Search Results (16)

The adoption of artificial intelligence (AI) in industrial manufacturing lags behind research progress, partly due to smaller, imbalanced datasets derived from real processes. In non-destructive aerospace testing, this challenge is amplified by the low defect rates of high-quality manufacturing. This study evaluates the use of synthetic data, generated via multiresolution stochastic texture synthesis, to mitigate class imbalance in material defect classification for the superalloy Inconel 718. Multiple datasets with increasing imbalance were sampled, and an image classification model was tested under three conditions: native data, data augmentation, and synthetic data inclusion. Additionally, round robin tests with experts assessed the realism and quality of synthetic samples. Results show that synthetic data significantly improved model performance on highly imbalanced datasets. Expert evaluations provided insights into identifiable artificial properties and class-specific accuracy. Finally, a quality assessment model was implemented to filter low-quality synthetic samples, further boosting classification performance to near the balanced reference level. These findings demonstrate that synthetic data generation, combined with quality control, is an effective strategy for addressing class imbalance in industrial AI applications. Full article

The generation of 360° video is gaining prominence in immersive media, virtual reality (VR), gaming projects, and the emerging metaverse. Traditional methods for panoramic content creation often rely on specialized hardware and dense video capture, which limits scalability and accessibility. Recent advances in generative artificial intelligence, particularly diffusion models and neural radiance fields (NeRFs), are examined in this research for their potential to generate immersive panoramic video content from minimal input, such as a sparse set of narrow-field-of-view (NFoV) images. To investigate this, a structured literature review of over 70 recent papers in panoramic image and video generation was conducted. We analyze key contributions from models such as 360DVD, Imagine360, and PanoDiff, focusing on their approaches to motion continuity, spatial realism, and conditional control. Our analysis highlights that achieving seamless motion continuity remains the primary challenge, as most current models struggle with temporal consistency when generating long sequences. Based on these findings, a research direction has been proposed that aims to generate 360° video from as few as 8–10 static NFoV inputs, drawing on techniques from image stitching, scene completion, and view bridging. This review also underscores the potential for creating scalable, data-efficient, and near-real-time panoramic video synthesis, while emphasizing the critical need to address temporal consistency for practical deployment. Full article

Generative image models have revolutionized artificial intelligence by enabling the synthesis of high-quality, realistic images. These models utilize deep learning techniques to learn complex data distributions and generate novel images that closely resemble the training dataset. Recent advancements, particularly in diffusion models, have led to remarkable improvements in image fidelity, diversity, and controllability. In this work, we investigate the application of a conditional latent diffusion model in the healthcare domain. Specifically, we trained a latent diffusion model using unlabeled histopathology images. Initially, these images were embedded into a lower-dimensional latent space using a Vector Quantized Generative Adversarial Network (VQ-GAN). Subsequently, a diffusion process was applied within this latent space, and clustering was performed on the resulting latent features. The clustering results were then used as a conditioning mechanism for the diffusion model, enabling conditional image generation. Finally, we determined the optimal number of clusters using cluster validation metrics and assessed the quality of the synthetic images through quantitative methods. To enhance the interpretability of the synthetic image generation process, expert input was incorporated into the cluster assignments. Full article

This study aims to propose a practical and realistic synthetic data generation method for object recognition in hazardous and data-scarce environments, such as construction sites. Artificial intelligence (AI) applications in such dynamic domains require domain-specific datasets, yet collecting real-world data can be challenging due to safety concerns, logistical constraints, and high labor costs. To address these limitations, we introduce object range expansion synthesis (ORES), a lightweight and non-generative method for generating synthetic image data by inserting real object masks into varied background scenes using open datasets. ORES synthesizes new scenes, while preserving scale and ground alignment, enabling controllable and realistic data augmentation. A dataset of 30,000 synthetic images was created using the proposed method and used to train an object recognition model. When tested on real-world construction site images, the model achieved a mean average precision at IoU 0.50 (mAP50) of 98.74% and a recall of 54.55%. While recall indicates room for improvement, the high precision highlights the practical value of synthetic data in enhancing model performance without requiring extensive field data collection. This research contributes a scalable approach to data generation in safety-critical and data-deficient environments, reducing dependence on direct data acquisition, while maintaining model efficacy. It provides a foundation for accelerating the deployment of AI technologies in high-risk industries by overcoming data bottlenecks and supporting real-world applications through practical synthetic augmentation. Full article

