Accurate assessment of the breast cancer deterioration degree plays a crucial role in making medical plan, and the important basis for degree assessment is the number of mitoses in a given area of the pathological image. We utilized deep multi-scale fused fully convolutional neural network (MFF-CNN) combing with conditional random felid (CRF) to detect mitoses in hematoxylin and eosin stained histology image. Analyze the characteristics of mitotic detection ----scale invariance and sparsity, as well as the difficulties ---- small amount of data , inconsistent image staining and sample class unbalanced. Based on this, mitotic detection model is designed. In this paper, a tissue-based staining equalization method is used, and to establish an effective training sample set, we select training samples by using CNN. A mitotic detection model fusing multi-level and multi-scale features and context information was designed, and the corresponding training strategy was made to reduce over-fitting. As preliminarily validated on the public 2014 ICPR MITOSIS data, our method achieves a better performance in term of detection accuracy than ever recorded for this dataset.

Fabrication of a true-3D inorganic ceramic with resolution down to nanoscale using sol-gel resist precursor is demonstrated. The method has an unrestricted free-form capability, control of the fill-factor, and high fabrication throughput. A systematic study of the proposed approach based on ultrafast laser 3D lithography of organic-inorganic hybrid sol-gel resin followed by a heat treatment enabled formation of inorganic amorphous and crystalline composites guided by the composition of the initial resin. The achieved resolution of 100 nm was obtained for 3D patterns of complex free-form architectures. Fabrication throughput of 50×10³ voxels/s is achieved; voxel - a single volume element was recorded by a single pulse exposure. After a subsequent thermal treatment, ceramic phase was formed depending on the temperature and duration of the heat treatment as validated by Raman micro-spectroscopy. The X-ray diffraction (XRD) revealed a gradual emergence of the crystalline phases at higher temperatures with a signature of cristobalite SiO₂, a high-temperature polymorph. Also, the tetragonal ZrO₂ phase known for its high fracture strength was observed. This 3D nano-sintering technique is scalable from nano- to millimeter dimensions and opens a conceptually novel route for optical 3D nano-printing of various crystalline inorganic materials defined by an initial composition for diverse applications for microdevices in harsh physical and chemical environments and high temperatures.

3D cell cultures have improved the evaluation of drugs for cancer therapy, due to their high similarity to solid tumors. In melanoma, autophagy appears to show a dual role depending on the progression of the disease. p62 protein has been proposed for the evaluation of autophagic flux since its expression is an indicator of the state of autophagy. Pentoxifylline (PTX) and Norcantharidin (NCTD) are drugs that have been shown to have anticancer effects in various types of cancer. In this work, B16F1 mouse melanoma cell line was used, from which two-dimensional (2D) monolayer cultures and three-dimensional (3D) organoids were carried out using the hanging drop technique. The expression of p62 was determined by western blot and immunofluorescences. Our results indicate that pentoxifylline reduces p62 expression in both types of culture. While Norcantharidin increases its expression in 3D cultures at 24 h. Therefore, these drugs could have a potential therapeutic use for the regulation of autophagy in melanoma, depending on the state of evolution of the disease.

Additive manufacturing, commonly referred to as 3D printing, is an exciting and versatile manufacturing technology that is gaining traction and interest in both academic and industrial settings. Polymeric materials are essential components in a majority of the “inks” used across the various 3D printing technologies. As the environmental ramifications of sole or primary reliance on petrochemicals as a resource for industrial polymers continue to manifest themselves at a global scale, a transition to more sustainable bioderived alternatives could offer solutions. In particular, cellulose is promising due to its global abundance, biodegradability, excellent thermal and mechanical properties, and ability to be chemically modified to suit various applications. Thus far, cellulose has typically been incorporated in additive manufacturing applications as a substrate, filler, or reinforcement for other materials. However, due to its versatility and desirable properties, the exploration of all-cellulose 3D printing materials and associated methodologies is increasing. This review will discuss the progress and status of all-cellulose 3D printing approaches, associated challenges, and their potential as a key player in a more sustainable industrial future.

This research presents the creation of a Virtual Reality experience for the Balzi Rossi museum, commemorating the centenary of Prince Albert I Grimaldi's archaeological work at the site. The project, a collaboration between the University of Genoa's 3D Lab Factory, Eurodrone, and the Balzi Rossi archaeological museum, aims to preserve and convey the site's heritage through advanced VR technology. Initially employing Unreal Engine 4, the team used photogrammetry for 3D reconstruction of the "Caviglione" and "Florestano" caves, notable for their ancient rock engravings. This first VR model, despite hardware limitations, provided an interactive exploration of the site. The subsequent development phase utilized Unreal Engine 5, incorporating Nanite technology for enhanced visual fidelity. This advancement resulted in a more detailed and immersive VR experience, presenting the Balzi Rossi cliff across different historical periods, including the Würm glaciation. Key to this phase was optimizing the VR experience for performance, focusing on stable frame rates and minimizing motion sickness, and integrating a multi-lingual interface for broader accessibility. Since November 2023, the VR setup at the Balzi Rossi Museum has been an educational and interactive feature, enabling visitors to explore the site's history virtually. This research demonstrates the potential of VR in cultural heritage preservation and education, providing a foundation for future technological improvements in the field.

When a limb suffers a fracture, rupture, or dislocation, it is traditionally immobilized with plaster. This may induce discomfort in the patient, excessive itching and sweating, which creates the growth of bacteria, leading to an unhygienic and difficulty to keep clean from treatment. Furthermore, if the plaster remains for a long period, it may cause lesions in the joints and ligaments. To overcome all these disadvantages, orthoses have emerged as important medical devices to help patients in rehabilitation, as well as for self-care of deficiencies in clinics and daily life. Traditionally, these devices are produced manually, which becomes time-consuming and error prone. From another point-of-view, it is possible to use imageology (X-ray or computed tomography) to scan the human body; a process that may help orthoses manufacturing but induces radiation to the patient. To overcome this great disadvantage, several types of 3D scanners, without any kind of radiation have emerged. This article describes the use of various types of scanners capable of digitizing the human body, to produce custom orthoses. Studies have shown that photogrammetry is the most used and most suitable 3D scanner for the acquisition of the human body in 3D. With this evolution of technology, it is possible to decrease the scanning time and it will be possible to introduce this technology in clinical environment.

Geotechnical investigation is an important site characterization process in engineering construction. Excavation pits and boreholes are popular geotechnical investigation methods for accessing subsurface soil and rock characteristics. Although they are accurate, they are limited to the discrete locations where tests are carried out. The demand for 3D representation has been increasing as an alternative for improved visualization of geotechnical investigations. This study developed a procedure for 3D modelling of geotechnical investigations using open-source software. It improves 3D visualization of geotechnical investigations and characterization of accuracy and uncertainty assessment. Presently, most geotechnical investigations do not regularly report uncertainty assessment despite its importance in risk analysis of the investigations. The procedure developed in this study was tested in a proposed site for construction of an Inland Container Depot where it depicted geotechnical soil properties with more than 80% accuracy on holdout samples. It was able to model both horizontal and vertical variations of the soil properties with quantification of uncertainty. More testing and wide applications are recommended.

Melanoma is a highly aggressive type of skin cancer produced by malignant transformation of melanocytes and it is usually associated with a poor prognosis. Clinically, melanoma has several stages associated with migration and invasion of the cells through the skin layers, rapid cell spreading and formation of tumors in multiple organs. The main problem is the emergence of resistance of melanoma to the applied methods of treatment, thus it is of primary importance to find more crucial signaling pathways that control the progression of this type of cancer and could be targeted to prevent melanoma spreading. The main life-threatening stage of melanoma is metastasis formation, and 3D cell spheroids are better suited for the study of this process. Using a combinative approach (RT-PCR, immunofluorescence, patch-clamp and calcium imaging) we showed the functional expression of mechanosensitive Piezo1 channels in SK-MEL-2 aggressive melanoma cell line. We found that chemical activation of Piezo1 by its selective agonist Yoda1 completely prevents melanoma spheroid formation, and could be considered as a novel approach for the prevention of melanoma development.

Free-edge effect is one of the factors affecting the mechanical properties of three-dimensional woven composites under tensile load. However, current research is relatively poorly understood regarding the effect of free-edge on the stiffness and strength of the material. This paper aims at examining the influence of free-edge effect on the mechanical properties of 3D woven composites under tension through experimental and simulation mathods. The three-dimensional DIC technique is used to collect the full-field strains on the specimen surface during the test, and the stress-strain differences in different regions in the width direction are analyzed, and the overlap of the curves in each region is found to be high. Experimental studies are conducted on specimens of different widths (within the range of 15-20 mm), and the results indicate that the differences in mechanical properties of 3D woven composites under tension loading in this width range are not significant. A progressive damage finite element model is developed for calculation and compared with experimental results.

The increased accessibility of drone technology and the wide use of Structure from Motion 3D scene reconstruction have transformed the approach for mapping inaccessible slopes undergoing active rockfalls. The Poggio Baldi landslide offers the possibility for many of these techniques to be deployed and integrated with the aim of defining a suitable workflow for the analysis of hazards in mountainous regions. The generation of multitemporal digital slope twins (2016 – 2019), informed a rockfall trajectory analysis that was carried out with a physical-based GIS model. We tested the rockfall scenario reconstructed and calibrated on the analysis of the rock mass characteristics and the geometrical and physical constraints given by the multi-temporal analysis of the SfM point clouds. This time-independent rockfall hazard analysis is a critical component to any subsequent holistic risk analysis on this case study, and any potential similar mountainous setting.

Beyond semantic segmentation,3D instance segmentation(a process to delineate objects of interest and also classifying the objects into a set of categories) is gaining more and more interest among researchers since numerous computer vision applications need accurate segmentation processes(autonomous driving, indoor navigation, and even virtual or augmented reality systems…) This paper gives an overview and a technical comparison of the existing deep learning architectures in handling unstructured Euclidean data for the rapidly developing 3D instance segmentation. First, the authors divide the 3D point clouds based instance segmentation techniques into two major categories which are proposal based methods and proposal free methods. Then, they also introduce and compare the most used datasets with regard to 3D instance segmentation. Furthermore, they compare and analyze these techniques performance (speed, accuracy, response to noise…). Finally, this paper provides a review of the possible future directions of deep learning for 3D sensor-based information and provides insight into the most promising areas for prospective research.

Polystyrene as a thin film on arbitrary substrates or pellets form defective graphene films or powders that can be dispersed in water and organic solvents. The materials were characterized by visible absorption, Raman and X-ray photoelectron spectroscopy, electron and atomic force microscopy and electrochemistry. Raman spectra of these materials show the presence of the expected 2D, G and D peaks at 2750, 1590 and 1350 cm^-1, respectively. The relative intensity of the G vs. the D peak is taken as a quantitative indicator of the density of defects in the G layer.

Osteoarthritis (OA) is a joint disease involving cartilage degeneration. This study aimed to compare properties of chondrocytes from less-affected (LA-Cartilage) and severely-affected (SA-Cartilage) of human OA articular cartilage. Based on Dougados classification, OA cartilage was classified into two groups; less-affected (Grade 0–1) and severely-affected (Grade 2–3). Chondrocytes from each group were cultured until passage (P) 4. Growth, migration, stem cell properties and chondrogenic properties under normal and inflammatory conditions, and the formation of in vitro 3D cartilage tissues were compared between groups. The growth and migratory properties of LA-chondrocytes and SA-chondrocytes were similar, except that the migration rate of SA-chondrocytes was significantly higher at P0 compared to LA-chondrocytes. Both LA-chondrocytes and SA-chondrocytes expressed mesenchymal stem cell markers and tri-lineage differentiation, but the expression of stem cell markers decreased significantly with increasing passage number. Exposure to inflammatory conditions induced distinct morphological changes and significant increases in expression of SOX9 at P4 and MMP3 at P1 for LA-chondrocytes. LA-chondrocytes and SA-chondrocytes able to develop into in vitro 3D constructs, but SA-chondrocytes exhibited superior cartilage-like properties. Chondrocytes from both less- and severely-affected regions are suitable to be used in clinical applications, however, chondrocytes from severely-affected regions could be a more favorable cell source.

