor can effectively recognize the signals of artery pulse and finger flexion. Finally, a 3 × 3 sensor array is fabricated to monitor the pressure distribution wirelessly. This study provides an innovative methodology for reinforcing interfacial polarized piezoelectric materials and insight into structural designs.

Addressing the increasing global demand for sustainable energy, triboelectric nanogenerators (TENGs) have emerged as a promising solution for converting wind energy into electricity, but their practical use is limited by high cut‐in wind speeds and significant wear at high wind speeds. Herein, a high‐durability TENG enabled by easy‐starting design and high‐durability design is proposed for broad‐spectrum wind energy harvesting. It displays remarkable adaptability to varying wind speeds, thereby ensuring dynamic balance and continuous operation. The fan blades of this TENG has been redesigned, reducing the cut‐in wind speed to as low as 0.9 m −1s, with structure analyzed and verified by theory and experiment. Moreover, the continuous running time of this TENG is 6 times longer than the TENG without the high‐durability design, as demonstrated by the comparison of friction wear and the difference of electrical output. This TENG is able to be applied in a highway tunnel environment to harvest wind energy in the tunnel, providing power for three major systems in the tunnel, including environmental monitoring, lighting safety, and flood alerts. This work introduces a new strategy to adapt TENGs to broad‐spectrum wind energy environment, and offers a concept for the construction of tunnel wind energy system. This study presents an easy‐starting and high‐durability triboelectric nanogenerator (ESHD‐TENG) for efficient broad‐spectrum wind energy harvesting. By integrating a fan blade design and a mode‐switching mechanism, the device achieves a low cut‐in wind speed of 0.9 m −1s and significantly enhanced durability, addressing key challenges in current TENG technology for urban and distributed energy applications.

Bioinspired soft robots hold great potential to perform tasks in unstructured terrains. Ferroelectric polymers are highly valued in soft robots for their flexibility, lightweight, and electrically controllable deformation. However, achieving large strains in ferroelectric polymers typically requires high driving voltages, posing a significant challenge for practical applications. In this study, we investigate the role of crystalline domain size in enhancing the electrostrain performance of the relaxor ferroelectric polymer poly(vinylidene fluoride‐trifluoroethylene‐chlorofluoroethylene‐fluorinated alkynes) (P(VDF‐TrFE‐CFE‐FA)). Leveraging its remarkable inverse piezoelectric coefficient (|d33*| = 701 pm V−1), we demonstrate that the planar films exhibit a five times larger bending angle than that of commercial PVDF films at low electric fields. Based on this material, we design a petal‐structured soft robot that achieves a curvature of up to 4.5 cm−1 at a DC electric field of 30 V μm−1. When integrated into a bipedal soft robot, it manifests outstanding electrostrain performance, achieving rapid locomotion of ~19 body lengths per second (BL s−1) at 10 V μm−1 (560 Hz). Moreover, the developed robot demonstrates remarkable abilities in climbing slopes and carrying heavy loads. These findings open new avenues for developing low‐voltage‐driven soft robots with significant promise for practical applications. To overcome the limitation of conventional electroactive materials that require high electric fields, we prepared a relaxor ferroelectric material featuring fine domains, enabling significant strains under low electric fields. This breakthrough in electrostrain performance paves the way for bionic robots to achieve fast locomotion at low electric fields, which provides new opportunities for designing high‐performance soft robots.

Red melilite structure CaY[sub.1−x]Al[sub.3]O[sub.7]: Eux (x = 0.04–0.24) phosphors for white LEDs were synthesized through a straightforward solid-state reaction process. These phosphors exhibit efficient excitation under near-ultraviolet light at 398 nm ([sup.7] F [sub.0] → [sup.5] L [sub.6]), producing the desired emission peak at 622 nm from the transitions of [sup.5] D [sub.0] → [sup.7] F [sub.2]. The Eu doping concentration was also optimized as x = 0.16. The complete 3003 × 3003 energy matrix was constructed based on an effective Hamiltonian including both free-ion and crystal-field interactions within a complete diagonalization method (CDM). Eighteen experimental fluorescent spectra for Eu[sup.3+] ions at the Y[sup.3+] site of CaYAl[sub.3]O[sub.7] crystal were quantitatively identified with high accuracy through fitting calculations. The fitting values are in reasonable agreement with the experimental results, thereby showcasing the efficacy of the CDM in probing luminescent phosphors for white LEDs.

Red melilite structure CaY1−xAl3O7: Eux (x = 0.04–0.24) phosphors for white LEDs were synthesized through a straightforward solid-state reaction process. These phosphors exhibit efficient excitation under near-ultraviolet light at 398 nm (7F0 → 5L6), producing the desired emission peak at 622 nm from the transitions of 5D0 → 7F2. The Eu doping concentration was also optimized as x = 0.16. The complete 3003 × 3003 energy matrix was constructed based on an effective Hamiltonian including both free-ion and crystal-field interactions within a complete diagonalization method (CDM). Eighteen experimental fluorescent spectra for Eu3+ ions at the Y3+ site of CaYAl3O7 crystal were quantitatively identified with high accuracy through fitting calculations. The fitting values are in reasonable agreement with the experimental results, thereby showcasing the efficacy of the CDM in probing luminescent phosphors for white LEDs.

Red melilite structure CaY Al O : Eu ( = 0.04-0.24) phosphors for white LEDs were synthesized through a straightforward solid-state reaction process. These phosphors exhibit efficient excitation under near-ultraviolet light at 398 nm ( → ), producing the desired emission peak at 622 nm from the transitions of → . The Eu doping concentration was also optimized as = 0.16. The complete 3003 × 3003 energy matrix was constructed based on an effective Hamiltonian including both free-ion and crystal-field interactions within a complete diagonalization method (CDM). Eighteen experimental fluorescent spectra for Eu ions at the Y site of CaYAl O crystal were quantitatively identified with high accuracy through fitting calculations. The fitting values are in reasonable agreement with the experimental results, thereby showcasing the efficacy of the CDM in probing luminescent phosphors for white LEDs.