The analysis of human gait is a cornerstone in diagnosing and monitoring a variety of neuromuscular and orthopedic conditions. Recent technological advancements have paved the way for innovative methodologies that combine multimodal neuroimaging and eXtended Reality (XR) technologies to enhance the precision and applicability of gait analysis. This review explores the state-of-the-art solutions of an advanced gait analysis approach, a multidisciplinary concept that integrates neuroimaging, extended reality technologies, and sensor-based methods to study human locomotion. Several wearable neuroimaging modalities such as functional near-infrared spectroscopy (fNIRS) and electroencephalography (EEG), commonly used to monitor and analyze brain activity during walking and to explore the neural mechanisms underlying motor control, balance, and gait adaptation, were considered. XR technologies, including virtual, augmented, and mixed reality, enable the creation of immersive environments for gait analysis, real-time simulation, and movement visualization, facilitating a comprehensive assessment of locomotion and its neural and biomechanical dynamics. This advanced gait analysis approach enhances the understanding of gait by examining both cerebral and biomechanical aspects, offering insights into brain–musculoskeletal coordination. We highlight its potential to provide real-time, high-resolution data and immersive visualization, facilitating improved clinical decision-making and rehabilitation strategies. Additionally, we address the challenges of integrating these technologies, such as data fusion, computational demands, and scalability. The review concludes by proposing future research directions that leverage artificial intelligence to further optimize multimodal imaging and XR applications in gait analysis, ultimately driving their translation from laboratory settings to clinical practice. This synthesis underscores the transformative potential of these approaches for personalized medicine and patient outcomes. Full article

The inducible enzyme cyclooxygenase-2 (COX-2) and the subsequent synthesis of eicosanoids initiated by this enzyme are important molecular players in bone healing. In this pilot study, the suitability of a novel selective COX-2 inhibitor bearing a nitric oxide (NO)-releasing moiety was investigated as a modulator of healing a critical-size bone defect in rats. A 5 mm femoral defect was randomly filled with no material (negative control, NC), a mixture of collagen and autologous bone fragments (positive control, PC), or polycaprolactone-co-lactide (PCL)-scaffolds coated with two types of artificial extracellular matrix (aECM; collagen/chondroitin sulfate (Col/CS) or collagen/polysulfated hyaluronic acid (Col/sHA3)). Bone healing was monitored by a dual-tracer ([¹⁸F]FDG/[¹⁸F]fluoride) approach using PET/CT imaging in vivo. In addition, ex vivo µCT imaging as well as histological and immunohistochemical studies were performed 16 weeks post-surgery. A significant higher uptake of [¹⁸F]FDG, a surrogate marker for inflammatory infiltrate, but not of [¹⁸F]fluoride, representing bone mineralization, was observed in the implanted PCL-scaffolds coated with either Col/CS or Col/sHA3. Molecular targeting of COX-2 with NO-coxib had no significant effect on tracer uptake in any of the groups. Histological and immunohistochemical staining showed no evidence of a positive or negative influence of NO-coxib treatment on bone healing. Full article

Diffusion models, as representative models in the field of artificial intelligence, have made significant progress in text-to-image synthesis. However, studies of style transfer using diffusion models typically require a large amount of text to describe semantic content or specific painting attributes, and the style and layout of semantic content in synthesized images are frequently uncertain. To accomplish high-quality fixed content style transfer, this paper adopts text-free guidance and proposes a multi-source, training-free and controllable style transfer method by using single image or video as content input and single or multiple style images as style guidance. To be specific, the proposed method firstly fuses the inversion noise of a content image with that of a single or multiple style images as the initial noise of stylized image sampling process. Then, the proposed method extracts the self-attention mechanism’s query, key, and value vectors from the DDIM inversion process of content and style images and injects them into the stylized image sampling process to improve the color, texture and semantics of stylized images. By setting the hyperparameters involved in the proposed method, the style transfer effect of symmetric style proportion and asymmetric style distribution can be achieved. By comparing with state-of-the-art baselines, the proposed method demonstrates high fidelity and excellent stylized performance, and can be applied to numerous image or video style transfer tasks. Full article

Biosensing technology, which aims to measure and control the signals of biological substances, has recently been developed rapidly due to increasing concerns about health and the environment. Top–down technologies have been used mainly with a focus on reducing the size of biomaterials to the nano-level. However, bottom–up technologies such as self-assembly can provide more opportunities to molecular-level arrangements such as directionality and the shape of biomaterials. In particular, block copolymers (BCPs) and their self-assembly have been significantly explored as an effective means of bottom–up technologies to achieve recent advances in molecular-level fine control and imaging technology. BCPs have been widely used in various biosensing research fields because they can artificially control highly complex nano-scale structures in a directionally controlled manner, and future application research based on interactions with biomolecules according to the development and synthesis of new BCP structures is greatly anticipated. Here, we comprehensively discuss the basic principles of BCPs technology, the current status of their applications in biosensing technology, and their limitations and future prospects. Rather than discussing a specific field in depth, this study comprehensively covers the overall content of BCPs as a biosensing platform, and through this, we hope to increase researchers’ understanding of adjacent research fields and provide research inspiration, thereby bringing about great advances in the relevant research fields. Full article

