Machine learning models facilitate the search for non-linear relationships when modeling hydrological processes, but they are equally effective for automation at the data preparation stage. The tasks whose automation was analyzed consisted in estimating changes in the roughness of a mountain streambed and the extent of floods from images. The Segment Anything Model (SAM) developed this year by Meta was used for this purpose. Images from many years from the Wielka Puszcza mountain stream located in the Polish Carpathians were used as the only input data. The model was not additionally trained for the described tasks. The model can be run in several modes, but the two most appropriate were used in this study. The first one is available in the form of a web application, while the second one is available in the form of a Jupyter notebook run in the Google Colab environment. Both methods do not require specialized knowledge and can be used by virtually any hydrologist. In the roughness estimation task, the average Intersection over Union (IoU) ranges from 0.55 for grass to 0.82 for shrubs/trees. Ultimately, it was possible to estimate the roughness coefficient of the mountain streambed between 0.027 and 0.059 based solely on image data. In the task of estimation of the flood extent, when selecting appropriate images, one can expect IoU at the level of at least 0.94, which seems to be an excellent result considering that SAM is a general-purpose segmentation model. It can therefore be concluded that SAM model can be a useful tool for a hydrologist.

This paper explores the application of machine learning techniques for automated object grasping. Current electronic prosthetics often require extensive training for users to gain fine motor control over the prosthetic fingers, hindering their usability and acceptance. To address this challenge, this paper proposes an automated method that leverages computer vision-based techniques and machine learning algorithms. In this study, three reinforcement learning algorithms, namely Soft Actor-Critic (SAC), Deep Q-Network (DQN), and Proximal Policy Optimization (PPO), are employed to train agents for automated grasping tasks. The results indicate that the SAC algorithm achieves the highest success rate of 99% among the three algorithms at just under 200,000 timesteps. This research also shows that object’s physical characteristics can affect the agent’s ability to learn an optimal policy. Moreover, the findings highlight the potential of the SAC algorithm in developing intelligent prosthetic hands with automatic object gripping capabilities.

This study proposes a method for image matching between infrared(IR)-RGB images using a deep learning network to estimate the deformation field. We propose a deformation field generator (DFG) that estimates the deformation field of the transformation matrix to match each pixel or IR image to the RGB image. DFG is a network that receives IR and RGB images as input; the output size is two channels and has the sample resolution as the input image. By warping the IR image through a grid-sampler that warps the image according to the value of the deformation field, we can obtain a warped IR image that matches the RGB image. Additionally, to check whether the warped IR image matched the RGB image, the masking images detecting the segmentation of objects were photographed in two images. Without directly comparing IR and RGB images, we proposed mask loss that warps the IR mask image through the deformation field and grid sampler and then compares the warped IR mask image with the RGB mask image. Mask loss solves the spatial similarity comparison problem with multi-modality images, such as IR and RGB images, by comparing the mask image with the same modality image as the mask image.

In Mexico, the incorporation of deaf people into education has been lacking since only 14% of the deaf population in the age group between 3 and 29 years access education with the support of a hearing aid. Additionally, those who have been incorporated frequently face inappropriate educational strategies which poorly develop the use of Mexican Sign Language (MSL) and therefore academical success and opportunities for insertion in the workplace are difficult. This research explores a novel mexican sign language lexicon video dataset containing the dynamical gestures most frequently used by MSL. Each gesture consists of a set of different versions of videos under uncontrolled conditions. MX-ITESO-100 data set is composed of a lexicon of 100 gestures and 5,000 videos from three participants with different grammatical elements. Additionally, the data set is evaluated in a two-step neural network model with an accuracy greater than 99%. and thus serves as a benchmark for future training of machine learning models in computer vision systems. Finally, this research provides an inclusive environment within society and organizations in particular for people with hearing impairment.

Mice are one of the frequently used animal models in science research whose behavioral characteristics can provide much valuable information in biology, neuroscience, and pharmacology. Nowadays, artificial intelligence is widely used in mice behavior analysis. Integrated AI systems such as ChatGPT and VisualGPT are already available, and we discuss the feasibility of MiceGPT to help researchers identify and classify mouse behavior more easily. We review the applications of mice behavior analysis, analyze the tasks of deep learning on these applications based on an AI pyramid, and finally summarize the AI approaches to solve these tasks. Based on these summaries, we propose three MiceGPT architectures to demonstrate the theoretical feasibility of MiceGPT.

Computer simulation relies on well-defined experimental supported theories, models, and numerical methods. Computer simulation is an alternative to fill the gaps where the experiment is pricy or limited in engineering. Computer simulation is a high-fidelity computational technique that can work as an engineering innovation tool to try imaginative ideas beyond the available technologies. The accuracy of current computer simulation results is reliable enough to accelerate innovation for new materials and mechanical technologies without experimental validation. So, we may need to urge relying on computer simulation results without any experimental validation to accelerate engineering innovations. In addition, using high-fidelity computer simulation for engineering innovation acceleration without validation will be promoted if it is credited as a new classification. This subject and a related justification's classification in engineering have been discussed.

