Search Results (9,852)

Contamination with foreign fibers—such as mulch films and polypropylene strands—during cotton harvesting and processing severely compromises fiber quality. The traditional detection methods often fail to identify fine impurities under visible light, while full-spectrum hyperspectral imaging (HSI) techniques—despite their effectiveness—tend to be prohibitively expensive and computationally intensive. Specifically, the vast amount of redundant spectral information in full-spectrum HSI escalates both the system’s costs and processing challenges. To address these challenges, this study presents an intelligent detection framework that integrates optimized spectral band selection with a lightweight neural network. A novel hybrid Harris Hawks–Whale Optimization Operator (HWOO) is employed to isolate 12 discriminative bands from the original 288 channels, effectively eliminating redundant spectral data. Additionally, a lightweight attention mechanism, combined with a depthwise convolution module, enables real-time inference for online production. The proposed attention-enhanced CNN architecture achieves a 99.75% classification accuracy with real-time processing at 12.201 μs per pixel, surpassing the full-spectrum models by 11.57% in its accuracy while drastically reducing the processing time from 370.1 μs per pixel. This approach not only enables the high-speed removal of impurities in harvested seed cotton production lines but also offers a cost-effective pathway to practical multispectral solutions. Moreover, this methodology demonstrates broad applicability for quality control in agricultural product processing. Full article

To address critical challenges in tiny object detection within remote sensing imagery, including resolution–semantic imbalance, inefficient feature fusion, and insufficient localization accuracy, this study proposes Hierarchical Feature Compensation You Only Look Once 11 (HFC-YOLO11), a lightweight detection model based on hierarchical feature compensation. Firstly, by reconstructing the feature pyramid architecture, we preserve the high-resolution P2 feature layer in shallow networks to enhance the fine-grained feature representation for tiny targets, while eliminating redundant P5 layers to reduce the computational complexity. In addition, a depth-aware differentiated module design strategy is proposed: GhostBottleneck modules are adopted in shallow layers to improve its feature reuse efficiency, while standard Bottleneck modules are maintained in deep layers to strengthen the semantic feature extraction. Furthermore, an Extended Intersection over Union loss function (EIoU) is developed, incorporating boundary alignment penalty terms and scale-adaptive weight mechanisms to optimize the sub-pixel-level localization accuracy. Experimental results on the AI-TOD and VisDrone2019 datasets demonstrate that the improved model achieves mAP50 improvements of 3.4% and 2.7%, respectively, compared to the baseline YOLO11s, while reducing its parameters by 27.4%. Ablation studies validate the balanced performance of the hierarchical feature compensation strategy in the preservation of resolution and computational efficiency. Visualization results confirm an enhanced robustness against complex background interference. HFC-YOLO11 exhibits superior accuracy and generalization capability in tiny object detection tasks, effectively meeting practical application requirements for tiny object recognition. Full article

The emergence of the AI era driven by Large Language Models (LLMs) and the next-generation high-definition multimedia interface for immersive technologies (AR/VR/metaverse) have created an unprecedented demand for high-bandwidth interconnects. While optical communication systems provide a broad bandwidth, their relatively low power efficiency continues to limit their deployment in new applications. This work addresses the power efficiency challenges in CMOS optical transceiver design, leveraging the inherent cost and integration advantages of CMOS technology. After outlining the design principles for low-power optical transmitter (Tx) and receiver (Rx) design, we present a comprehensive design of a low-power optical transceiver chipset implemented in 28 nm CMOS. The Tx features a high-impedance asymmetric current-steering output stage with a stacked architecture that facilitates unipolar power supply operation for the efficient anode driving of a common-cathode VCSEL array and achieved a power efficiency of 1.59 pJ/bit. The Rx incorporates a tail-current-controlled Cherry–Hooper-based variable gain amplifier (VGA), which achieved a transimpedance gain that ranged from 68.4 to 78.5 dB$\Omega$ and a power efficiency of 1.06 pJ/bit. The Rx–Tx back-to-back measurements confirmed successful data transmission at 4 × 20 Gbps, which demonstrated an overall power efficiency of 2.65 pJ/bit. Full article

This study reports the development of peptide-based hydrogels for the encapsulation and controlled release of peptide nucleic acids in drug delivery applications. Ultrashort aromatic peptides, such as Fmoc-FF, self-assemble into biocompatible hydrogels with nanostructured architectures. The functionalization of tripeptides (Fmoc-FFK and Fmoc-FFC) with lysine (K) or cysteine (C) enables electrostatic or covalent interactions with model PNAs engineered with glutamic acid or cysteine residues, respectively. Hydrogels were polymerized in situ in the presence of PNAs, and component ratios were systematically varied to optimize mechanical properties, loading efficiency, and release kinetics. The formulations obtained with a 1/10 ratio of Fmoc-FF(K or C)/Fmoc-FF provided an optimal balance between structural integrity and delivery performance. All hydrogel formulations demonstrated high stiffness (G′ > 19,000 Pa), excellent water retention, and minimal swelling under physiological conditions (ΔW < 4%). The release studies over 10 days showed that electrostatic loading enabled faster and higher release (up to 90%), while covalent bonding resulted in slower, sustained delivery (~15%). These findings highlight the tunability of the hydrogel system for diverse therapeutic applications. Full article