Numerical weather prediction is an initial-value problem, for determination of the initial conditions, there are many methods and one of the most classical methods is variational methods in three dimensions, or 3D-Var. In this approach, with a defined cost function proportional to the square of the distance between the analysis and both the background and the observations, one can obtain the analysis. In the cost function, the background and the observations are reshaped to vectors; within this step, the order of the background error covariance matrix and the observational error covariance matrix becomes huge, which is not convenient to one to obtain the analysis. In this paper, according to the matrix analysis approach, we put forward some possible improvements to the dimension-reduction algorithm of 3D-Var, so that provide some references for data assimilation.

Background: Wilms tumor (WT) is the main renal tumor in children. SIOP-UMBRELLA Guidelines admit Nephron sparing surgery (NSS) in syndromic patients, and in small (<300 ml) nonsyndromic unilateral WTs, without lymph node involvement, and with a substantial expected remnant renal function, after neoadjuvant chemotherapy. We report our prechemotherapy transperitoneal robot-assisted partial nephrectomy (RAPN) in a unilateral non-syndromic Wilms tumor. Methods: A 6-year-old-child showed an exophytic 3.6 cm diameter solid rounding mass involving the upper right renal pole at an incidental abdominal echotomography. CT-scan and abdominal MRI proved no local infiltration neither lymph node involvement was appreciated, suggesting an exophytic mass easily resectable through a NSS robotic approach, with a low risk of rupture and no subverted renal anatomy. The preoperative imaging was not suggestive for WT. A virtual 3D reconstruction of the tumor was performed. Results: the oncologic board approved a robot-assisted partial nephrectomy with the intraperitoneal approach. The histopathologic analysis displayed a WT. The patient underwent 10 vincristine-doses adjuvant chemotherapy. 28-months follow-up showed no tumor recurrence. Conclusions: Intraperitoneal RAPN can represent an opportunity for WT and needs to be assessed as a challenging possibility. This case suggests a potential role of prechemotherapy RAPN in the near future for highly selected patients.

In this paper, we present the idea of Self Supervised learning on the Shape Completion and Classification of point clouds. Most 3D shape completion pipelines utilize autoencoders to extract features from point clouds used in downstream tasks such as Classification, Segmentation, Detection, and other related applications. Our idea is to add Contrastive Learning into Auto-Encoders to learn both global and local feature representations of point clouds. We use a combination of Triplet Loss and Chamfer distance to learn global and local feature representations. To evaluate the performance of embeddings for Classification, we utilize the PointNet classifier. We also extend the number of classes to evaluate our model from 4 to 10 to show the generalization ability of learned features. Based on our results, embedding generated from the Contrastive autoencoder enhances Shape Completion and Classification performance from 84.2% to 84.9% of point clouds achieving the state-of-the-art results with 10 classes.

The continuous advancements in healthcare technology have empowered the discovery, diagnosis, and prediction of diseases, revolutionizing the field. Artificial intelligence (AI) is expected to play a pivotal role in achieving the goals of precision medicine, particularly in disease prevention, detection, and personalized treatment. This study aims to determine the optimal combination of the mother wavelet and AI model for the analysis of pediatric electroretinogram (ERG) signals. The dataset, consisting of signals and corresponding diagnoses, undergoes Continuous Wavelet Transform (CWT) using commonly used wavelets to obtain a time-frequency representation. Wavelet images were used for the training of five widely used deep learning models: VGG-11, ResNet-50, DensNet-121, ResNext-50, and Vision Transformer, to evaluate their accuracy in classifying healthy and unhealthy patients. The findings demonstrate that the combination of Ricker Wavelet and Vision Transformer consistently yields the highest median accuracy values for ERG analysis, as evidenced by the upper and lower quartile values. The median balanced accuracy of the obtained combination of the three considered types of ERG signals in the article are 0.83, 0.85, and 0.88. However, other wavelet types also achieved high accuracy levels, indicating the importance of carefully selecting the mother wavelet for accurate classification. The study provides valuable insights into the effectiveness of different combinations of wavelets and models in classifying ERG wavelet scalograms.

The problem of health status prediction of insulated-gate bipolar transistors (IGBTs) gains a lot of attention in the field of health management of power electronic equipment. The performance degradation of IGBT gate oxide layer is one of the important failure modes. In view of failure mechanism analysis and easy implementation of monitoring circuit, this paper selects the gate leakage current of IGBT as the precursor parameter of gate oxide degradation, and uses time domain characteristic analysis, gray correlation degree, Mahalanobis distance, Kalman filter and other methods to carry out feature selection and fusion, and finally obtains a health indicator characterizing the degradation of IGBT gate oxide. Based on the Convolutional Neural Network and Long Short-Term Memory (CNN-LSTM) network, this paper constructs an IGBT gate oxide degradation prediction model, and performs experimental analysis on the dataset released by NASA-Ames Laboratory, and the average absolute error of performance degradation prediction is as low as 0.0216. Compared with Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), Support Vector Regression (SVR) and CNN-LSTM models, CNN-LSTM network has the highest prediction accuracy. These results show the feasibility of gate leakage current as a precursor parameter of IGBT gate oxide layer failure, as well as the accuracy and reliability of the CNN-LSTM prediction model.

In the last few decades, glaucoma became the second biggest leading cause of irreversible vision loss. Because of its asymptotic growth, it is not properly diagnosed until the relatively late stage. To stop the severe damage by glaucoma it is needed to detect glaucoma in its early stages. Surprisingly diabetes also be the greatest cause of glaucoma. In the modern era, artificial intelligence makes great progress in the medical image processing field. Image analysis based on machine learning gives a huge success in diagnosis glaucoma without any misdiagnosis. The aim of this proposed paper is to create an automated process that can detect glaucoma and diabetic retinopathy. Here various Machine Learning models are used and results of these methods are presented.

The diagnosis of a rolling bearing for monitoring its status is critical for maintaining industrial equipment using rolling bearings. The traditional method of diagnosing faults of the rolling bearing has low identification accuracy, which needs artificial feature extraction to enhance the accuracy. 1D-CNN method not only can diagnose bearing faults accurately but also overcome shortcomings of the traditional methods. Different from machine learning and other deep learning models, the 1D-CNN method does not need pre-processing one-dimensional data of rolling bearing’s vibration. Thus, it enhances the processing speed and improves the network structure to have a reasonable design for small sample data sets. This study proposes and tests a 1D-CNN method for diagnosing rolling bearings. By introducing the dropout operation, the method obtains high accuracy and improves the generalizing ability. The experimental results show 99.52% of the average accuracy under a single load and 98.26% under different loads.

Accurate and efficient traffic incident detection methods can effectively alleviate traffic congestion caused by traffic incidents, prevent secondary accidents and improve the safety of urban road traffic.Aiming at the problems that the traditional machine learning event detection method cannot fully extract the parameter characteristics of traffic flow and is not suitable formulti-dimensional and non-linear massive data, we propose a new traffic event detection method(CNN-XGBoost).This method combines the respective advantages of Convolution Neural Network(CNN) and Extreme Gradation Boosting (XGBoost). Firstly, we preprocessed the original freeway traffic incident detection data set by constructing initial variable set, data normalization, data balance processing and dimension reorganization. Secondly,we use CNN network to automatically extract the deep features of event detection data, and use XGBoost as a classifier to classify the extracted features for expressway traffic event detection.Finally, we use the data set of Hangzhou expressway microwave detector in China to carry out simulation experiments on CNN-XGBoost. The experimental results show that compared with XGBoost, CNN, Support Vector Machine (SVM) and Gradient Boosting Decision Tree (GBDT) and other methods, CNN-XGBoost method can effectively improve the accuracy of expressway traffic event detection and has better generalization ability.

Detection of the region of interest (ROI) is a critical step in laryngeal image analysis for the delineation of glottis contour. The process can improve both computational efficiency and accuracy of the image segmentation task, which will facilitate subsequent analysis and characterization of the vocal fold vibration as it correlates with voice quality and pathology. This study aims to develop machine learning based approaches for automatic detection of ROI for glottis image sequences captured by high-speed video-endoscopy (HSV), a clinical laryngeal imaging modality. In particular, we first applied the supporting vector machine (SVM) method using histogram of oriented gradients (HOG) feature descriptor, and second, trained a convolutional neural network (CNN) model for this task. Comparisons are made for both approaches in terms of accuracy of recognition and computation time.

To improve the tangerine crop yield, the work of recognizing and then disposing of specific pests is becoming increasingly important. The task of recognition is based on the features extracted from the images that have been collected from websites and outdoors. Traditional recognition and deep learning methods, such as KNN (k-nearest neighbors) and AlexNet, are not preferred by knowledgeable researchers, who have proven them inaccurate. In this paper, we exploit four kinds of structures of advanced deep learning to classify 10 citrus pests. The experimental results show that Inception-ResNet-V3 obtains the minimum classification error.

Preliminaries Convolutional Neural Network (CNN) applications have recently emerged in Structural Health Monitoring (SHM) systems focusing mostly on vibration analysis. However, the SHM literature shows clearly that there is a lack of application regarding the combination of PZT (Lead Zirconate Titanate) based method and CNN. Likewise, applications using CNN along with the Electromechanical Impedance (EMI) technique applied to SHM systems are rare. To encourage this combination, an innovative SHM solution through the combination of the EMI-PZT and CNN is presented here. To accomplish this, the EMI signature is split into several parts followed by computing the Euclidean distances among them to form a RGB (red, green and blue) frame. As a result, we introduce a dataset formed from the EMI-PZT signals of 720 frames, encompassing a total of 4 types of structural conditions for each PZT. In a case study, the CNN-based method was experimentally evaluated using three PZTs glued onto an aluminum plate. The results reveal an effective pattern classification; yielding a 100% hit rate which outperforms other SHM approaches. Furthermore, the method needs only a small dataset for training the CNN, providing several advantages for industrial applications.

Electric energy has become essential nowadays not only for the daily life of each of us but also for the economy of different countries. The dissemination of geographic information plays an important role in national development as it facilitates communication between managers, investors, and consumers in this sector. Since the management of electricity network data was previously done in Tunisia based on paper maps and plans, the purpose of this article is to present a case of planning based on GIS, Web, and 3D Web GIS, which would have significant positive consequences on this sector from a technical and financial sides with an improvement in customer satisfaction and the creation of an intelligent electricity network which will be a real decision-making tool. This work draws up an inventory of the network MV (Medium Voltage)/LV (Low Voltage) of the region of Medjez El Bab which routes electricity to the big centers of consumption with access to MV/LV subscribers. The analysis of the network's impedance allowed carrying out different scenarios to optimize performance and obtain more realistic routes. Many thematic maps were produced as part of this project (Slope map, Land use map, map of the MV voltage domains, map of the MV/LV transformer stations power, etc.). A three-dimensional virtual city has been developed to visualize the graphical and attribute data for the study area. A Web and 3D Web GIS applications that allows the publication of the interactive maps on the Web as well as the database information have been developed to offer users the possibility of consulting the produced products by internet. Finally, a website related to the study was developed.

A pilot study on laser 3D printing of inorganic free-form micro-optics is experimentally validated. Ultrafast laser nanolithography is employed for structuring hybrid organic-inorganic material SZ2080TM followed by high-temperature calcination post-processing. The combination allows production of 3D architectures and the heat-treatment results in converting the material to inorganic substance. The produced miniature optical elements are characterized and their optical performance demonstrated. Finally, the concept is validated for manufacturing compound optical components such as stacked lenses. This is opening for new directions and applications of laser made microoptics under harsh conditions such as high intensity radiation, temperature, acidic environment, pressure variations, which include open space, astrophotonics, and remote sensing.

The necessity for effective intrusion detection systems (IDS) in big data environments has grown critical due to the rising prevalence of big data systems and the rising amount of security threats. Applying conventional intrusion detection methods to the enormous and intricate data produced by big data ecosystems presents difficulties. Deep learning, has proven to be exceptionally adept at deciphering complex, large-scale data. This study proposes a Deep Learning-based Intrusion Detection System (IDS) created specifically for the Big Data environment. Traditional intrusion detection systems struggle to efficiently identify and prevent cyber threats due to the ever-increasing volume and complexity of data in current networks. We suggest an IDS that makes use of Deep Learning (CNN, LSTM, GAN, etc.), to address this problem. These cutting-edge neural network topologies give the system the ability to process and analyze massive amounts of data for precise intrusion detection. Data collection, data preprocessing, feature engineering, DL model training, intrusion detection, warning generation, and reaction are some of the crucial parts of the suggested IDS. The data collection module mines the Big Data environment for network traffic, system logs, and security event information. To make sure the data is suitable for analysis, it is preprocessed. To improve the detection abilities of the DL models, important features are extracted from the data using feature engineering approaches.

