Search Results (171)

Precise recognition of individual ovine specimens plays a pivotal role in implementing smart agricultural platforms and optimizing herd management systems. With the development of deep learning technology, sheep face recognition provides an efficient and contactless solution for individual sheep identification. However, with the growth of sheep, their facial features keep changing, which poses challenges for existing sheep face recognition models to maintain accuracy across the dynamic changes in facial features over time, making it difficult to meet practical needs. To address this limitation, we propose the lifelong biometric learning of the sheep face network (LBL-SheepNet), a feature decoupling network designed for continuous adaptation to ovine facial changes, and constructed a dataset of 31,200 images from 55 sheep tracked monthly from 1 to 12 months of age. The LBL-SheepNet model addresses dynamic variations in facial features during sheep growth through a multi-module architectural framework. Firstly, a Squeeze-and-Excitation (SE) module enhances discriminative feature representation through adaptive channel-wise recalibration. Then, a nonlinear feature decoupling module employs a hybrid channel-batch attention mechanism to separate age-related features from identity-specific characteristics. Finally, a correlation analysis module utilizes adversarial learning to suppress age-biased feature interference, ensuring focus on age-invariant identifiers. Experimental results demonstrate that LBL-SheepNet achieves 95.5% identification accuracy and 95.3% average precision on the sheep face dataset. This study introduces a lifelong biometric learning (LBL) mechanism to mitigate recognition accuracy degradation caused by dynamic facial feature variations in growing sheep. By designing a feature decoupling network integrated with adversarial age-invariant learning, the proposed method addresses the performance limitations of existing models in long-term individual identification. Full article

In the era of smart agriculture, accurate identification of plant species is critical for effective crop management, biodiversity monitoring, and the sustainable use of medicinal resources. However, existing deep learning approaches often underperform when applied to fine-grained plant classification tasks due to the lack of domain-specific, high-quality datasets and the limited representational capacity of traditional architectures. This study addresses these challenges by introducing a novel, well-curated leaf image dataset consisting of 39 classes of medicinal and aromatic plants collected from the Aromatic and Medicinal Plant Research Station in Odakkali, Kerala, India. To overcome performance bottlenecks observed with a baseline Convolutional Neural Network (CNN) that achieved only 44.94% accuracy, we progressively enhanced model performance through a series of architectural innovations. These included the use of a pre-trained VGG16 network, data augmentation techniques, and fine-tuning of deeper convolutional layers, followed by the integration of Squeeze-and-Excitation (SE) attention blocks. Ultimately, we propose a hybrid deep learning architecture that combines VGG16 with Batch Normalization, Gated Recurrent Units (GRUs), Transformer modules, and Dilated Convolutions. This final model achieved a peak validation accuracy of 95.24%, significantly outperforming several baseline models, such as custom CNN (44.94%), VGG-19 (59.49%), VGG-16 before augmentation (71.52%), Xception (85.44%), Inception v3 (87.97%), VGG-16 after data augumentation (89.24%), VGG-16 after fine-tuning (90.51%), MobileNetV2 (93.67), and VGG16 with SE block (94.94%). These results demonstrate superior capability in capturing both local textures and global morphological features. The proposed solution not only advances the state of the art in plant classification but also contributes a valuable dataset to the research community. Its real-world applicability spans field-based plant identification, biodiversity conservation, and precision agriculture, offering a scalable tool for automated plant recognition in complex ecological and agricultural environments. Full article

Crop disease identification is a pivotal research area in smart agriculture, forming the foundation for disease mapping and targeted prevention strategies. Among the most prevalent global wheat diseases, powdery mildew—caused by fungal infection—poses a significant threat to crop yield and quality, making early and accurate detection crucial for effective management. In this study, we present QY-SE-MResNet34, a deep learning-based classification model that builds upon ResNet34 to perform multi-class classification of wheat leaf images and assess powdery mildew severity at the single-leaf level. The proposed methodology begins with dataset construction following the GBT 17980.22-2000 national standard for powdery mildew severity grading, resulting in a curated collection of 4248 wheat leaf images at the grain-filling stage across six severity levels. To enhance model performance, we integrated transfer learning with ResNet34, leveraging pretrained weights to improve feature extraction and accelerate convergence. Further refinements included embedding a Squeeze-and-Excitation (SE) block to strengthen feature representation while maintaining computational efficiency. The model architecture was also optimized by modifying the first convolutional layer (conv1)—replacing the original 7 × 7 kernel with a 3 × 3 kernel, adjusting the stride to 1, and setting padding to 1—to better capture fine-grained leaf textures and edge features. Subsequently, the optimal training strategy was determined through hyperparameter tuning experiments, and GrabCut-based background processing along with data augmentation were introduced to enhance model robustness. In addition, interpretability techniques such as channel masking and Grad-CAM were employed to visualize the model’s decision-making process. Experimental validation demonstrated that QY-SE-MResNet34 achieved an 89% classification accuracy, outperforming established models such as ResNet50, VGG16, and MobileNetV2 and surpassing the original ResNet34 by 11%. This study delivers a high-performance solution for single-leaf wheat powdery mildew severity assessment, offering practical value for intelligent disease monitoring and early warning systems in precision agriculture. Full article