Computer vision methods have shown to be effective in classifying garbage into recycling categories for waste processing, existing methods are costly, imprecise, and unclear. To tackle this issue, we introduce MWaste, a mobile application that uses computer vision and deep learning techniques to classify waste materials as trash, plastic, paper, metal, glass or cardboard. Its effectiveness was tested on various neural network architectures and real world images, achieving an average precision of 92% on the test set. This app can help combat climate change by enabling efficient waste processing and reducing the generation of greenhouse gases caused by incorrect waste disposal.

Intracortical microelectrodes that can be implanted have the ability to capture fast-changing neuron action potentials in the living brain. Despite this potential, many obstacles must still be overcome for reliable, long-term, high-quality recordings and accurate analysis of brain activity. These challenges include improving recording quality, enhancing recording stability, increasing recording capacity, and adding multi-functional features. One potential approach to enhance implantable microelectrodes involves the advancement of materials, refinement of implantation methodologies, and augmentation of the number of sites for recording. However, these challenges are still being actively researched, and advancements in microelectrode technology are underway. The difficulties with implantable microelectrodes are evaluated, and solutions are presented from different perspectives. The latest advancements in microelectrode technology are reviewed and condensed, and future possibilities are explored.

In this article, we report how we constructed a dataset that contains the responses to a survey designed for investigating the relationship that humans have with their smart devices. The dataset has been collected in May-July 2020 and is a sample of over 500 respondents of various different ethnicities and backgrounds. These data have been used for modelling the ways people relate to their devices using the notion of agency. However, the data can be used for complementing any study that intends to investigate a tool-mediated communication from the perspective of the users and via a variety of attitudes and expectations the users invest in their devices and in themselves as users. This article presents the survey items as well as some preliminary data insights. The data have been collected in English and answers have been anonymized in order to ensure GDPR compliance. They are stored in a .csv file containing the respondents’ answers to the questions.

The designs of two large arenas of different epochs are discussed, which are the most famous antique amphitheater the Roman Colosseum (Italy) and the modern Gazprom Arena stadium (St. Petersburg, Russia). 3D-computer models of the arenas have been built and evacuation of people has been simulated in the Sigma FS software (Russia). The arena designs are analyzed in terms of organizing pedestrian evacuation, a comparative analysis is made, and the specific characteristics affecting the evacuation time are established.

This code provides computational facilities to simulate current versus time during the charging of Li-ion cells at desire constant voltage by considering multiscale physical phenomena. This code only considers a powder of active materials (at microscale or nanoscale) and a small part of electrolyte around it as a half cell. Then it is extended to a complete cell by applying correct boundary conditions. This code is very useful by modifying code parameters to understand the effect of the complex shape of active materials powder (surface area and powder size), kind of electrolyte, and the applied voltages on the charging response of Li-ion cell. As a summary, a microscale approach to the design of Li-ion cells has been provided via this code.

If a clear and valid no-go for Einsteinian hidden parameters is real, it must in no way be possible to violate the CHSH with a local hidden variables based computer simulation. In the paper we show that with the use of a modied Glauber-Sudarshan method it is possible to violate the CHSH.The criterion value comes close to the quantum value and is approximately 2.4. The proof (POC) is presented with the use of an R computer program. The important snippets of the code are discussed and the complete code is presented in an appendix.

In this paper, our goal is to perform a virtual restoration of an ancient coin from its image. The present work is the first one to propose this problem, and it is motivated by two key promising applications. The first of these emerges from the recently recognised dependence of automatic image based coin type matching on the condition of the imaged coins; the algorithm introduced herein could be used as a pre-processing step, aimed at overcoming the aforementioned weakness. The second application concerns the utility both to professional and hobby numismatists of being able to visualise and study an ancient coin in a state closer to its original (minted) appearance. To address the conceptual problem at hand, we introduce a framework which comprises a deep learning based method using Generative Adversarial Networks, capable of learning the range of appearance variation of different semantic elements artistically depicted on coins, and a complementary algorithm used to collect, correctly label, and prepare for processing a large numbers of images (here 100,000) of ancient coins needed to facilitate the training of the aforementioned learning method. Empirical evaluation performed on a withheld subset of the data demonstrates extremely promising performance of the proposed methodology and shows that our algorithm correctly learns the spectra of appearance variation across different semantic elements, and despite the enormous variability present reconstructs the missing (damaged) detail while matching the surrounding semantic content and artistic style.