In recent years, Synthetic Aperture Radar (SAR) has received attention in the Automatic Target Recognition (ATR) field due to its ability to acquire images both day and night, combined with the superior resolution offered by the latest sensors. However, despite advances, there remains a deficiency in dataset quality and quantity. This has necessitated the use of simulated data to overcome challenges associated with obtaining large quantities of high-quality images of targets and their subsequent labeling. In this study, we trained a Convolutional Neural Network (CNN) using a simulated dataset, subsequently employing it to classify real images from the MSTAR dataset. Traditional training methodologies often struggle with generalization when confronted with domain disparities between simulated and real data. To mitigate this, we exploited Margin Disparity Discrepancy (MDD), a domain adaptation technique not previously explored in SAR context. Findings from this study showcased a 13% increase in classification accuracy and improved generalization using MDD. Through Explainable AI (XAI) techniques such as t-SNE and other metrics like Kullback Leibler Divergence (KLD), we revealed a more distinct alignment of feature spaces between the two domains after domain adaptation, emphasizing MDD’s role in enhancing model accuracy and generalization.

Abstract: The surge of diabetes poses a significant global health challenge, particularly in Oman and the Middle East. Early detection of diabetes is crucial for proactive intervention and improved patient outcomes. This research leverages the power of machine learning, specifically, Convolutional Neural Networks (CNNs), to develop an innovative 4D CNN model dedicated to early diabetes prediction. A region-specific dataset from Oman is utilized to enhance health outcomes for individuals at risk of developing diabetes. The proposed model showcases remarkable accuracy, achieving an average accuracy of 98.49% to 99.17% across various epochs. Additionally, it demonstrates excellent F1 score, recall, and sensitivity, highlighting its ability to identify true positive cases. The findings contribute to the ongoing effort to combat diabetes and pave the way for future research in using deep learning for early disease detection and proactive healthcare.

Automatic target detection of remote sensing images (RSI) plays an important role in military reconnaissance, disaster monitoring, and target rescue. The core task of remote sensing target detection is to judge the target categories and complete precise location. However, the existing target detection algorithms have limited accuracy and weak generalization capability for remote sensing images with complex backgrounds. To achieve accurate detection of different categories targets in remote sensing images, this study presents a novel feature enhancement single shot multibox detector (FESSD) algorithm for remote sensing target detection. The FESSD introduces feature enhancement module and attention mechanism into the convolution neural networks (CNN) model, which can effectively enhance the feature extraction ability and nonlinear relationship between different convolution features. Specifically, the feature enhancement module is used to extract the multi-scale feature information, and enhance the model nonlinear learning ability; the self-learning attention mechanism (SAM) is used to expand the convolution kernel local receptive field, which makes the model extract more valuable features. In addition, the nonlinear relationship between different convolution features is enhanced using the feature pyramid attention mechanism (PAM). The advantage of FESSD over other state-of-the-art target detection methods is validated by experiments on the presented seven-class target detection dataset (SD-RSI) and the public DIOR dataset.

Research has been growing on object detection using semi-supervised methods in past few years. We examine the intersection of these two areas for floor-plan objects to promote the research objective of detecting more accurate objects with less labelled data. The floor-plan objects include different furniture items with multiple types of the same class, and this high inter-class similarity impacts the performance of prior methods. In this paper, we present Mask R-CNN based semi-supervised approach that provides pixel-to-pixel alignment to generate individual annotation masks for each class to mine the inter-class similarity. The semi-supervised approach has a student-teacher network that pulls information from the teacher network and feeds it to the student network. The teacher network uses unlabeled data to form pseudo-boxes, and the student network uses both unlabeled data with the pseudo boxes and labelled data as ground truth for training. It learns representations of furniture items by combining labelled and unlabeled data. On the Mask R-CNN detector with ResNet-101 backbone network, the proposed approach achieves mAP of 98.8%, 99.7%, and 99.8% with only 1%, 5% and 10% labelled data, respectively. Our experiment affirms the efficiency of the proposed approach as it outperforms the fully supervised counterpart using only 10% of the labels.

High costs for the repair of concrete structures can be prevented if damage at an early stage of degradation is detected and precautionary maintenance measures are applied. To this end, we use numerical wave propagation simulations to identify simulated damage in concrete using convolutional neural networks (CNN). Damage in concrete subjected to compression is modeled at the mesoscale using the discrete element method. Ultrasonic wave propagation simulation on the damaged concrete specimens are performed using the rotated staggered finite-difference grid method. The simulated ultrasonic signals are used to train a CNN based classifier capable of classifying three different damage stages (microcrack initiation, microcrack growth and microcrack coalescence leading to macrocracks). The performance of the classifier is improved by refining the dataset via an analysis of the averaged envelope of the signal. The classifier using the refined dataset has an overall accuracy of 90%.

The automatic recognition of scanned Medieval manuscripts still represents a challenge due to degradation, non standard layouts, or notations. This paper focuses on the Medieval square notation developed around the 11th century which is composed of staff lines, clefs, accidentals, and neumes which are basically connected single notes. We present a novel approach to tackle the automatic transcription by applying CNN/LSTM networks that are trained using the segmentation-free CTC-loss-function which considerably facilitates the GT-production. For evaluation, we use three different manuscripts and achieve a dSAR of 86.0% on the most difficult book and 92.2% on the cleanest one. To further improve the results, we apply a neume dictionary during decoding which yields a relative improvement of about 5%.

The evaluation of nanostructured biomaterials and medicines is associated with 2D cultures that provide insight into the biological mechanisms at the molecular level, while critical aspects of the tumor microenvironment (TME) are provided by the study of animal xenograft models. More realistic models that can histologically reproduce human tumors are provided by tissue engineering methodologies of co-culturing cells of varied phenotypes, to provide 3D tumor spheroids that recapitulate the dynamic TME in 3D matrices. The novel approaches of 3D tumor models are combined with tumor tissue engineering (TTE) scaffolds including hydrogels, bioprinted materials, decellularized tissues, fibrous and nanostructured matrices. This review focuses on the use of nanostructured materials in cancer therapy and regeneration, and the development of realistic models for studying TME molecular and immune characteristics. Tissue regeneration is an important aspect of TTE scaffolds for restoring the normal function of the tissues, while providing cancer treatment. Thus, this article reports recent advancements on the development of 3D TTE models for antitumor drug screening, studying of tumor metastasis, and tissue regeneration. Also, this review identifies the great opportunities of 3D TTE scaffolds in the evaluation of the immunological mechanisms and processes involved in the application of immunotherapies.

A detailed review of the scientific literature was undertaken to examine the most recent developments in plasma processing in the field of medicine. The first part of the review includes a detailed breakdown of the different types of coatings that can be applied onto medical devices using plasma, with a specific focus on antimicrobial surfaces. The developments during 2023 in plasma deposited biocompatible, drug delivery and adhesive coatings are described and specific applications in additive manufacturing are highlighted. The use of plasma and plasma activated liquids as standalone therapeutics continues to evolve and pertinent advances in this field are described. In addition, the combination of plasma medicine with conventional pharmaceutical interventions was reviewed and key emerging trends were highlighted, including the use of plasma to enhance drug delivery directly into tissue. The potential synergies between plasma medicine and chemotherapeutics for oncology and infection treatment is a growing area and recent advancements are noted. Finally, the use of plasma to control excess antibiotics and to intentionally degrade such materials in waste streams is described.

Immediate load of full-arch rehabilitations over implants, specially over 4 implants are very well documented in the literature. More recently, the use of computed surgical guides to help the planning and the execution of these treatments, in many situations without the need of raising a flap, and diminishing the appearance of hematomas, bleeding and with less trauma to the patient has gained preference among implantologists. The objective of this case report is to show a clinical case of an immediate load full-arch fixed rehabilitation over 4 implants produced by 3D printing manufacturing technology, and placed with a computed surgical guide, in the same appointment, and the 24 months follow-up. The patient returned after 3 months to replace the immediate temporary fixed prosthesis for a new one, with metallic bar, better teeth and more delicate. Soft and hard tissue around the implants seemed to be stable, without signs of inflammation, either on the 3 or the 24 months follow-up. 3D printing of implants by direct metal laser sintering is a technology that seems to be promising for oral implantology, with solid studies showing reliable results, as seen in this single case. More clinical studies are necessary to testify its efficacy.

Characters are one of the most important elements in composing digital animation. The appear-ance and voice of a character should be designed to express the personality and values of the character. However, it is not easy for animation producers to harmoniously match the appear-ance and voice of a character. Advances in deep learning technology have made it possible to overcome this limitation. To achieve this, firstly, an audio-visual dataset of characters is required. In this study, we construct and verify a Korean audio-visual dataset consisting of frontal face im-ages of various characters and short voice clips. We developed an application that can automati-cally extract the frontal face image and a short voice clip of a character by collecting videos up-loaded to YouTube. Through this, a dataset consisting of a total of 1,522 face images and a total of 7,999 seconds of voice clips was built based on 490 characters. Furthermore, we automatically la-bel characters by gender and age to validate the dataset. The dataset built in this study is expected to be used in various deep learning fields, such as classification, generative adversarial networks, and speech synthesis.

The 3D reconstruction of vermiculite-based sealing material was carried out based on CT scanning experiments and Avizo software. The precision and representation of the reconstructed digital core were tested by calculating the pore structure parameters and comparing them with the experimental results of mercury compression. Avizo is a perfect interface with Fluent software to perform micro-scale seepage simulation to explore the distribution of pressure and velocity fields during fluid transport. In this paper, a new approach is proposed to study the penetration leakage of non-metallic gaskets by using equivalent pore networks.

The three-dimensional Ising model on the m$\times$n$\times$l cubic lattice with the screw boundary condition along the ${\bf X}$ direction and the periodic boundary conditions along both ${\bf Y}$ and ${\bf Z}$ directions is exactly solved by using the $2^{mn}$-dimensional representation of the rotation group in $2mn$-dimensions, similar to the Kaufman's spinor approach in two dimensions. The exact partition function is obtained from two sets of $2^{mn-1}$ eigenvalues of the $2^{mn}$-dimensional transfer matrix {\bf V} corresponding to the even and odd eigenvectors, respectively. Such the eigenvalues are determined by the angles of the 2mn-dimensional rotation associated with {\bf V}.

In this article, metallic additive manufacturing (AM) processes were classified and demonstrated. AM technology can be applied to a wide range of industrial areas because of its great feasibility in the design and manufacturing of various complex parts. The main factor that distinguishes various metallic AM processes from each other is the deposition method. Deposited metal can be imported in the form of melt or semi-solid. AM technology also covers a wide range of materials like aluminum, titanium, and many other alloys. Some of the common applications of metallic AM processes are the quick manufacturing of the parts which utilized in various industries like medical, automotive, aerospace, and jewelry industries. AM can help to fabricate parts that are impossible to be manufactured by other processes.

Existing methods for 3D human pose estimation mainly divide the task into two stages. The first stage identifies the 2D coordinates of the human joints in the input image, namely the 2D human joint coordinates. The second stage uses the results from the first stage as input to recover the depth information of human joints from the 2D human joint coordinates to achieve 3D human pose estimation. However, the recognition accuracy of the two-stage method relies heavily on the results of the first stage and includes too many redundant processing steps, which reduces the inference efficiency of the network. To address these issues, we propose the EDD, a fully End-to-end 3D human pose estimation method based on transformer architecture with Dual Decoders. By learning multiple human poses, the model can directly infer all 3D human poses in the image using a pose decoder, and then further optimize the recognition result using a joint decoder based on the kinematic relations between joints. With the attention mechanism, this method can adaptively focus on the most relevant features to the target joint, effectively overcoming the feature misalignment problem in the human pose estimation task and greatly improving the model performance. Any complex post-processing step, such as non-maximum suppression, is eliminated, further improving the efficiency of the model. The results show that the method achieves an accuracy of 87.4% on the MuPoTS-3D dataset, significantly improving the accuracy of end-to-end 3D human pose estimation methods.