Emerging contaminants (ECs) in wastewater threaten environmental and human health, while conventional methods often prove inadequate. This has driven increased concern among decision makers, justifying the need for innovative and effective treatment approaches. Pyrite-derived materials have attracted great interest in advanced oxidation processes (AOPs) as catalysts because of their unique Fe-S structure, ability to undergo redox cycling, and environmental friendliness. This review explores recent advances in pyrite-derived materials for AOP applications, focusing on their synthesis, catalytic mechanisms, and pollutant degradation. It examines how pyrite activates oxidants such as hydrogen peroxide (H₂O₂), peracetic acid (PAA), and peroxymonosulfate (PMS) can be used to generate reactive oxygen species (ROS). The role of multi-dimensional pyrite architectures (0D–3D) in enhancing charge transfer, catalytic activity, and recyclability is also discussed. Key challenges, including catalyst stability, industrial scalability, and Fe/S leaching, are addressed alongside potential solutions. Future directions include the integration of pyrite-based catalysts with hybrid materials, as well as green synthesis to improve practical applications. This review provides researchers and engineers with valuable insights into developing sustainable wastewater treatment technologies. Full article

The convergence of blockchain technology with artificial intelligence presents a promising paradigm shift in data management and trust within AI ecosystems. Starting from the initial cryptocurrency-oriented versions, the blockchain potential is improved up to the highly scalable and programmable versions available currently. Even though the integration of real-world applications offers a promising future for distributed computing, there are limitations on executing AI models on blockchain due to high external library dependencies, storage, and cost constraints. Addressing this issue, this study explores the transformative potential of integrating blockchain with AI within the paradigm of blockchain 5.0. We propose the next-generation novel blockchain architecture named Doctrina that allows executing AI models directly on blockchain. Compared to the existing approaches, Doctrina allows sharing and using AI services in a fully distributed and privacy-preserved manner. Full article

Medical image classification often relies on CNNs to capture local details (e.g., lesions, nodules) or on transformers to model long-range dependencies. However, each paradigm alone is limited in addressing both fine-grained structures and broader anatomical context. We propose ConvTransGFusion, a hybrid model that fuses ConvNeXt (for refined convolutional features) and Swin Transformer (for hierarchical global attention) using a learnable dual-attention gating mechanism. By aligning spatial dimensions, scaling each branch adaptively, and applying both channel and spatial attention, the proposed architecture bridges local and global representations, melding fine‑grained lesion details with the broader anatomical context essential for accurate diagnosis. Tested on four diverse medical imaging datasets—including X-ray, ultrasound, and MRI scans—the proposed model consistently achieves superior accuracy, precision, recall, F1, and AUC over state-of-the-art CNNs and transformers. Our findings highlight the benefits of combining convolutional inductive biases and transformer-based global context in a single learnable framework, positioning ConvTransGFusion as a robust and versatile solution for real-world clinical applications. Full article

This study investigates the ability of well-known deep learning models, such as ResNet and EfficientNet, to perform audio-based infant cry detection. By comparing the performance of different machine learning algorithms, this study seeks to determine the most effective approach for the detection of infant crying, enhancing the functionality of baby monitoring systems and contributing to a more advanced understanding of audio-based deep learning applications. Understanding and accurately detecting a baby’s cries is crucial for ensuring their safety and well-being, a concern shared by new and expecting parents worldwide. Despite advancements in child health, as noted by UNICEF’s 2022 report of the lowest ever recorded child mortality rate, there is still room for technological improvement. This paper presents a comprehensive evaluation of deep learning models for infant cry detection, analyzing the performance of various architectures on spectrogram and MFCC feature representations. A key focus is the comparison between pretrained and non-pretrained models, assessing their ability to generalize across diverse audio environments. Through extensive experimentation, ResNet50 and DenseNet trained on spectrograms emerged as the most effective architectures, significantly outperforming other models in classification accuracy. Additionally, the study investigates the impact of feature extraction techniques, dataset augmentation, and model fine-tuning, providing deeper insights into the role of representation learning in audio classification. The findings contribute to the growing field of audio-based deep learning applications, offering a detailed comparative study of model architectures, feature representations, and training strategies for infant cry detection. Full article