The growing demand for the production of food has led to the development of new analytical techniques in the food industry, enabling innovative strategies to streamline food production and ensure its physicochemical and microbiological quality. In this work, a smart sensor was developed using the electrical impedance spectroscopy (EIS) technique. The system is based on discrete Fourier transform (DFT) and incorporates a Howland current source. The experimental results showed that the sensor was able to detect the moisture content in potatoes (Solanum tuberosum L.). Favorable responses were obtained by exciting the system with two frequency intervals: 0–100 Hz and 500–5000 Hz. An exhaustive analysis of the frequency response was performed to identify the most linear behavior in the moisture measurement, with an R-squared of 0.786 and signals in intervals from 500 to 5000 Hz. Moreover, the linearity remained stable across most frequencies, resulting in consistent measurements, even with the implementation of low-cost components. Full article

With the digital transformation of power systems, higher demands are being placed on smart grids for the timely and precise acquisition of the status of transmission and transformation equipment during operational and maintenance processes. When a transformer is energized under no-load conditions, an excitation inrush phenomenon occurs in the windings, posing a hazard to the stable operation of the power system. A machine learning approach is proposed in this paper for predicting the internal magnetic field of transformers under excitation inrush condition, enabling the monitoring of transformer operation status. Experimental results indicate that the mean absolute percentage error (MAPE) for predicting the transformer’s magnetic field using the deep neural network (DNN) model is 4.02%. The average time to obtain a single magnetic field data prediction is 0.41 s, which is 46.68 times faster than traditional finite element analysis (FEA) method, validating the effectiveness of machine learning for magnetic field prediction. Full article

Bringing together the Internet of Things (IoT), LLMs, and Federated Learning (FL) offers exciting possibilities, creating a synergy to build smarter, privacy-preserving distributed systems. This review explores the merging of these technologies, particularly within edge computing environments. We examine current architectures and practical methods enabling this fusion, such as efficient low-rank adaptation (LoRA) for fine-tuning large models and memory-efficient Split Federated Learning (SFL) for collaborative edge training. However, this integration faces significant hurdles: the resource limitations of IoT devices, unreliable network communication, data heterogeneity, diverse security threats, fairness considerations, and regulatory demands. While other surveys cover pairwise combinations, this review distinctively analyzes the three-way synergy, highlighting how IoT, LLMs, and FL working in concert unlock capabilities unattainable otherwise. Our analysis compares various strategies proposed to tackle these issues (e.g., federated vs. centralized, SFL vs. standard FL, DP vs. cryptographic privacy), outlining their practical trade-offs. We showcase real-world progress and potential applications in domains like Industrial IoT and smart cities, considering both opportunities and limitations. Finally, this review identifies critical open questions and promising future research paths, including ultra-lightweight models, robust algorithms for heterogeneity, machine unlearning, standardized benchmarks, novel FL paradigms, and next-generation security. Addressing these areas is essential for responsibly harnessing this powerful technological blend. Full article

Under low-temperature conditions, the load-bearing capacity of piezoelectric stacks arises from coupled thermo-electro-mechanical interactions, with temperature fluctuations, compressive prestress, and excitation voltage critically modulating performance. This study introduces an integrated measurement platform to systematically quantify these interdependencies, employing a cantilever-based sensing mechanism where bending strain serves as a direct metric of load-bearing capacity. A particle swarm-optimized theoretical framework guides the spatial configuration of actuators and sensors, maximizing strain signal fidelity while suppressing noise interference. Experimental characterization reveals three key findings: 1. Voltage-dependent linear enhancement of load-bearing capacity across all operational regimes, unaffected by thermal or mechanical variations; 2. Prestress-induced amplification (79–90% increase from 0 to 6 MPa) and thermally driven attenuation (15–30% reduction from 20 to −70 °C) of static performance; 3. Frequency-dependent degradation (1–6 Hz) in dynamic load-bearing capacity. The methodology establishes a robust foundation for designing multiphysics-compatible instrumentation systems, enabling precise evaluation of smart material behavior under extreme coupled-field conditions. Full article