The growing threat of antimicrobial-resistant (AMR) pathogens to human health worldwide emphasizes the need for more effective infection control strategies. Bacterial and fungal biofilms pose a major challenge in treating AMR pathogen infections. Biofilms are formed by pathogenic microbes encased in extracellular polymeric substances to confer protection from antimicrobials and the host immune system. Biofilms also promote the growth of antibiotic-resistant mutants and latent persister cells and thus complicate therapeutic approaches. Biofilms are ubiquitous and cause serious health risks due to their ability to colonize various surfaces, including human tissues, medical devices, and food-processing equipment. Detection and characterization of biofilms are crucial for prompt intervention and infection control. To this end, traditional approaches are often effective, yet they fail to identify the microbial species inside biofilms. Recent advances in artificial intelligence (AI) have provided new avenues to improve biofilm identification. Machine-learning algorithms and image-processing techniques have shown promise for the accurate and efficient detection of biofilm-forming microorganisms on biotic and abiotic surfaces. These advancements have the potential to transform biofilm research and clinical practice by allowing faster diagnosis and more tailored therapy. This comprehensive review focuses on the application of AI techniques for the identification of biofilm-forming pathogens in various industries, including healthcare, food safety, and agriculture. The review discusses the existing approaches, challenges, and potential applications of AI in biofilm research, with a particular focus on the role of AI in improving diagnostic capacities and guiding preventative actions. The synthesis of the current knowledge and future directions, as described in this review, will guide future research and development efforts in combating biofilm-associated infections. Full article

This study explored how the Lombard effect, a natural or artificial increase in speech loudness in noisy environments, can improve speech-in-noise communication. This study consisted of several experiments that measured the impact of different types of noise on synthesizing the Lombard effect. The main steps were as follows: first, a dataset of speech samples with and without the Lombard effect was collected in a controlled setting; then, the frequency changes in the speech signals were detected using the McAulay and Quartieri algorithm based on a 2D speech representation; next, an average formant track error was computed as a metric to evaluate the quality of the speech signals in noise. Three image assessment methods, namely the SSIM (Structural SIMilarity) index, RMSE (Root Mean Square Error), and dHash (Difference Hash) were used for this purpose. Furthermore, this study analyzed various spectral features of the speech signals in relation to the Lombard effect and the noise types. Finally, this study proposed a method for automatic noise profiling and applied pitch modifications to neutral speech signals according to the profile and the frequency change patterns. This study used an overlap-add synthesis in the STRAIGHT vocoder to generate the synthesized speech. Full article

Algorithms and computing power have consistently been the two driving forces behind the development of artificial intelligence. The computational power of a platform has a significant impact on the implementation cost, performance, power consumption, and flexibility of an algorithm. Currently, AI algorithmic models are mainly trained using high-performance GPU platforms, and their inferencing can be implemented using GPU, CPU, and FPGA. On the one hand, due to its high-power consumption and extreme cost, GPU is not suitable for power and cost-sensitive application scenarios. On the other hand, because the training and inference of the neural network use different computing power platforms, the data of the neural network model needs to be transmitted on platforms with varying computing power, which affects the data processing capability of the network and affects the real-time performance and flexibility of the neural network. This paper focuses on the high computing power implementation method of the integration of convolutional neural network (CNN) training and inference in artificial intelligence and proposes to implement the process of CNN training and inference by using high-performance heterogeneous architecture (HA) devices with field programmable gate array (FPGA) as the core. Numerous repeated multiplication and accumulation operations in the process of CNN training and inference have been implemented by programmable logic (PL), which significantly improves the speed of CNN training and inference and reduces the overall power consumption, thus providing a modern implementation method for neural networks in an application field that is sensitive to power, cost, and footprint. First, based on the data stream containing the training and inference process of the CNN, this study investigates methods to merge the training and inference data streams. Secondly, high-level language was used to describe the merged data stream structure, and a high-level description was converted to a hardware register transfer level (RTL) description by the high-level synthesis tool (HLS), and the intellectual property (IP) core was generated. The PS was used for overall control, data preprocessing, and result analysis, and it was then connected to the IP core via an on-chip AXI bus interface in the HA device. Finally, the integrated implementation method was tested and validated with the Xilinx HA device, and the MNIST handwritten digit validation set was used in the tests. According to the test results, compared with using a GPU, the model trained in the HA device PL achieves the same convergence rate with only 78.04 percent training time. With a processing time of only 3.31 ms and 0.65 ms for a single frame image, an average recognition accuracy of 95.697%, and an overall power consumption of only 3.22 W @ 100 MHz, the two convolutional neural networks mentioned in this paper are suitable for deployment in lightweight domains with limited power consumption. Full article