In this paper, the columnar supramolecular aggregates of photosensitive star-shaped azobenzenes with benzene-1,3,5-tricarboxamide core and azobenzene arms are analysed theoretically applying a combination of computer simulation techniques. Without a light stimulus, the trans-stars build one-dimensional columns of stacked molecules during the first stage of the noncovalent association. These columnar aggregates represent the structural elements of more complex experimentally observed morphologies -- fibers, spheres, gels and others. Upon UV light exposure, the azobenzene arms isomerise from thermodynamically stable planar trans- to a metastable kinked cis-state influencing the aggregate morphology. Here, we determine the most favourable mutual orientations of the \textit{trans}-stars in the stack in terms of (i) the pi-pi distance between the cores lengthwise the aggregate, (ii) the star slipped displacements and (iii) the rotation promoting the helical twist and chirality of the aggregate by calculating the binding energy diagrams using density functional theory. The model predictions are further compared with available experimental data. The intermolecular forces responsible for the stability of the stacks made of trans-azobenzene stars in crystals are quantified using Hirshfeld surface analysis. Finally, to characterize the self-assembly mechanism of such stars in solution, we calculate the hydrogen bond lengths, the normalized dipole moment and the binding energies as the functions of the columnar length using molecular dynamics trajectories, and conclude about the cooperative nature of this process.

A brain-computer interface for controlling elements commonly used at home is presented in this paper. It includes the electroencephalography device needed to acquire signals associated to the brain activity, the algorithms for artefact reduction and event classification, and the communication protocol.

Gesture-based recognition is one of the most intuitive methods for inputting information and is not subject to cumbersome operations. Recognition is performed on human's consecutive motion without reference to retrial or alternation by user. We propose a gesture recognition model with a mechanism for correcting recognition errors that operates interactively and is practical. We applied the model to a setting involving a manual grading task in order to verify its effectiveness. Our system, named GERMIC, consists of two major modules, namely, handwritten recognition and interactive correction. Recognition is materialized with image feature extraction and convolutional neural network. A mechanism for interactive correction is called on-demand by a user-based trigger. GERMIC monitors, track, and stores information on the user's grading task and generates output based on the recognition information collected. In contrast to conventional grading done manually, GERMIC significantly shortens the total time for completing the task by 24.7% and demonstrates the effectiveness of the model with interactive correction in two real world user environments.

This article analyzes some available bike mobile applications for smartphones as an alternative to bike computers (Cycle Computers or speedometer or speed sensors). We have records of a large number of MTB (Mountain Bike) datasets, 219 datasets were recorded on 4 different routes. These applications create maps and profiles from geographic data. Inputs can be in GPS data (tracks and waypoints), driving routes, street addresses, or simple coordinates. Most applications estimate fields such as speed, heading, slope, distance, VMG (velocity made good) and pace (cadence). However, it is necessary to calculate the relationship between cadence and power in pedaling so that cyclists know the appropriate moment to apply power to their legs to improve the torque. This paper shows tables, comparative graphs, and performance evaluation of biking routes in four different cycling mobile applications.

Purpose: The purpose of this study is to apply the Composite Radiographic Index modified (CRIm) in CBCT scans of patients with Medication related osteonecrosis of the jaws (MRONJ) in order to detect its validity, and corelate the radiologic findings with the clinical staging of the disease. Methods: This study included 43 patients with MRONJ diagnosis and CBCT scans performed in the School of Dentistry and approved by the Research Ethics Committee. Clinical staging for every patient (0-3) was provided according to AAOMS 2022 guidelines. In cases of patients with both jaws affected, each jaw was evaluated independently resulting to 52 CBCT scans. The 52 CBCT scans were assessed under standardized viewing conditions by 2 observers who evaluated independently the following 8 radiologic features: lytic changes, sclerosis, periosteal reaction, sequestration, non-healing extraction sockets and other findings (sinus implication, inferior alveolar canal involvement, jaw fracture). The CRIm index was constructed to assess the extent of osseous changes. The radiologic features were scored as absent (0), localized/single (1), extensive/multiple (2), yielding a theoretical range of 0–12. For statistical analysis Fisher’s exact test and Spearman’s correlation coefficient were performed. Results: A statistically significant association of clinical stage with lytic changes, sequestration and inferior alveolar canal involvement was found. Also, a statistically significant correlation of clinical stage with CRIm index classification was obtained. Conclusions: The CRIm index tends to increase as the clinical stages of MRONJ advance, suggesting a correlation between the clinical stage of MRONJ and the CRIm index.