The rapid development of electrochemical CO2 reduction offers a promising route to convert in-termittent renewable energy into products of high value-added fuels or chemical feedstocks. However, low faradaic efficiency, low current density, and a narrow potential range still limited the large-scale application of CO2RR electrocatalyst. Herein, monolith 3D bi-continuous nano-porous Bismuth (np-Bi) electrodes are fabricated via a simple one-step electrochemical dealloying strategy from Pb-Bi binary alloy. The unique bi-continuous porous structure ensures highly effective charge transfer, meanwhile the controllable millimeter-size geometric porous structure enables easy catalyst adjustment to expose highly suitable surface curvatures with abundant reactive sites. This results in a high selectivity of 92.6% and superior potential window (400 mV, selectivity >88%) for electrochemical reduction of carbon dioxide to formate. Our scalable strategy provides a feasible pathway for mass-producing high-performance and versatile CO2 electrocatalysts.

A key component of efforts to identify the biological and drug-specific aspects that contribute to therapeutic failure or unexpected exposure-associated toxicity is the study of drug-intestinal barrier interactions. While methods supporting such assessments are widely described for human therapeutics, there is relatively little information available for similar evaluation in support of veterinary pharmaceuticals. There is, therefore, a critical need to develop novel approaches for evaluating drug-gut interactions in veterinary medicine. Three-dimensional (3D) organoids can address these difficulties in a reasonably affordable system that circumvents the need for more invasive in vivo assays in live animals. However, a first step in the development of such systems is understanding organoid interactions in a 2D monolayer. Given the importance of orally administered medications for meeting the therapeutic need of companion animals, we demonstrate growth conditions under which canine colonoid-derived intestinal epithelial cells survive, mature, and differentiate into confluent cell systems with high monolayer integrity. We further examine the applicability of this canine colonoid-derived 2D model to assess the permeability of three structurally diverse, passively absorbed β-blockers (e.g., propranolol, metoprolol, and atenolol). Both absorptive and secretive apparent permeability (Papp) of these drugs at two different pH conditions were evaluated in canine colonoid-derived monolayers and were compared with that of Caco-2 cells. This proof-of-concept study provides promising preliminary results with regard to the utility of canine-derived organoid monolayers for species-specific assessments of therapeutic drug passive permeability.

Smart health applications have received significant attention in recent years. Novel applications hold significant promise to overcome many of the inconveniences faced by persons with disabilities throughout daily living. For people with blindness and low vision (BLV), environmental perception is compromised, creating myriad difficulties. Precise localization is still a gap in the field and is critical to safe navigation. Conventional GNSS positioning cannot provide satisfactory performance in urban canyons. 3D mapping-aided (3DMA) GNSS may serve as an urban GNSS solution, since the availability of 3D city models has widely increased. As a result, this study developed a real-time 3DMA GNSS-positioning system based on state-of-the-art 3DMA GNSS algorithms. Shadow matching was integrated with likelihood-based ranging 3DMA GNSS, generating positioning hypothesis candidates. To increase robustness, the 3DMA GNSS solution was then optimized with Doppler measurements using factor graph optimization (FGO) in a loosely-coupled fashion. This study also evaluated positioning performance using an advanced wearable system’s recorded data in New York City. The real-time forward processed FGO can provide a root-mean-square error (RMSE) with about 21 m. The RMSE drops to 16 m when the data is post-processed with FGO in a combined direction. Overall results show that the proposed loosely-coupled 3DMA FGO algorithm can provide a better and more robust positioning performance for the multi-sensor integration approach used by this wearable for persons with BLV.

This article describes the methodology used to identify the mathematical model that describes the correlations between the input parameters of an experiment and the parameters being followed. As a technological process, the aerodynamic separation was chosen, respectively, the behavior of a solid particle within an ascending vertical airflow. The experimental data obtained were used to identify two parameters, the average linear velocity, and the angular velocity, and through the Table Curve 3D program was developed a mathematical model which describes the dependence between the input parameters (the shape and size of the solid particle and the velocity of the airflow) and the monitored parameters. In order to determine a single mathematical equation that describes as accurately as possible the correlation between the input variables and those obtained, a pyramid-type analysis was designed. The determination of the mathematical equation started from the number of equations generated by the Table Curve 3D program, then the equations with a correlation coefficient greater than 0.85 were chosen, and finally, the common equations were identified. Respecting the working methodology was identified one equation which has for the average linear velocity a correlation coefficient r2 between 0.88-0.99 and 0.86-0.99 for the angular velocity.

Radar observation data with high temporal and spatial resolution are used in the data assimilation experiment to improve precipitation forecast of a numerical model. The numerical model considered in this study is Weather Research and Forecasting (WRF) model with double-moment 6-class microphysics scheme (WDM6). We calculated radar equivalent reflectivity factor using higher resolution WRF and compared with radar observations in South Korea. To compare the precipitation forecast characteristics of three-dimensional variational (3D-Var) assimilation of radar data, four experiments are performed based on different precipitation types. Comparisons of the 24-h accumulated rainfall with Automatic Weather Station (AWS) data, Contoured Frequency by Altitude Diagram (CFAD), Time Height Cross Sections (THCS), and vertical hydrometeor profiles are used to evaluate and compare the accuracy. The model simulations are performed with and with-out 3D-VAR radar reflectivity, radial velocity and AWS assimilation for two mesoscale convective cases and two synoptic scale cases. The radar data assimilation experiment improved the location of precipitation area and rainfall intensity compared to the control run. Especially, for the two convective cases, simulating mesoscale convective system was greatly improved.

The initial stability after implantology is paramount to the survival of the dental implant and the surface roughness of the implant plays a vital role in this regard. The characterisation of surface topography is a complicated branch of metrology, with a huge range of parameters available. Each parameter contributes significantly towards the survival and mechanical properties of 3D-printed specimens. The purpose of this paper is to experimentally investigate the effect of surface roughness of 3D-printed dental implants and 3D-printed dogbone tensile samples under areal height (Ra) parameters, amplitude parameters (average of ordinates), skewness (Rsk) parameters and mechanical properties. During the experiment, roughness values were analysed and the results showed that the skewness parameter demonstrated a minimum value of 0.596%. The 3D-printed dental implant recorded Ra with a 3.4 mm diameter at 43.23% and the 3D-printed dental implant with a 4.3 mm diameter at 26.18%. Samples with a complex geometry exhibited a higher roughness surface, which was the greatest difficulty of additive manufacturing when evaluating surface finish. The results show that when the ultimate tensile stress (UTS) decreases from 968.35 MPa to 955.25 MPa, Ra increases by 1.4% and when UTS increases to 961.18 MPa, Ra increases by 0.6%. When the cycle decreases from 262142 to 137433, Ra shows that less than a 90.74% increase in cycle is obtained. For 3D-printed dental implants, the higher the surface roughness, the lower the mechanical properties, ultimately leading to decreased implant life and poor performance.

Three-dimensional (3D) printing techniques have received considerable focus in the area of bone engineering due to its precise control in the fabrication of complex structures with customizable shapes, internal and external architectures, mechanical strength, and bioactivity. In this study, we design a new composition biomaterial consisting of polylactic acid (PLA), and halloysite nanotubes (HNTs) loaded with zinc nanoparticles (PLA+H+Zn). The hydrophobic surface of the 3D printed scaffold was coated with two layers of fetal bovine serum (FBS) on the sides and one layer of NaOH in the middle. Additionally, a layer of gentamicin was coated on the outermost layer against bacterial infection. Scaffolds were cultured in standard cell culture medium without the addition of osteogenic medium. This surface modification strategy improved material hydrophilicity and enhanced cell adhesion. Pre-osteoblasts cultured on these scaffolds differentiated into osteoblasts and proceeded to produce a type I collagen matrix and subsequent calcium deposition. 3D printed scaffolds formed from this composition possessed high mechanical strength and showed an osteoinductive potential. Furthermore, the external coating of antibiotics not only preserved the previous osteogenic properties of the 3D scaffold but also significantly reduced bacterial growth. Our surface modification model enabled the fabrication of a material surface that was hydrophilic and antibacterial, simultaneously, with an osteogenic property. The designed PLA+H+Zn may be a viable candidate for the fabrication of customized bone implants.

Paclitaxel is a natural, highly lipophilic anti proliferative drug widely used in medicine. We have studied the release of tritium-labeled paclitaxel (³H-PTX) from matrices destined for the coating of vascular stents and produced by the electrospinning method from the solutions of polycaprolactone (PCL) with paclitaxel (PTX) in hexafluoisoropropanol (HFIP) and/or solutions of PCL with PTX and human serum albumin (HSA) in HFIP or HIFP-dimethyl sulphoxide (DMSO) blend. The release of PTX has been shown to depend on the solvent and the composition of electrospinning solution, as well as the composition of the surrounding medium, particularly the concentration of free PTX and PTX-binding biomolecules present in human serum. It was shown that 3D matrices can completely release PTX without weight loss. Two-phase PTX release from optimized 3D matrices was obtained: ~27% of PTX was released in the first day, another 8% were released over the next 26 days. Wherein ~2.8%, ~2.3%, and ~0.25% of PTX was released on day 3, 9, and 27, respectively. Considering PTX toxicity, the rate of its diffusion through the arterial wall, and the data obtained the minimum cytostatic dose of the drug in the arterial wall will be maintained for at least three months.

AbstractWhile the technology is relatively new, low cost 3D printing has impacted many aspects of human life. 3D printers are being used as manufacturing tools for a wide variety of devices in a spectrum of applications ranging from diagnosis to implants to external prostheses. The ease of use and availability of 3D design software and low cost has made 3D printing an accessible manufacturing and fabrication tool in many research laboratories. 3D printers can print materials with varying density, optical character, strength and chemical properties providing platforms for a huge number of strategies that can be chosen for user’s needs. In this review, we focus on applications in biomedical diagnostics and how this revolutionary technique is facilitating development of low cost, sensitive and often geometrically complex tools. 3D printing in fabrication of microfluidics, supporting equipment, optical and electronic components of diagnostic devices is presented. Emerging diagnostic 3D bioprinting as a tool to incorporate living cells or biomaterials into 3D printing is also discussed.

This study aimed to assess the response of 3D printed PLA scaffolds biomimetically coated with apatite on human primary osteoblast spheroids and evaluate the biological response to its association with Bone Morphogenetic Protein 2 (rhBMP-2) in rat calvaria. PLA scaffolds were produced via 3D printing, soaked in simulated body fluid (SBF) solution, and characterized by physical-chemical, morphological, and mechanical properties. The in vitro biological response was assessed with human primary osteoblast (HOb) spheroids. The in vivo analysis was conducted through the implantation of 3D printed PLA scaffolds either alone, covered by apatite (PLA-CaP) or PLA-CaP loaded with rhBMP-2 (PLA-CaP+rhBMP-2) on critical-sized defects (8 mm) of rat calvaria. Increased cell adhesion and in vitro release of growth factors (PDGF, bFGF, VEGF) was observed for PLA-CaP scaffolds when pre-treated with FBS. PLA-CaP+BMP2 presented higher values of newly formed bone (NFB) than other groups at all experimental periods (p<0.05), attaining 44.85% of NFB after 6 months. These findings indicate that functionalization of PLA scaffolds with biomimetic apatite can improve its biological properties in the presence of complex biological media. Its association with BMP2 may enhance bone repair, suggesting this strategy as a promising candidate for bone tissue engineering.

Currently, the number of approved veterinary medicines are limited, and human medications are used off-label. These approved human medications are of too high potencies for a cat or a small dog breed. Therefore, there is a dire demand for smaller doses of veterinary medicines. This study aims to investigate the use of three semi-solid extrusion 3D printers in a pharmacy or animal clinic setting for extemporaneous manufacturing of prednisolone containing orodispersible films for veterinary use. Orodispersible films with adequate content uniformity and acceptance values defined by the European Pharmacopoeia was produced with one of the studied printers, namely, the Allevi 2 bioprinter. Smooth and flexible films, with high mechanical strength, neutral pH, and low moisture content were produced with high correlation between prepared design and obtained drug amount, indicating that the Allevi 2 printer could successfully be used to extemporaneously manufacture personalized doses for animals at the point-of-care.