This article addresses the technical, aesthetic, and strategic problem of the limited attention paid to design and selection of materials in photovoltaic system (PSS) support structures despite their direct impact on the efficiency, durability and economic viability of these systems. As the costs of modules and electronic components continues to decrease, the structural elements acquire greater weight in the total cost and long-term performance. Our research comprehensively analyzes the mechanical, environmental, and regulatory factors influencing material selection and structural design in PV mounting systems. The PRISMA methodology was used to perform a systematic review of 122 articles published between 2018 and 2025, which were classified along two axes: materials (mild steel, galvanized steel, aluminum, polymers, and composites) and structural design (angle, orientation, loads, support typology, and adaptation to the environment). The results show that an adequate match between design and climatic conditions improves system stability, efficiency, and service life. With the support of digital modeling and advanced simulations, we identify trends towards modular, lightweight, and adaptive solutions, particularly in architectural applications (BIPV). This work provides a robust and contextualized technical framework that facilitates informed decision-making in solar energy projects, with direct implications for the sustainability, structural resilience, and competitiveness of the PSS sector in different geographical regions. Full article

Animal keypoint detection holds significant applications in fields such as biological behavior research and animal health monitoring. Although related research has reached a relatively mature stage of human keypoint detection, it still faces numerous challenges in the realm of animal keypoint detection. Firstly, there is a scarcity of keypoint detection datasets related to animals in public datasets. Secondly, existing solutions have adopted large-scale deep learning models to achieve higher accuracy, but these models are costly and difficult to widely promote within the industry. On the other hand, small-scale, low-cost detection models that are used to reduce costs suffer from insufficient accuracy and cannot meet the needs of industrial production. Therefore, designing and implementing a lightweight and high-accuracy animal keypoint detection model to meet industry needs has significant theoretical and practical importance. Addressing the aforementioned issues, this thesis proposes a lightweight animal keypoint detection method, HRDS, which maintains high accuracy while significantly reducing model complexity. Firstly, by removing the fourth stage from the HRNet architecture, the number of parameters and the computational complexity of the model are successfully reduced. Secondly, to enhance the model’s performance and robustness, a new attention mechanism module, DS, is designed. This module effectively counterbalances the loss of accuracy due to the significant reduction in the parameter count and helps to strengthen the model’s keypoint detection capability in complex scenarios. Experiments were performed on the AP-10K dataset, and the results indicated that the HRDS method achieves an accuracy rate of 70.34%, with a 73.05% reduction in the number of parameters compared to HRNet and only a 2.64% decrease in accuracy, maintaining high precision. The inference time of HRDS reaches 26.58 ms, with an inference speed of 37.62 FPS, and its inference time is only 87.3% of that of HRNet. This provides a new solution for applications in resource-constrained environments. Full article

Nanogenerators have garnered significant scholarly interest as a groundbreaking approach to energy harvesting, encompassing applications in self-sustaining electronics, biomedical devices, and environmental monitoring. The rise of additive manufacturing has fundamentally transformed the production processes of nanocomposites, allowing for the detailed design and refinement of materials aimed at optimizing energy generation. This review presents a comprehensive analysis of 3D-printed nanocomposites in the context of nanogenerator applications. By employing layer-by-layer deposition, multi-material integration, and custom microstructural architectures, 3D-printed nanocomposites exhibit improved mechanical properties, superior energy conversion efficiency, and increased structural complexity when compared to their conventionally manufactured counterparts. Polymers, particularly those with inherent dielectric, piezoelectric, or triboelectric characteristics, serve as critical functional matrices in these composites, offering mechanical flexibility, processability, and compatibility with diverse nanoparticles. In particular, the careful regulation of the nanoparticle distribution in 3D printing significantly enhances piezoelectric and triboelectric functionalities, resulting in a higher energy output and greater consistency. Recent investigations into three-dimensional-printed nanogenerators reveal extraordinary outputs, encompassing peak voltages of as much as 120 V for BaTiO₃-PVDF composites, energy densities surpassing 3.5 mJ/cm², and effective d₃₃ values attaining 35 pC/N, thereby emphasizing the transformative influence of additive manufacturing on the performance of energy harvesting. Furthermore, the scalability and cost-effectiveness inherent in additive manufacturing provide substantial benefits by reducing material waste and streamlining multi-phase processing. Nonetheless, despite these advantages, challenges such as environmental resilience, long-term durability, and the fine-tuning of printing parameters remain critical hurdles for widespread adoption. This assessment highlights the transformative potential of 3D printing in advancing nanogenerator technology and offers valuable insights into future research directions for developing high-efficiency, sustainable, and scalable energy-harvesting systems. Full article