We propose a new generative model named adaptive cycle-consistent generative adversarial network, or Ad CycleGAN to perform image translation between normal and COVID-19 positive chest X-ray images. An independent pre-trained criterion is added to the conventional Cycle GAN architecture to exert adaptive control on image translation. The performance of Ad CycleGAN is compared with the Cycle GAN without the external criterion. The quality of the synthetic images is evaluated by quantitative metrics including Mean Squared Error (MSE), Root Mean Squared Error (RMSE), Peak Signal-to-Noise Ratio (PSNR), Universal Image Quality Index (UIQI), visual information fidelity (VIF), Frechet Inception Distance (FID), and translation accuracy. The experimental results indicate that the synthetic images generated either by the Cycle GAN or by the Ad CycleGAN have lower MSE and RMSE, and higher scores in PSNR, UIQI, and VIF in homogenous image translation (i.e., Y → Y) compared to the heterogenous image translation process (i.e., X → Y). The synthetic images by Ad CycleGAN through the heterogeneous image translation have significantly higher FID score compared to Cycle GAN (p < 0.01). The image translation accuracy of Ad CycleGAN is higher than that of Cycle GAN when normal images are converted to COVID-19 positive images (p < 0.01). Therefore, we conclude that the Ad CycleGAN with the independent criterion can improve the accuracy of GAN image translation. The new architecture has more control on image synthesis and can help address the common class imbalance issue in machine learning methods and artificial intelligence applications with medical images. Full article

Due to the high flexibility and conformity to people’s usage habits, text description has been widely used in image synthesis research recently and has achieved many encouraging results. However, the text can only determine the basic content of the generated image and cannot determine the specific shape of the synthesized object, which leads to poor practicability. More importantly, the current text-to-image synthesis research cannot use new text descriptions to further modify the synthesis result. To solve these problems, this paper proposes a text-guided customizable image synthesis and manipulation method. The proposed method synthesizes the corresponding image based on the text and contour information at first. It then modifies the synthesized content based on the new text to obtain a satisfactory result. The text and contour information in the proposed method determine the specific content and object shape of the desired composite image, respectively. Aside from that, the input text, contour, and subsequent new text for content modification can be manually input, which significantly improves the artificial controllability in the image synthesis process, making the entire method superior to other methods in flexibility and practicability. Experimental results on the Caltech-UCSD Birds-200-2011 (CUB) and Microsoft Common Objects in Context (MS COCO) datasets demonstrate our proposed method’s feasibility and versatility. Full article

Over the past decade, cell therapy has found many applications in the treatment of different diseases. Some of the cells already used in clinical practice include stem cells and CAR-T cells. Compared with traditional drugs, living cells are much more complicated systems that must be strictly controlled to avoid undesirable migration, differentiation, or proliferation. One of the approaches used to prevent such side effects involves monitoring cell distribution in the human body by any noninvasive technique, such as magnetic resonance imaging (MRI). Long-term tracking of stem cells with artificial magnetic labels, such as magnetic nanoparticles, is quite problematic because such labels can affect the metabolic process and cell viability. Additionally, the concentration of exogenous labels will decrease during cell division, leading to a corresponding decrease in signal intensity. In the current work, we present a new type of genetically encoded label based on encapsulin from Myxococcus xanthus bacteria, stably expressed in human mesenchymal stem cells (MSCs) and coexpressed with ferroxidase as a cargo protein for nanoparticles’ synthesis inside encapsulin shells. mZip14 protein was expressed for the enhancement of iron transport into the cell. Together, these three proteins led to the synthesis of iron-containing nanoparticles in mesenchymal stem cells—without affecting cell viability—and increased contrast properties of MSCs in MRI. Full article

Jaw reconstruction using an additive-manufacturing titanium artificial bone (AMTAB) has recently attracted considerable attention. The synthesis of a titanium artificial bone is based on three-dimensional computed tomography images acquired before surgery. A histological evaluation of porous AMTAB (pAMTAB) embedded in rat calvarial bone defects was conducted. This study examined three groups: rats implanted with mixed-acid and heat-treated pAMTAB, rats implanted with untreated pAMTAB, and rats with no implant. In both pAMTAB groups, bone defects were created in rat calvarial bones using a 5-mm trephine bar, followed by pAMTAB implantation. The pAMTAB was fixed to the defect using the fitting force of the surrounding bones. The rats were sacrificed at 4, 8, and 16 weeks after implantation, and the skull was dissected. Undecalcified ground slides were prepared and stained with Villanueva Goldner. Compared with the no implant control group, both pAMTAB groups exhibited new bone formation inside the defect, with greater bone formation in the mixed-acid and heat-treated pAMTAB group than in the untreated pAMTAB group, but the difference was not significant. These data suggest that pAMTAB induces bone formation after implantation in bone defects. Bone formation appears to be enhanced by prior mixed-acid and heat-treated pAMTAB. Full article