Direct laser writing three-dimensional nano-lithography is an established technique for manufacturing functional 3D micro- and nano-objects via non-linear absorption induced polymerization process. In this Chapter an underlying physical mechanisms taking place during nano-confined polymerization reaction, induced by tightly focused ultra-short laser pulses, are reviewed and discussed. The special attention is paid on the effects that directly impact structuring resolution and minimum achievable feature size. Analysis of possible photo-initiation mechanisms as contributing multi-photon absorption and avalanche ionization in pre-polymers under diverse exposure conditions (wavelength, pulse duration) is presented. Feasible structuring of pure (non-photosensitized) and functional nanoparticles doped polymer precursors is justified and benefits of such materials/structures for microoptics, photonics and cell scaffolds are highlighted. The influence of temperature effects (induced by writing process itself or determined by ambient conditions) on polymerization process, observed in different pre-polymers under diverse exposure regimes is outlined. The further adjustment of the structuring resolution is possible via precise control of light polarization and diffusion assisted radical quenching. The work is concluded with a brief outlook on future challenges and perspectives related to refinement of 3D ultra-fast laser lithography fabrication process in the means of application of diverse post-processing methods and research into novel photo-curable materials including inorganic ones.

3D meso-scale structures that can reach up to centimeters in overall size but retain micro- or nano-features, proved to be promising in various science fields ranging from micro-mechanical metamaterials to photonics and bio-medical scaffolds. In this work we present synchronization of the linear and galvano scanners for efficient femtosecond 3D optical printing of objects at the meso-scale (from sub-μm to sub-cm spanning five orders of magnitude). In such configuration the linear stages provide stitch-free structuring at nearly limitless (up to tens-of-cm) working area, while galvo-scanners allow to achieve translation velocities in the range of mm/s-cm/s without sacrificing nano-scale positioning accuracy and preserving undistorted shape of the final print. The principle behind this approach is demonstrated, proving its inherent advantages in comparison to separate use of only linear stages or scanners. The printing rate is calculated in terms voxels/s, showcasing the capability to maintain an optimal feature size while increasing throughput. Full capabilities of this approach are demonstrated by fabricating structures that reach millimeters in size but still retain μm-scale features: scaffolds for cell growth, microlenses and photonic crystals. All this is combined into a benchmark structure: a meso-butterfly. Provided results show that synchronization of two scan modes is crucial for the end goal of industrial-scale implementation of this technology and makes the laser printing well aligned with similar approaches in nanofabrication by electron and ion beams.

Это исследование сосредоточено на разработке системы искусственного зрения для гибкого дельта-робота-манипулятора и ее интеграции с межмашинной связью для оптимизации взаимодействия устройств в реальном времени. Эта интеграция направлена ​​на увеличение скорости роботизированной системы и улучшение ее общей производительности. Предлагаемое сочетание системы искусственного зрения с межмашинной связью позволяет обнаруживать и распознавать цели с высокой точностью в режиме реального времени в ограниченном пространстве, предназначенном для позиционирования, дальнейшей локализации и выполнения производственных процессов, таких как сборка или сортировка деталей. . В данном исследовании RGB-изображения используются в качестве входных данных для алгоритма MASK-R-CNN, а результаты обрабатываются в соответствии с особенностями прототипа дельта-манипулятора робота. Данные, полученные от MASK-R-CNN, адаптированы для использования в системе управления дельта-роботом с учетом ее уникальных характеристик и требований к позиционированию. Технология M2M позволяет манипулятору робота быстро реагировать на изменения, например, на перемещение объектов или изменение их положения, что имеет решающее значение для задач сортировки и упаковки. Система была протестирована в условиях, близких к реальным, чтобы оценить ее производительность и надежность.

Facial recognition systems are widely used systems around the globe. Their applications in real world scenarios like law enforcement, surveillance, ID card identification, information security, access control and many more has made them very important in today’s world. These systems have shown promising results and excellent performance; however, these systems need tremendous number of facial images for training before they are implemented in the real-world scenarios. The problem arises when we face lack of training images due to which the performance of such systems decreases exponentially. The problem becomes even worse when there is only one image per subject for training our facial recognition system, the probe image might contain variation like illumination, expression and disguise which are hard to be accurately recognized. Generative models have achieved great success for handling the lack of training data by generating synthetic data that resembles the original data. We have created a new method by fine tuning the basic Conditional Generative Adversarial Network (CGAN) to generate synthetic facial images provided only single image per subject. These synthetic facial images contain six variations that are smile, anger, stare, illumination and disguise. We increased the size of the dataset and then applied a convolutional neural network for facial recognition, which improved the accuracy of our system from 0.76 to 0.99.

In order to improve real-time performance of gesture recognition by micro-Doppler map of mmWave Radar, the point cloud based gesture recognition for mmWave Radar is proposed in this paper.Two steps are carried out for mmWave Radar based gesture recognition. The first step is to estimate the point cloud of the gestures by 3D-FFT and the peak grouping. The second step is to train the TRANS-CNN model by combining the multi-head self-attention and the 1D-convolutional network, so as to extract the features in the point cloud data at a deeper level to categorize the gestures. In the experiments, TI mmWave Radar sensor IWR1642 is used as benchmark to evaluate the feasibility of the proposed approach. The results show that the accuracy of the gesture recognition reaches 98.5%. In order to prove the effectiveness of our approach, a simply 2Tx2Rx Radar sensor is developed in our lab and the accuracy of recognition reaches 97.1%. The results show that our proposed gesture recognition approach achieves the best performance in real-time with limited training data, in comparison with the existing methods.

Diabetic retinopathy (DR), a major complication of prolonged diabetes, poses a significant risk of vision loss. Early detection is critical for effective treatment, yet traditional diagnostic methods by ophthalmologists are time-consuming, costly, and subject to variability. This study introduces a novel approach employing a hybrid Convolutional Neural Network-Radial Basis Function (CNN-RBF) classifier integrated with Multi-Scale Discriminative Robust Local Binary Pattern (MS-DRLBP) features for enhanced DR detection. We implemented advanced image preprocessing techniques, including noise reduction, morphological operations, and Otsu’s thresholding, to optimize blood vessel segmentation from retinal images. Our method demonstrates exceptional performance in screening DR, achieving an average of 96.10% precision, 95.35% sensitivity, 97.06% specificity, and 96.10% accuracy. These results significantly outperform traditional methods and offer a promising tool for remote and efficient screening of DR. Applied to publicly available datasets, this research contributes to the development of accessible, accurate diagnostic methods in ophthalmology, potentially reducing the global burden of diabetic vision loss.

Ultrasound (US) has become a widely used imaging modality in clinical practice, characterized by its rapidly evolving technology, advantages, and unique challenges such as low imaging quality and high variability. There is a critical need to develop advanced automatic US image analysis methods to enhance diagnostic accuracy and objectivity. Vision transformer, a recent innovation in machine learning, has demonstrated significant potential in various research fields, including general image analysis and computer vision, due to its capacity to process large datasets and learn complex patterns. Its suitability for automatic US image analysis tasks, such as classification, detection, and segmentation, has been recognized. This review provides an introduction to vision transformer and discusses its applications in specific US image analysis tasks, while also addressing the open challenges and potential future trends in its application in medical US image analysis. Vision transformer has shown promise in enhancing the accuracy and efficiency of ultrasound image analysis and is expected to play an increasingly important role in the diagnosis and treatment of medical conditions using ultrasound imaging as technology progresses.

Chinese calligraphy, revered globally for its therapeutic and mindfulness benefits, encompasses styles such as Regular (Kai Shu), Running (Xing Shu), Official (Li Shu), and Cursive (Cao Shu) scripts. Beginners often start with Regular script, advancing to more intricate styles like Cursive. Each style, marked by unique historical calligraphers' contributions, requires learners to discern distinct nuances. The integration of AI in calligraphy analysis, collection, recognition, and classification are pivotal. This study introduces an innovative Convolutional Neural Network (CNN) architecture, pioneering the application of CNN in the classification of Chinese calligraphy. Focusing on the four principal calligraphers' styles from the Tang dynasty (690-907 A.D), this research spotlights the era when the traditional regular script font (Kai Shu) was refined. A comprehensive dataset of 8282 samples from these calligraphers, representing the zenith of regular style, was compiled for CNN training and testing. The model distinguishes personal styles for classification, showing superior performance over existing networks. Achieving 89.5-96.2% accuracy in calligraphy classification, our approach underscores the significance of CNN in both font and artistic style categorization. This research paves the way for advanced studies in Chinese calligraphy and its cultural implications.

Photoelectric smoke detectors are the most cost-effective devices for very early fire alarms. However, due to different light intensity response values for different fire smoke and interference from interferential aerosols, they have a high false alarm rate, which limits their popularity in Chinese homes. To address these issues, an embedded spatial-temporal convolutional neural network (EST-CNN) model is proposed for real fire smokes identification and aerosols (fire smokes and interferential aerosol) classification. EST-CNN consists of three modules including information fusion, scattering feature extraction, and aerosol classification. Moreover, a two dimensional spatial-temporal scattering (2D-TS) matrix is designed to fuse the scattered light intensities in different channels and adjacent time slices, which is the output of the information fusion module and the input of the scattering feature extraction module. EST-CNN is trained and tested with experimental data measured on the established fire test platform using the developed dual-wavelength dual-angle photoelectric smoke detector. The optimal network parameters are selected through extensive experiments resulting in an average classification accuracy of 95.6% for different aerosols with only 66 kB network parameters. The experimental results demonstrate the feasibility of the designed EST-CNN model to be directly installed in existing commercial photoelectric smoke detectors to realize aerosol classification.

More and more people quantify their sleep using wearables and are getting obsessed in their pursuit of optimal sleep (“orthosomnia”). However, it is criticized that many of these wearables are giving inaccurate feedback and even can lead to negative daytime consequences. Acknowledging these facts, we here aim to extend previous findings [] in a new sample of 136 self-reported poor sleepers by implementing optimization procedures to minimize erroneous classification when ambulatory sensing sleep. Firstly, here, we introduce an advanced interbeat-interval (IBI) quality control using a random forest method to account for wearable recordings in naturalistic and more noisy settings. We further aim to improve sleep classification by opting for a loss function model instead of overall epoch-by-epoch accuracy to avoid model biases towards the majority class (i.e., “light sleep”). Using these implementations, we compare the classification performance between the optimized (loss function model) and the accuracy model. We use signals derived from PSG, one-channel ECG, and two consumer wearables: the ECG breast belt Polar® H10 (H10) and the Polar® Verity Sense (VS), an optical Photoplethysmography (PPG) heart-rate sensor. Results reveal high overall accuracy for the new model for ECG (86.3 %, κ=.79), H10 (84.4%, κ=.76), and VS (84.2%, κ=.75) with intended improvements in deep sleep and wake. In addition, the new optimized model displays moderate to high correlations and agreement with PSG on primary sleep parameters, while measures of reliability, expressed in intra-class correlations, suggest excellent reliability for most sleep parameters. Finally, it is demonstrated that the new model is still classifying sleep accurately in 4-classes in users taking heart-affecting and/or psychoactive medication which can be considered a prerequisite for use also in high age groups and/or with common disorders. Further improving and validating sleep stage classification algorithms with affordable wearables may resolve existing scepticism and open the door for such approaches in clinical practice.

Some recent studies show that filters in convolutional neural networks (CNNs) have low color selectivity in datasets of natural scenes such as Imagenet. CNNs, bio-inspired in the visual cortex, are characterized by their hierarchical learning structure, which appears to gradually transform the representation space. Inspired by the direct connection between the LGN and V4, which allows V4 to handle low-level information closer to the trichromatic input in addition to processed information that comes from V2/V3, we propose the addition of a long skip connection (LSC) between the first and last blocks of the feature extraction stage to allow deeper parts of the network to receive information from shallower layers. This type of connection improves classification accuracy by combining simple-visual and complex-abstract features to create more color-selective ones. We have applied this strategy to classic CNN architectures and quantitatively and qualitatively analyzed the improvement in accuracy while focusing on color selectivity. The results show that, in general, skip connections improve accuracy, but LSC improves it even more and enhances the color selectivity of the original CNN architectures. As a side result, we propose a new color representation procedure for organizing and filtering feature maps, making their visualization more manageable.

The purpose of this work was to achieve non-destructive detection of the internal defects of in-shell walnuts using X-ray radiography technology based on improved Faster R-CNN network model. First, the FPN structure was added to the feature extraction layer to extract richer image information. Then ROI Align was used to instead of ROI Pooling for eliminating the localization bias problem caused by quantization operation. Finally, the Softer-NMS module was introduced to the final regression layer with the predicted bounding box for improving the localization accuracy of the candidate boxes. The results indicated that the internal defects in intact walnuts with shells could be identified effectively using the proposed improved network model in this study. Specifically, the discrimination accuracy of the in-shell sound, shriveled and empty-shell walnuts were 96.14%, 91.72% and 94.80% respectively, and the highest overall accuracy can reach 94.22 %. Contrasted with original Faster R-CNN network model, the mAP and F1-value of the improved Faster R-CNN model increased by 5.86% and 5.65%, respectively. Consequently, the proposed method can be applied for the in-shell walnuts with shriveled and empty-shell defects.