As global energy demand continues to rise, accurate load forecasting has become increasingly crucial for power system operations. This study proposes a novel Complete Ensemble Empirical Mode Decomposition with Adaptive Noise-Fast Fourier Transform-inverted Transformer-Long Short-Term Memory (CEEMDAN-FFT-iTransformer-LSTM) methodological framework to address the challenges of component complexity and transient fluctuations in power load sequences. The framework initiates with CEEMDAN-based signal decomposition, which dissects the original load sequence into multiple intrinsic mode functions (IMFs) characterized by different temporal scales and frequencies, enabling differentiated processing of heterogeneous signal components. A subsequent application of Fast Fourier Transform (FFT) extracts discriminative frequency-domain features, thereby enriching the feature space with spectral information. The architecture employs an iTransformer module with multi-head self-attention mechanisms to capture high-frequency patterns in the most volatile IMFs, while a gated recurrent unit (LSTM) specializes in modeling low-frequency components with longer temporal dependencies. Experimental results demonstrate the proposed framework achieves superior performance with an average 80% improvement in R-squared ($R^2$), 40.1% lower Mean Absolute Error (MAE), and 54.1% reduced Mean Squared Error (RMSE) compared to other models. This advancement provides a robust computational tool for power grid operators, enabling optimal resource dispatch through enhanced prediction accuracy to reduce operational costs. The demonstrated capability to resolve multi-scale temporal dynamics suggests potential extensions to other forecasting tasks in energy systems involving complex temporal patterns. Full article

The rapid growth of genomic sequence datasets in a FASTQ format calls for efficient storage and transmission solutions. Compression–decompression algorithms for streaming applications offer a promising potential to address these challenges. In this paper, we present a novel Pipelined Lossless Reference-free Compression (PLORC) architecture designed specifically for streaming genomic data in a FASTQ format. The proposed PLORC architecture consists of several submodules optimized for the structure of FASTQ files, maintaining the balance between the compression ratio (CR) and throughput rate (TPR). To verify the PLORC architecture in hardware, we implemented the PLORC compressor and decompressor in FPGA (field-programmable gate array). The experimental results across various open-source genomic datasets reveal that our PLORC compressor achieved about a 440 MB/s throughput rate, which was higher than the tested Gzip, LZ4, and Zstd compressors. In addition, the PLORC decompressor achieved a throughput rate matching that of the compressor. Additionally, the PLORC achieved competitive compression ratios with some well-known non-streaming compression algorithms. Full article

Ocean forecasting is critical for various applications and is essential for understanding air–sea interactions, which contribute to mitigating the impacts of extreme events. While data-driven forecasting models have demonstrated considerable potential and speed, they often primarily focus on spatial variations while neglecting temporal dynamics. This paper presents the TSformer, a novel non-autoregressive spatio-temporal transformer designed for medium-range ocean eddy-resolving forecasting, enabling forecasts of up to 30 days in advance. We introduce an innovative hierarchical U-Net encoder–decoder architecture based on 3D Swin Transformer blocks, which extends the scope of local attention computation from spatial to spatio-temporal contexts to reduce accumulation errors. The TSformer is trained on 28 years of homogeneous, high-dimensional 3D ocean reanalysis datasets, supplemented by three 2D remote sensing datasets for surface forcing. Based on the near-real-time operational forecast results from 2023, comparative performance assessments against in situ profiles and satellite observation data indicate that the TSformer exhibits forecast performance comparable to leading numerical ocean forecasting models while being orders of magnitude faster. Unlike autoregressive models, the TSformer maintains 3D consistency in physical motion, ensuring long-term coherence and stability. Furthermore, the TSformer model, which incorporates surface auxiliary observational data, effectively simulates the vertical cooling and mixing effects induced by Super Typhoon Saola. Full article

Environmental design provides crucial solutions for achieving sustainable development goals while offering new opportunities to improve human living conditions and enhance social welfare. This study employs bibliometric analysis using the R language to examine environmental design-related journal articles collected from the WoS database between 2000 and 2024, quantitatively analyzing the overall development of the environmental design research field over the past two decades. Currently, environmental design research is experiencing rapid development. Through cluster analysis, three major research hotspots in this field have been identified: green buildings and sustainable urbanization, ecological restoration and environmental governance, and the application of intelligent technology in environmental design. Through evolution analysis, the logical development of environmental design research has been determined, with technological innovation playing a pivotal role in the field’s advancement. Following this logic, we propose three frontiers with explosive development in the environmental design field: human-centered environmental design, intelligent technology application, and regional cultural adaptability. Environmental design represents a core research direction in architecture, urban planning, and environmental science disciplines, and serves as a crucial domain for emerging technologies to empower sustainable development. The research findings clearly present the current status, evolutionary logic, and research frontiers of this field, providing valuable references for its further development. Full article