With advancements in IoT and smart home tech, WiFi-driven gesture recognition is attracting more focus due to its non-contact nature and user-friendly design. However, WiFi signals are affected by multipath effects, attenuation, and interference, resulting in complex and variable signal patterns that pose challenges for accurately modeling gesture characteristics. This study proposes SE-WiGR, an innovative WiFi gesture recognition method to address these challenges. First, channel state information (CSI) related to gesture actions is collected using commercial WiFi devices. Next, the data is preprocessed, and Doppler-shift image data is extracted as input for the network model. Finally, the method integrates the squeeze-and-excitation (SE) mechanism with the VGG16 network to classify gestures. The method achieves a recognition accuracy of 94.12% across multiple scenarios, outperforming the standalone VGG16 network by 4.13%. This improvement confirms that the SE module effectively enhances gesture feature extraction while suppressing background noise. Full article

Bridges play a key and controlling role in transportation systems. Steel bridges are favored for their high strength, good seismic performance, and convenient construction. As important node connectors of steel bridges, high-strength bolts are extremely susceptible to damage such as corrosion and loosening. Therefore, accurate identification of bolt loosening is crucial. First, a new type of adhesive piezoelectric sensor is designed and prepared using PMN-PT piezoelectric single-crystal materials. The PMN-PT sensor and polyvinylidene fluoride (PVDF) sensor are subjected to steel plate fixed frequency load and swept frequency load tests to test the performance of the two sensors. Then, a steel plate component connected by high-strength bolts is designed. By applying exciter square wave load to the structure, the vibration response characteristics of the structure are analyzed to identify the loosening of the bolts. In addition, a piezoelectric smart washer sensor is designed to make up for the shortcomings of the adhesive piezoelectric sensor, and the effectiveness of the piezoelectric smart washer sensor is verified. Finally, a bolt loosening index is proposed to quantitatively evaluate the looseness of the bolt. The results show that the sensitivity of the PMN-PT sensor is 21 times that of the PVDF sensor. Compared with the peak stress change, the natural frequency change is used to identify the bolt loosening more effectively. Piezoelectric smart washer sensor and bolt loosening indicator can be used for bolt loosening identification. Full article

With the rise of smart manufacturing, defect detection in small-size liquid crystal display (LCD) screens has become essential for ensuring product quality. Traditional manual inspection is inefficient and labor-intensive, making it unsuitable for modern automated production. Although machine vision techniques offer improved efficiency, the lack of high-quality defect datasets limits their performance. To overcome this, we propose a symmetry-aware generative framework, the Squeeze-and-Excitation Wasserstein GAN with Gradient Penalty and Visual Geometry Group(VGG)-based perceptual loss (SWG-VGG), for realistic defect image synthesis.By leveraging the symmetry of feature channels through attention mechanisms and perceptual consistency, the model generates high-fidelity defect images that align with real-world structural patterns. Evaluation using the You Only Look Once version 8(YOLOv8) detection model shows that the synthetic dataset improves mAP@0.5 to 0.976—an increase of 10.5% over real-data-only training. Further assessment using Peak Signal-to-Noise Ratio (PSNR), Structural Similarity Index Measure (SSIM), Root Mean Square Error (RMSE), and Content Similarity (CS) confirms the visual and structural quality of the generated images.This symmetry-guided method provides an effective solution for defect data augmentation and aligns closely with Symmetry’s emphasis on structured pattern generation in intelligent vision systems. Full article

Artificial intelligence (AI) is revolutionizing the field of orthopedic bioengineering by increasing diagnostic accuracy and surgical precision and improving patient outcomes. This review highlights using AI for orthopedics in preoperative planning, intraoperative robotics, smart implants, and bone regeneration. AI-powered imaging, automated 3D anatomical modeling, and robotic-assisted surgery have dramatically changed orthopedic practices. AI has improved surgical planning by enhancing complex image interpretation and providing augmented reality guidance to create highly accurate surgical strategies. Intraoperatively, robotic-assisted surgeries enhance accuracy and reduce human error while minimizing invasiveness. AI-powered smart implant sensors allow for in vivo monitoring, early complication detection, and individualized rehabilitation. It has also advanced bone regeneration devices and neuroprosthetics, highlighting its innovation capabilities. While AI advancements in orthopedics are exciting, challenges remain, like the need for standardized surgical system validation protocols, assessing ethical consequences of AI-derived decision-making, and using AI with bioprinting for tissue engineering. Future research should focus on proving the reliability and predictability of the performance of AI-pivoted systems and their adoption within clinical practice. This review synthesizes recent developments and highlights the increasing impact of AI in orthopedic bioengineering and its potential future effectiveness in bone care and beyond. Full article