Object recognition is an essential element of machine intelligence tasks. However, one model cannot practically be trained to identify all the possible objects it encounters. An ensemble of models may be needed to cater to a broader range of objects. Building a mathematical understanding of the relationship between various objects that share comparable outlined features is envisaged as an effective method of improving the model ensemble through a pre-processing stage, where these objects' features are grouped under a broader classification umbrella. This paper proposes a mechanism to train an ensemble of recognition models coupled with a model selection scheme to scale-up object recognition in a multi-model system. An algorithmic relationship between the learnt parameters of a trained classification model and the features of input images is presented in the paper for the system to learn the model selection scheme. The multiple models are built with a CNN structure, whereas the image features are extracted using a CNN/VGG16 architecture. Based on the models' excitation weights, a neural network model selection algorithm, which links a new object with the models and decides how close the features of the object are to the trained models for selecting a particular model for object recognition is developed and tested on a five-model neural network platform. The experiment results show the proposed model selection scheme is highly effective and accurate in selecting an appropriate model for a network of multiple models.

Functional connectivity (FC) is a potential candidate that can increase the performance of brain-computer interfaces (BCIs) in the elderly because of its compensatory role in neural circuits. However, it is difficult to decode FC by current machine learning techniques because of a lack of its physiological understanding. To investigate the suitability of FC in BCI for the elderly, we propose the decoding of lower- and higher-order FCs using a convolutional neural network (CNN) in six cognitive-motor tasks. The layer-wise relevance propagation (LRP) method describes how age-related changes in FCs impact BCI applications for the elderly compared to younger adults. Seventeen younger (24.5±2.7 years) and twelve older (72.5±3.2 years) adults were recruited to perform tasks related to hand-force control with or without mental calculation. CNN yielded a six-class classification accuracy of 75.3% in the elderly, exceeding the 70.7% accuracy for the younger adults. In the elderly, the proposed method increases the classification accuracy by 88.3% compared to the filter-bank common spatial pattern (FBCSP). LRP results revealed that both lower- and higher-order FCs were dominantly overactivated in the prefrontal lobe depending on task type. These findings suggest a promising application of multi-order FC with deep learning on BCI systems for the elderly.

Timely detection of surface damages on wind turbine blades is imperative for minimising downtime and avoiding possible catastrophic structural failures. With recent advances in drone technology, a large number of high-resolution images of wind turbines are routinely acquired and subsequently analysed by experts to identify imminent damages. Automated analysis of these inspection images with the help of machine learning algorithms can reduce the inspection cost, thereby reducing the overall maintenance cost arising from the manual labour involved. In this work, we develop a deep learning based automated damage suggestion system for subsequent analysis of drone inspection images. Experimental results demonstrate that the proposed approach could achieve almost human level precision in terms of suggested damage location and types on wind turbine blades. We further demonstrate that for relatively small training sets advanced data augmentation during deep learning training can better generalise the trained model providing a significant gain in precision.

Detailed built-up area information is valuable for mapping complex urban environments. Although a large number of classification algorithms about built-up areas have been developed, they are rarely tested from the perspective of feature engineering and feature learning. Therefore we launched a unique investigation to provide a full test of the OLI imagery for 15-m resolution built-up area classification in 2015, in Beijing, China. Training a classifier requires many sample points, and we propose a method based on the ESA's 38-meter global built-up area data of 2014, Open Street Map and MOD13Q1-NDVI to achieve rapid and automatic generation of a large number of sample points. Our aim is to examine the influence of a single pixel and image patch under traditional feature engineering and modern feature learning strategies. In feature engineering, we consider spectra, shape and texture as the input features, and SVM, random forest (RF) and AdaBoost as the classification algorithms. In feature learning, the convolution neural network (CNN) is used as the classification algorithm. In total, 26 built-up land cover maps were produced. Experimental results show that: (1) the approaches based on feature learning are generally better than those based on feature engineering in terms of classification accuracy, and the performance of ensemble classifiers e.g., RF, is comparable to that of CNN. Two dimensional CNN and the 7 neighborhood RF have the highest classification accuracy of nearly 91%. (2) Overall, the classification effect and accuracy based on image patches are better than those based on single pixels. The features that can highlight the information of the target category (for example, PanTex and EMBI) can help improve classification accuracy.

In the last decade, three-dimensional (3D) printing has allowed the field of complex microfluidic channels to expand rapidly towards channels with variable cross-sections (i.e., beyond simple rounded media with a constant diameter) and channels. Whose trajectory can be outside a single plane and has gained numerous macro- and nanoscale manufacturing advances. Three-dimensional printing is being explored for various biomedical applications and the fabrication of nanomedicines using additive manufacturing techniques. Employing 3D-printed templates for macro-to-micro interfacing, a passively operated microfluidic device was designed. The research seeks to fabricate a biodevice that enables insulin microdosing, creating a subsystem like a microvalve and a microchannel matrix using additive manufacturing techniques. Our systems feature designs that enhance fluid dynamics without affecting the stability of the insulin. We propose using Humalog insulin in tropical climates (up to 30°C) without refrigeration for 28 days. The microvalve has a spiral trajectory with four outlet channels distributed along it. These channels align with the microchannels organized in a 10 mm x 15 mm matrix with 25 microchannels, each with a 770 µm internal diameter. The system delivers a dose of 2,3 mL in 6 minutes. We designed these systems for insulin micro-dosing, but they can also serve similar devices for other drugs.

Three-dimensional flexible piezoresistive porous sensors have been used in health diagnosis and wearable devices. By utilizing 3D printed sacrificial mold casting with highly conductive polymer composites, porous sensors with high conductivity and complex structures were achieved. Traditional conductive polymer composites are usually heated using external heat sources, which are time and energy consuming. However, in this study, conductive porous sensors with triply periodic minimal surface (TPMS) structures were manufactured using self-resistance electric heating by utilizing the conductive nature of the polymers. The porous structures were designed based on Diamond (D), Gyroid (G), and I-WP (I) unit cells of the TPMS. The use of self-resistance electric heating has improved the compression performance and piezoresistive response of the structures. Among these structures, the D-based structure exhibited the maximum response strain (61 %), with a corresponding resistance response value of 0.97, which increased by 10.26 % compared to that of the structures heated by using the external heat sources. This study offers a new perspective on designing and optimizing porous materials with specific functionalities, particularly in the realm of flexible and portable piezoresistive sensors.

Microspheres, synthesized from diverse natural or synthetic polymers, are readily utilized in biomedical tissue engineering to improve the healing of various tissues. Their ability to encapsulate growth factors, therapeutics, and natural biomolecules, which can aid tissue regeneration, makes microspheres invaluable for future clinical therapies. While microsphere-supplemented scaffolds have been investigated, a pure microsphere-based scaffold with an optimized architecture has been challenging to create via 3D printing methods due to issues that prevent consistent deposition of microsphere-based materials and their ability to maintain the shape of the 3D-printed structure. Utilizing the extrusion printing process, we established a methodology which not only allows to create large microsphere-based scaffolds but also multicomposite matrices into which cells, growth factors, and therapeutics encapsulated in microspheres can be directly deposited during the printing process. Our 3D-McMap method addresses issues with scaffold shape fidelity during and after printing. Carefully timed breaks, minuscule drying steps, and adjustments to extrusion parameters, generated an evenly layered large microsphere-based scaffold that retains its internal architecture. Such scaffolds are superior to other microsphere-containing scaffolds, as they can release biomolecules in a highly controlled spatiotemporal manner. This capability permits to study cell responses to the delivered signals, to develop scaffolds that precisely modulate new tissue formation.

Bismaleimide (BMI) is a high-performance thermosetting resin widely used in the aerospace, automotive, and mechanical and electronics industries due to its chemical and mechanical stability. It also has the capability of being used as an ink in polyjets used for 3D printing evident from thinner mellamide FTIR bands and faster curing rates as observed from TGA-DSC studies.

To improve the measurement accuracy of three-dimensional rotation angle of the spherical joint, a novel approach is proposed in this study, which combines the magnetic detection by Hall sensor and surface feature identification by eddy current sensor. Firstly, a permanent magnet is embedded in the ball head of spherical joint, and Hall sensors are set and distributed in the ball socket to measure the variation of magnetic flux density when spherical joint rotating, which are related to 3D rotation angle. In order to further improve measurement accuracy and robustness, we also set grooves on the ball head and use eddy current sensors to synchronously identify the rotation angle of the ball head. After the combination of two signals is adopted, a measurement model is established using the RBF neural network by training, and realized real-time measurement of the 3D rotation angle of spherical joint. The feasibility and superiority of this method are validated through experiments. The experimental results indicated that the measurement accuracy is promoted substantially compared to the preliminary measurement scheme based on spherical coding, the average measurement error of single axis is reduced by 9'9". The root mean square errors for the measurement of 3D rotation angles in this proposed method are as follows: the pitch angle α has an error of 1'8", the yaw angle β has an error of 2'15", and the roll angle γ has an error of 29'6".

With increasing demand from unmanned driving and robotics, more attention has been paid to point cloud-based 3D object accurate detection technology. However, due to the sparseness and irregularity of the point cloud, the most critical problem is how to utilize the relevant features more efficiently. In this paper, we proposed a point-based object detection enhancement network to improve the detection accuracy in the 3D scenes understanding based on the distance features. Firstly, the distance features are extracted from the raw point sets and fused with the raw features about reflectivity of the point cloud to maximizing the use of information in point cloud. Secondly, we enhanced the distance features and raw features that we collectively refer to them as self-features of the key points in Set Abstraction (SA) layers with the self-attention mechanism, so that the foreground points can be better distinguished from the background points. Finally, we revised the group aggregation module in SA layers to enhance the feature aggregation effect of key points. We conducted experiments on the KITTI dataset and nuScenes dataset and the results show the enhancement method proposed in this paper has excellent performance.

In the realm of autonomous vehicle environment perception, the primary objective of point cloud target detection is to swiftly and accurately identify three-dimensional objects from point cloud data. To meet this requirement, the prevalent network architecture employed in the industry is the voxel-based PointPillars model. Nonetheless, this model faces challenges in maintaining detection accuracy when objects are obscured or diminutive in size. In response to this issue, we introduce AGPNet, a novel model that seamlessly integrates four key modules: Data Augmentation, Dynamic Graph CNN, Pillar Feature Net, and Detection Head (SSD). The Data Augmentation module enhances the adaptability of point cloud data to complex and ever-changing real-world environments. The Dynamic Graph CNN module endows the network structure with geometric features, which encapsulate not only the point itself but also its adjacent points. The Pillar Feature Net module translates three-dimensional point cloud data into pseudo-image data through the utilization of voxels. Subsequently, the Detection Head (SSD) module leverages this pseudo-image data to conduct target detection of three-dimensional objects. Our experiments, conducted on the KITTI dataset, demonstrate that our proposed method boosts object detection accuracy by 6-7 percentage points compared to the PointPillars model, while maintaining similar detection times.

We present a near real-time solution for 3D reconstruction from aerial images captured by consumer UAVs. Our core idea is to simplify the multi-view stereo problem into a series of two-view stereo matching problems. Our method applies to UAVs equipped with only one camera and does not require special stereo-capturing setups. We found that the neighboring two video frames taken by UAVs flying at a mid-to-high cruising altitude can be approximated as left and right views from a virtual stereo camera. Leveraging GPU-accelerated real-time stereo estimation, efficient PnP correspondence solving algorithms and extended Kalman filter, our system simultaneously predicts scene geometry and camera position/orientation from the virtual stereo cameras. Also, this method allows user selection of varying baseline lengths, which provides more flexibility given the trade-off between camera resolution, effective measuring distance, flight altitude, and mapping accuracy. Our method outputs dense point clouds at a constant speed of 25 frames per second and is validated on a variety of real-world datasets with satisfactory results.

The process of identifying and approving a new drug is a time-consuming and expensive procedure. One of the biggest issues to overcome is the risk of hepatotoxicity, which is one of the main reasons for drug withdrawal from the market. While animal models are the gold standard in preclinical drug testing, the translation of results into therapeutic intervention is often ambiguous due to interspecies differences in hepatic metabolism. The discovery of human induced Pluripotent Stem Cells (hiPSCs) and their derivatives has opened new possibilities for drug testing. We used mesenchymal stem cells and hepatocytes both derived from hiPSC, together with endothelial cells, to miniaturize the process of generating hepatic organoids. These organoids were then cultivated in vitro using both static and dynamic cultures. Additionally, we tested spheroids composed solely by induced hepatocytes. By miniaturizing the system, we demonstrated the possibility of maintaining the organoids, but not the spheroids, in culture for up to 15 days. This timeframe may be sufficient to carry out a hypothetical pharmacological test or screening. In conclusion, we propose that the hiPSC-derived liver organoids model could complement or, in the near future, replace the pharmacological and toxicological tests conducted on animals.

High efficiency and safety are critical factors in ensuring optimal performance and reliability of systems and equipment across various industries. Fault Monitoring (FM) techniques play a pivotal role in this regard by continuously monitoring system performance and identifying the presence of faults or abnormalities. However, traditional FM methods face limitations in fully capturing the complex interactions within a system and providing real-time monitoring capabilities. To overcome these challenges, Digital Twin (DT) technology has emerged as a promising solution to enhance existing FM practices. By creating a virtual replica or digital copy of a physical equipment or system, DT offers the potential to revolutionize fault monitoring approaches. This paper aims to explore and discuss the diverse range of predictive methods utilized in DT and their implementations in FM across industries. Furthermore, it will showcase successful implementations of DT in FM across a wide array of industries, including manufacturing, energy, transportation, and healthcare The utilization of DT in FM enables a comprehensive understanding of system behavior and performance by leveraging real-time data, advanced analytics, and machine learning algorithms. By integrating physical and virtual components, DT facilitates the monitoring and prediction of faults, providing valuable insights into the system’s health and enabling proactive maintenance and decision-making.

Recently, 3D printing techniques gained much attention in solid dosage form production. Even though the methods are increasingly studied, there are still many challenges in establishing an accurate content of active ingredients in the final products. In the present study, new experimental design techniques and statistical software were developed to identify and optimize a formula to predict the mass of the tablet to be 3D printed before it actually is. The first step was to develop a virtual 3D object in the FreeCad Software, then, using a CURA slicer software, the G-code Format was obtained. The tablets were printed using a Cartesian 3D printer based on the generated data. Finally, adapting the object sequencing mode, a predicted drug mass value was obtained. As expected, the oblong tablet's scaling directly influences its mass. The software generates a correlation coefficient (r) of 0.84, confirming the directly proportional relationship between scaling and tablet weight. However, the r values progressively decreased, indicating a poor correlation between tablet weight and other factors: infill density percent (r = 0.403) and wall thickness (r = 0.185). After repeating the 3D printing with the values ​​suggested by the software, tablets with a practical value of 1066 mg were obtained. Considering that the confidence interval calculated is [834.95—1165.05] and the experimental value is 1066 mg, it can be certified that the proposed model is valid.

Magnesium ions play an important immune-regulatory role during bone repair. For this study, we prepared micro-nano bioactive glass containing magnesium, which can release magnesium, silicon, and calcium ions and has a positive impact on osteogenic differentiation and vascular regeneration. In this study, MgMNBG was compounded and combined with PLGA and PCL for 3D printing. Afterwards, the physicochemical properties and bone repair performance of the scaffolds were evaluated through in vitro and in vivo experiments. We also investigated the effects of MgMNBG on osteogenic differentiation, immune regulation, and vascular regeneration. The results showed that MgMNBG can inhibit inflammation and promote osteogenesis and angiogenesis by regulating macrophages. PLGA/PCL/MgMNBG scaffolds have good osteogenic and angiogenic effects, and the composite scaffolds have excellent bone repair performance and potential application value.

The addition of biocarriers can improve the biological processes appearing in a bioreactor since their surface allows the immobilization, attachment, protection, and growth of microorganisms. In addition, the development of a biofilm layer allows the colonization of microorganisms in the biocarriers. The structure, composition, and roughness of the biocarriers' surface are crucial factors that affect the development of the biofilm. In the current work, the aluminosilicate zeolites 13X and ZSM-5 were examined as the main building components of the biocarrier scaffolds, using bentonite, montmorillonite, and halloysite nanotubes as inorganic binders in various combinations. 3D printing was utilized to form pastes into monoliths that underwent heat treatment. The 3d-printed biocarriers were subjected to a mechanical analysis, including density, compression, and nanoindentation tests. Furthermore, the 3d-printed biocarriers were morphologically and structurally characterized using nitrogen adsorption at 77 K (LN2), scanning electron microscopy (SEM), and X-ray diffraction (XRD). The stress-strain response of the materials being studied was obtained through nanoindentation tests combined with finite element analysis (FEA). These tests were also utilized to simulate the lattice geometries under compression loading conditions to investigate their deformation and stress distribution in relation to experimental compression testing. The results indicated that the 3d-printed biocarrier 13X/halloysite nanotubes was endowed with high specific surface area and extended mesoporous structure. Due to these assets, its bulk density was one of the lowest observed amongst the biocarriers derived from the various combinations of materials. The biocarriers based on the 13X zeolite exhibited the highest mechanical stability and appropriate morphological features. The 13X/halloysite nanotubes scaffold exhibits a moderate hardness value compared to the rest, while it presents the highest value of modulus of elasticity. In conclusion, Aluminosilicate zeolites and their combination with clays and inorganic nanotubes afford 3d-printed biocarriers of various textural and structural properties, which can be utilized to improve biological processes.

The unsolved problem in three-dimensional surgical planning for patients with facial deformity, dysgnathia, or asymmetry is the lack of a normative database of “norm skulls” that can be used as treatment objectives. A study was conducted on 90 Eurasian persons (46 male and 44 female adults) with normal and balanced facial appearance, skeletal Class I pattern, and proper interincisal relationship with normal occlusion. Cone-beam computed tomography was performed. 18 landmarks were digitized and 3D cephalometric measurements of overall facial features, skull, midface and mandible were performed and analyzed by means of proportions calculated from the landmarks. Male and female skulls were analyzed as well as subdivisions revealed by cluster analysis. The data showed that four subtypes of skulls were distinguishable with statistical significance (p< 0,05). A male and a female type subdivided in a brachiocephalic and dolichocephalic phenotype could be identified. For each type then a mean shape was calculated by a Procrustes transformation, which in turn was used to create four template skulls from a male and a female skull by means of a thin plate spline transformation. The normative data of the subtypes can individually serve as a guide for orthodontic surgery, especially helpful in 3D plan-ning and execution of craniofacial operations.

UAV has become powerful devices for both practitioners and researchers. In recent years, there has been a substantial growth in the usage of UAV for a wide range of applications in research and engineering. UAV are mostly utilized for image capturing techniques due to their time savings, low cost, minimum field work, and high precision. The purpose of this study is to generate an accurate and reliable 3D modelling process using UAVs photogrammetric technology; hence this study allows the techniques to evaluate the practicability of modelling and mapping inaccessible tunnels using images recorded by UAVs and photogrammetry. As a result, the approach was always employed to depict the true state of the place. This research incorporates three experiments. The first experiment is to build a 3D model using only one-directional light source and evaluate the accuracy of 3D photogrammetric model and conducted at the concrete tunnel. The second one is to build a 3D model of underground sewer tunnel using different light sources one-directional and omni-directional. The last experiment was to build 3D model using an UAV system which is developed based on first and second experiment’s result, evaluate an accuracy of 3D photogrammetric model and conducted at the tunnel named in the research as a “pedestrian tunnel. There is certain limitation in this study such as Adding a payload to a drone changed its weight distribution, which affected its stability. If the payload was not properly balanced, it caused the drone to fly unevenly, making it more difficult to control.

Regeneration of biological tissues in medicine is challenging, and 3D bioprinting offers an innovative way to create functional multicellular tissues. One common way in bioprinting is bioink which is one type of the cell-loaded hydrogel. For clinical application, however, the bioprinting still suffers from satisfactory performance, e.g. in vascularization, effective antibacterial, immunomodulation and regulation of collagen deposition. Many studies have incorporated different bioactive materials into the 3D printed scaffolds to optimize the bioprinting. Here, we review a variety of additives added to the 3D bioprinting hydrogel. The underlying mechanisms and methodology for biological regeneration are important and will provide useful basis for future research.

Abstract Natural disasters such as earthquakes have affected urban historical centers severely. Considering the limitations of the existing methods in conservation and preservation of these sensitive areas, and recent advances in technological devices and techniques such as GIS and 3D printers, this article aims to propose a new methodology utilizing available knowledge and resources. The authors of the present research propose an innovative, technological, and highly accurate method to assess the seismic vulnerability of historical contextures rectifying the existing obstacles and limitations. Through this methodology, the level of trial and error is substantially reduced and the output is stronger, more optimized and more conservative as compared with commonly used methods. Using high tech principles and theoretical foundations (i.e. sustainability principles) this method achieves updated analyses, practical plans, and economic optimization.

The repurposing of licenced drugs for use against COVID-19 is one of the most rapid ways to develop new and alternative therapeutic options to manage the ongoing pandemic. Given the approximately 8,000 licenced compounds available from Compounds Australia that can be screened, this paper demonstrates the utility of commercially-available ex vivo/3D airway and alveolar tissue models. These models are a closer representation of in vivo studies compared to in vitro models, but retain the benefits of rapid in vitro screening for drug efficacy. We demonstrate that several existing drugs appear to show anti-SARS-CoV-2 activity against both Delta and Omicron Variants of Concern in the airway model. In particular, fluvoxamine, as well as aprepitant, everolimus, and sirolimus have virus reduction efficacy comparable to the current standard of care (remdesivir, molnupiravir, nirmatrelvir). Whilst these results are encouraging, further testing and efficacy studies are required before clinical use can be considered.

The soft robot has many degrees of freedom, strong environmental adaptability and good human-computer interaction ability. As the end-effector of the soft robot, the soft gripper can grasp objects of different shapes without destructivity. Based on the theoretical analysis of the soft robot, the kinematics model of the flexible gripper and the theoretical model of the bending deformation of the air cavity were established. Accordingly, the relationship between the bending angle of the soft gripper and the air pressure was determined. Through the application of finite element software, the bending degree of pneumatic network multi-cavity soft gripper was simulated by finite element software, and the influence of structural parameters of soft actuator on bending deformation was determined. In addition, with the 3D technology conducting the printing of soft gripper fixtures and molds, the injection molding the actuator and the human-computer interaction interface controlling the movement of the gripper, the adaptability of the soft gripper in grasping object was verified. The result shows that the software gripper possesses good flexibility and can better grasp objects of different shapes.

3D city models integrate heterogeneous urban data from multiple sources in a unified geospatial representation, combining both semantics and geometry. Although in the last decades, they are predominantly used for visualization, today they are used in a large range of tasks related to exploration, analysis, and management across multiple domains. The complexity of urban processes and the diversity of urban environment bring challenges to the implementation of 3D city models. To address such challenges, this paper presents the development process of a 3D city model of a single neighborhood in Sofia city based on CityGML 2.0 standard. The model represents the buildings in LOD1 with a focus on CityGML features of related to the buildings like building part, terrain intersection curve and address. Similar building models of 18 cities provided as open datasets are explored and compared in order to extract good modeling practices. As a result, workflows for generation of 3D building models in LOD1 are elaborated and improvements in the feature modeling are proposed. Two options of building model are examined: modeling of a building as a single solid and modeling of a building with separate building parts. Finally, the possibilities for visualization of the model in popular platforms such as ArcGIS Pro and Cesium Ion are explored.

There is need to address the challenges of organ shortage, through development of tissues and organs with alternatives to those of the allograft-kind. This illustrates the quest behind novel biofabrication strategies such as 3D bio-printing, which is necessary to create artificial multi-cellular tissues/organs. Several findings have been reported in this review. First, the role of ECM components in tissue regenerative medicine is presented. Different ECM components such as collagen, gelatin, elastin, fibronectin, laminins and glycosaminoglycans are concisely examined for their tissue regenerative medicine applications. Next, current state of research on extrusion-based 3D bio-printing techniques and their limitations are reviewed. For example, we show that cell viability is still a challenge with extrusion, while the use of natural polymers such as collagen in improving composites’ mechanical properties is limited. Lastly, we examine unresolved research questions necessary to advance the present state of research in the field.