Addressing hazards from dangerous pollutants requires specialized techniques and risk-control strategies, including detection, neutralization and disposal of contaminants. Smart polymers, designed for specific contaminants, provide powerful solutions for hazardous compound challenges. Their remarkable performance capabilities and potential applications present exciting opportunities for further exploration and development in this field. This editorial aims to provide a comprehensive overview of smart materials with unique features and emerging polymeric technologies that are being developed for isolation, screening, removal, and decontamination of hazardous compounds (e.g., heavy metals, pharmaceutically active contaminants, hormones, endocrine-disrupting chemicals, pathogens, and energetic materials). It highlights recent advancements in synthesis methods, characterization, and the applications of molecularly imprinted polymers (MIPs), along with alternative smart polymeric platforms including hydrogels, ion-imprinted composites, screen-printed electrodes, nanoparticles, and nanofibers. MIPs offer highly selective recognition properties, reusability, long-term stability, and low production costs. Various MIP types, including particles and films, are used in applications like sensing/diagnostic devices for hazardous chemicals, biochemicals, pharmaceuticals, and environmental safety. Full article

Speaker recognition is essential in smart voice applications for personal identification. Current state-of-the-art techniques primarily focus on ideal acoustic conditions. However, the traditional spectrogram struggles to differentiate between noise, reverberation, and speech. To overcome this challenge, MFCC can be replaced with the output from a self-supervised learning model. This study introduces a TDNN enhanced with a pre-trained model for robust performance in noisy and reverberant environments, referred to as PNR-TDNN. The PNR-TDNN employs HuBERT as its backbone, while the TDNN is an improved ECAPA-TDNN. The pre-trained model employs the Canopy/Mini Batch k-means++ strategy. In the TDNN architecture, several enhancements are implemented, including a cross-channel fusion mechanism based on Res2Net. Additionally, a non-average attention mechanism is applied to the pooling operation, focusing on the weight information of each channel within the Squeeze-and-Excitation Net. Furthermore, the contribution of individual channels to the pooling of time-domain frames is enhanced by substituting attentive statistics with multi-head attention statistics. Validated by zhvoice in noisy conditions, the minimized PNR-TDNN demonstrates a 5.19% improvement in EER compared to CAM++. In more challenging environments with noise and reverberation, the minimized PNR-TDNN further improves EER by 3.71% and 9.6%, respectively, and MinDCF by 3.14% and 3.77%, respectively. The proposed method has also been validated on the VoxCeleb1 and cn-celeb_v2 datasets, representing a significant breakthrough in the field of speaker recognition under challenging conditions. This advancement is particularly crucial for enhancing safety and protecting personal identification in voice-enabled microphone applications. Full article

A smart capacitive transducer (SCT) for high-frequency vibration (HFV) measurements was developed, featuring self-calibration for the improvement of measurement accuracy. Measurements using this transducer are performed by positioning it over a thin (10 µm) dielectric layer on a conductive surface. This method was shown to be a non-contact vibration measurement technique for solid surfaces at frequencies over 10 kHz. Auto-calibration is performed every time the SCT is placed on the object being measured. This reduces the influence of positioning and the object’s surface properties on the measurement results. For the transducer’s auto-calibration, a predefined vibration of the measurement electrode is induced. This is achieved using a waveguide excited by a piezo element. The diameter of the developed SCT is 5 mm, with a frequency range of 10 kHz to 1 MHz, an object HFV amplitude measurement resolution of several picometers, and a repeatability error of several percent. Full article

Harnessing the power of phase change materials (PCMs) in asphalt pavements proposes a sustainable solution for addressing temperature-related issues, affording more robust and energy-efficient infrastructure. PCMs hold enormous potential for reforming various industries due to their ability to store and release large amounts of thermal energy, offering noteworthy benefits in energy efficiency, thermal management, and sustainability. The integration of PCMs within pavements presents an increasingly exciting field of research. PCMs have the ability to efficiently manage the changes in and distribution of temperature in asphalt pavements via the release and absorption of latent heat that occurs during the phase shifts of PCMs. Asphalt pavements experience less severe temperatures and a slower rate of temperature fluctuation as a result of this, which in turn reduces the amount of stress caused by temperature. In addition, the function of temperature adjustment that PCMs provide is natural, intelligent, and in line with the direction in which the development of smart pavements is heading in the future. This study aims to explore the impact of organic, inorganic, and mixed organic–inorganic PCMs on diverse surface characteristics of asphalt. In addition, this review addresses current challenges associated with using PCMs in asphalt and explores potential advantages that could facilitate future research in addition to broadening the implementation of PCMs in construction. Full article