Cancer cachexia is a multifactorial syndrome that is identified by ongoing muscle atrophy, along with functional impairment, anorexia, weakness, fatigue, anemia, reduced tolerance to antitumor treatments. Thus, reducing the patients’ quality of life. Cachexia alone causes about 22-25% of cancer deaths. This review covers the symptoms, mediators, available treatment, and prospects of 3D bioprinting for cancer cachexia. Studies about cachexia have shown several factors that drive this disease – protein breakdown, inflammatory cytokines activation, and mitochondrial alteration. Even with proper nutrition, physical exercises, anti-inflammatory agents, chemotherapy, and grafting attempts, standard treatment has been unsuccessful for cachexia. But the use of 3D bioprinting shows much promise compared to conventional methods by attempting to fabricate 3D constructs mimicking the native muscle tissues. In this review, some 3D bioprinting techniques with their advantages and drawbacks, along with their achievements and challenges in in-vivo applications have been discussed. Constructs with neural integration or muscle-tendon units aim to repair muscle atrophy. But it is still difficult to properly bio-print these complex muscles. Although progress can be made by developing new bio-inks or 3D printers to fabricate high-resolution constructs. Using secondary data, this review study shows prospects of why 3D bioprinting can be a good alternate approach to fight cachexia.

Pollen analysis as a part of palynology deals with the morphological determination of pollen and spores. Different technologies with different resolutions varying from simple light microscopy to highly elaborate electron microscopy are used for the examination, depending on the area of application (e.g. sedimentology, melissopalynology, forensic palynology, etc.). To answer the question of whether laser scanning microscopy (LSM) can replace scanning electron microscopy (SEM) for the determination of pollen species, 168 species were examined using LSM. It was concluded that LSM is both efficient and easy to handle. After preparing the fresh pollen, a 3D laser scan takes 5-10 minutes and unlike using SEM, the pollen does not have to be sputtered or processed. The 3D scans can be measured quickly and easily with the integrated software and there were no observable artifacts. At magnifications up to 8545x, the image quality is comparable to that of a sputtered SEM sample whereas at higher magnifications, the SEM method is superior. Overall, pollen display by LSM is much less time consuming and more cost effective than with the SEM method.

The control of the three-dimensional (3D) polymer network structure is important for permselective materials when specific biomolecules detection is needed. Here we investigate conditions to obtain a tailored hydrogel network that combine both molecular filtering and molecular capture capabilities for biosensing applications. Along this line short oligonucleotide detection in a displacement assay is set within PEGDA hydrogels synthetized by UV radical photopolymerization. To provide insights on the molecular filter capability, diffusion studies of several probes (sulforhodamine G and dextrans) with different hydrodynamic radii were carried out using NMR technique. Moreover, fluorometric analyses of hybridization of DNA oligonucleotides inside PEGDA-hydrogels shed light on the mechanisms of recognition in 3D, highlighting that mesh size and crowding effect greatly impact of hybridization mechanism onto polymer network. Finally, we found the best probe density and diffusion transport conditions to allow the specific oligonucleotide capture and detection inside PEGDA-hydrogels for oligonucleotide detection and the filtering out of higher molecular weight molecules.

The maker movement has reached the optics labs, empowering researchers to actively create and modify microscope designs and imaging accessories. 3D printing has especially had a disruptive impact on the field, as it entails an accessible new approach in fabrication technologies, namely additive manufacturing, making prototyping in the lab available at low cost. Examples of this trend are taking advantage of the easy availability of 3D printing technology. For example, inexpensive microscopes for education have been designed, such as the FlyPi. Also, the highly complex robotic microscope OpenFlexure represents a clear desire for the democratisation of this technology. 3D printing facilitates new and powerful approaches to science and promotes collaboration between researchers, as 3D designs are easily shared. This holds the unique possibility to extend the open-access concept from knowledge to technology, allowing researchers from everywhere to use and extend model structures. Here we present a review of additive manufacturing applications in microscopy, guiding the user through this new and exciting technology and providing a starting point to anyone willing to employ this versatile and powerful new tool.

Fluorescence-linked immunosorbent assay (FLISA) is a commonly used, quantitative technique for detecting biochemical based on antigen–antibody binding reactions using a well-plate platform. With the developments in the manufacturing technology of microfluidic systems, FLISA can be implemented onto microfluidic disk platforms, which allows the detection of trace biochemical with high resolutions. Apart from requiring a lower proportion of reagent (1/10), this method also reduces the time required for the entire process to less than an hour. The incubation process involves antigen–antibody binding reactions as well as the binding of fluorogenic substrates to target proteins. The protocol for FLISA on a microfluidic platform necessitates the appropriate execution of liquid reagent movements during each step in order to ensure sufficient binding reactions. Herein, we propose a novel microfluidic disk comprising a 3D incubation chamber. Vascular endothelial growth factor as concentration with ng mL-1 is detected sequentially using a benchtop process employing this 3D microfluidic disk. The 3D microfluidic disk is implemented without requiring manual intervention or additional procedures for liquid control. During the incubation process, microbead movement is controlled through centrifugal force, generated due to disk rotation, and gravitational force via bead sedimentation on the sloped floor of the chamber.

Metal 3D printing technology is a promising manufacturing method, especially in the case of complex shapes. The quality of the printed product is still a challenging issue for mechanical applications. The anisotropy of the microstructure, imperfections, and residual stress are some of the issues that diminish the mechanical properties of the printed sample. The simulation could be used to investigate some technical details, and this research has tried to computationally study the metal 3D printing of austenitic stainless steel to address austenite microstructure and local yield strength. Two computational codes were developed in Visual basics 2015 to simulate the local heating/cooling curve and subsequent austenite microstructure. A stochastic computational code was developed to simulate austenite grain morphology based on calculated thermal history. Then Hall-Pitch equation was used to estimate the yield strength of the printed sample. These codes were used to simulate the effect of temperature of the printer’s chamber on microstructure and subsequent yield strength. The austenite grain topology is more columnar at a lower temperature. The percentage of the equiaxed zone will be increased at a higher chamber’s temperature. Almost a fully equiaxed austenite microstructure will be achieved at 800 C chamber’s temperature, but the last printed layer, which is columnar and can be removed by cutting then. The estimated local austenite grain size and the local yield strength in the equiaxed regions are in the range of 15 to 30 μm and 270 to 330 MPa at 800 C temperature of printer’s chamber, respectively.

Solar Insolation is the major contributor of earth’s radiation and energy budget. The insolation reaching the surface is a prime input for eco-physiological processes such as evapotranspiration and photosynthesis. Therefore, it is as critical component to assess bio-energy and bio-fuel resources. It is also a crucial input to crop simulation model for yield forecasting and its further applications in solar energy solutions. Although ground observations are better for accuracy purpose, they have challenges of maintenance, regular calibration and upkeeping etc. This call for the continuous spatio-temporal satellite based observations barring the acceptable accuracy. In case of INSAT3D/3DR, Bhattacharya et al. (2015) have derived the surface insolation product which is being used widely. We propose a method of improvement in this product. It is envisaged that a correction applied with the help of ground truth estimates may enhance the utilization of insolation products derived from INSAT3D/3DR datasets. In the present study, surface insolation product derived from INSAT 3D/3DR data at an interval of 30 minutes each (collectively 15 minutes interval) with 4 km spatial resolution was used for duration from May-2017 to Apr-2019 over Nagpur. Ground truth observations for same duration were carried out with CNR4, which were used to correct the INSAT 3D/3DR surface insolation product using the statistical best-fit method. Corrected INSAT 3D/3DR products are found correlating with the ground values well with differences of approximately < 1 W/m2. Best-fit parameters evolved in the present study uses only 2 years of simultaneous ground and satellite data which can be further improved by multi-year data base. We propose better utilization of INSAT 3D/3DR based surface insolation products in the assessment of solar resource mapping over Nagpur (and possibly other regions, such as Bhandara) with the help of best-fit parameters as assessed in the present study.

Dynamic thermogravimetric (TG) analysis under nitrogen environment was used to understand the thermal decomposition process of 3D printing filaments made of wood-filled polylactic acid (PLA)/starch blend. The characteristic temperatures and apparent activation energy (AAE) of the filaments with various starch contents were calculated with well-known kinetic models by Friedman, Flynn-Wall-Ozawa, Coats-Redfern and Kissinger. With the increased starch content in the filament, the onset thermal decomposition temperatures of the filaments decreased gradually from 272.4 to 155.1°C. The thermal degradation degree became smaller, and the transitional temperature interval became larger with increased starch proportion. The AAE values of the three types of filaments with different starch ratios varied between 97 kJ/mol and 114 kJ/mol, depending on material composition and method of calculation. The improved understanding of thermal decomposition behavior of PLA-starch-wood composites can help develop more biodegradable PLA/starch-based filaments for 3D printing.

Although conventional immunohistochemistry for neurotropic Rabies virus (RABV) usually shows a high preference for neurons, non-neuronal cells are also potential target cells and abortive infection of astrocytes is considered a main trigger of innate immunity in the CNS. While in vitro studies indicated differences between field and less virulent lab-adapted RABVs, a systematic and quantitative comparison of astrocyte tropism in vivo is lacking. Here, a recently developed solvent-based tissue clearing technique was used to measure the RABV cell tropism in infected brains. Immunofluorescence analysis of 1 mm-thick tissue slices enabled 3D segmentation and quantification of infection frequencies of astrocytes and neurons. Comparison of highly virulent street virus clones from fox, dog, and raccoon with three lab strains of intermediate and low virulence revealed remarkable differences in the ability to infect astrocytes in vivo. While all viruses and infection routes led to comparable neuron infection frequencies, striking differences were detected for the infection of astrocytes. Consistent and inoculation route-independent astrocyte infection by field viruses, together with route-dependent or undetectable astrocyte infection by lab-adapted or vaccine viruses strongly suggests a model in which the ability to establish productive astrocyte infection in vivo functionally distinguishes field and attenuated lab RABV strains.

Duplex Stainless Steels (DSS) and Superduplex Stainless Steels (SDSS) are an important class of stainless steels because they combine the benefits of austenite and ferrite phases, resulting in steels with better mechanical properties and higher corrosion resistance. Due to these characteristics are widely employed in various industries. However, the appearance of deleterious phases in their microstructure impairs the properties of DSS and SDSS. Among the deleterious phases, the main one is the sigma phase (σ), which can be nucleated when the steel is exposed to the temperature range between 650 °C and 900 °C, reducing its toughness and resistance to corrosion. In a previous work, Fonseca and collaborators used two descriptors of the microstructural path to analyze the formation of sigma phase (σ), SV, interfacial area per unit volume between sigma phase and austenite, and <λ>, mean chord length of sigma, both in function of the VV, volume fraction of sigma, known in the literature as microstructural partial path (MP). In this work, the contiguity ratio is applied for the first time to describe the microstructural path in the study of sigma phase precipitation in SDSS. The contiguity ratio showed that the distribution of the ferrite/sigma boundaries is homogeneous. Thus, it is reasonable to infer that one has a uniform distribution of sigma phase nuclei within the ferrite. About the kinetics of sigma phase formation, the DSS can be described by the classical JMAK equation, whereas for the SDSS, the kinetics tends to follow the Cahn model for grain edge nucleation. Finally, we present the 3D reconstruction of the sigma phase in SDSS. The results demonstrate that the sigma phase nucleates at the edges of the ferrite/austenite interfaces. Moreover, the sigma phase grows consuming the ferrite, but it is not fully interconnected.

Buildability, i.e. the ability of a deposited material bulk to retain its dimmensions under increasing load, is an inherent prerequisite for formwork-free digital construction (DC). Since DC processes are relatively new, no standard methods of characterization are available yet. The paper at hand presents practice-oriented buildabilty criteria by taking various process parameters and construction costs into consideration. In doing so, direct links between laboratory buildability tests and target applications are established. A systematic basis for calculating the time interval (TI) to be followed during laboratory testing is proposed for the full-width printing (FWP) and filament printing (FP) processes. The proposed approach is validated by applying it to a high-strength, printable, fine-grained concrete. Comparative analyses of FWP and FP revealed that to test the buildability of a material for FP processes, higher velocities of the printhead should be established for laboratory tests in comparison to those needed for FWP process, providing for equal construction rates.