Breast cancer is a global health concern, necessitating continuous advancements in diagnostic medical imaging technologies for early detection and improvement of treatment. This paper presents an overview of the past, present and future of breast cancer imaging using light and some results from the current studies. The paper specifically presents the role of Diffuse Optical Tomography (DOT) in breast cancer imaging. Conventional methods, such as X-ray mammography, face limitations. Diffuse Optical Tomography, a non-invasive light-based imaging modality can provide quantitative descriptive and architectural information about breast tissue. The paper discusses the key challenges and recent developments in breast cancer imaging using DOT to overcome some key challenges. This paper aims to contribute to the understanding of the evolving technological landscape in breast cancer imaging using light for improving early detection and patient outcomes.

CBCT significantly impacts dental procedures and has brought significant reforms in our approach to diagnosis & treatment planning despite its limitations in differentiating soft tissues. It is an excellent imaging modality and quickly identifies sinus opacification and provides valuable in-sight into paranasal sinus pathologies with considerably lower radiation exposure. The present study aimed to investigate the occurrence of maxillary sinus abnormalities in CBCT scans, identify the frequency, type, and location of these findings, and find the correlation between the distance of periapical lesions and radiographic changes in the maxillary sinus. Two examiners independently evaluated 117 patients to diagnose and classify the cases into different abnormality subtypes. The periapical lesions most closely related to the sinus were recorded. The diameters of the left and right maxillary sinus ostium and the distance of the ostium's lower border to the sinus's osseous floor were recorded. The findings were correlated with the age and gender of these patients. The present study revealed that sixty-one patients were diagnosed with mucosal thickening (52.1%). The sinus wall most affected by mucosal thickening was the maxillary sinus floor, followed by the medial and lateral walls. Of 19 patients with periapical lesions, 15 had maxillary sinus mucosal thickening and was statistically significant (p=0.004). The high occurrence of abnormalities in the maxillary sinus emphasizes the importance for the radiologist to comprehensively interpret the whole volume acquired in CBCT images, including the entire sinus. Incidental findings may be considered in the individual clinical context of signs and symptoms, reducing the risk of overes-timating the real impact of radiographic findings.

Coronary angiography, long considered the gold standard for coronary imaging, faces limitations in assessing coronary vessel wall anatomy and guiding percutaneous coronary intervention (PCI). Despite its prevalence, studies have demonstrated that it is suboptimal in estimating the severity of coronary disease and physiologic significance of stenosis. Intracoronary imaging techniques, such as intravascular ultrasound (IVUS) and optical coherence tomography (OCT), offer promising alternatives to overcome these limitations. This review delves into the nuances of IVUS and OCT, highlighting their strengths and limitations as adjuncts to PCI. IVUS, utilizing ultrasound technology, and OCT, based on near-infrared light, each provide unique insights into coronary pathology. They differ in terms of temporal and spatial resolution, influencing their capabilities in plaque characterization and vessel assessment. The discussion navigates their historical evolution, technical specifications, and clinical utility. Meta-analyses and adjusted observational studies suggest that both IVUS and OCT-guided PCI correlate with reduced cardiovascular risks compared to angiographic guidance alone. While IVUS has demonstrated consistent benefits in terms of clinical outcomes, the evidence supporting OCT is less robust. However, the utilization of these imaging modalities remains variable across regions, with increasing adoption in recent years, particularly in IVUS-guided PCIs. Intravascular ultrasound's journey from early motion detection to current high-resolution mechanical systems is traced, including improvements in catheter size and compatibility. On the other hand, optical coherence tomography has advanced significantly, utilizing near infrared light to achieve unparalleled resolutions, albeit requiring temporary blood clearance for optimal imaging. In conclusion, IVUS and OCT offer valuable insights into coronary pathophysiology and guide interventions with improved precision compared to traditional angiography. While IVUS remains more extensively utilized, OCT's growing potential is underscored by advancements in technology, culminating in enhanced imaging capabilities. Both modalities demonstrate comparable clinical outcomes, emphasizing the need for tailored imaging choices based on individual clinical scenarios. The continued refinement and broader integration of intravascular imaging are expected to play a pivotal role in optimizing coronary interventions and patient outcomes.

COVID-19 generated a scenario for global health with multiple systemic impairments. This retrospective study evaluated the clinical, radiological, and pulmonary functional evolution in 302 post-COVID-19 patients. Regarding post-COVID-19 pulmonary symptoms, dry cough, dyspnea, and chest pain were the most frequent. Of the associated comorbidities, asthma was more frequent (23.5%). Chest Tomography (CT) initially showed a mean pulmonary involvement of 69.7%, and the evaluation in the subsequent months showed an improvement in the evolutionary image, and with less than six months post-pathology, there was a commitment of 37 .7%, from six to twelve months, 20% and after 12 months, 9.9%. And as for most of the sample, 50.3% of the patients presented CT normalization in less than six months after infection, 23% normalized between six and twelve months, and 5.2% normalized the images after twelve months, with one remaining. Percentage of 17.3% who maintained post-COVID-19 pulmonary residual sequelae. Regarding spirometry, in less than six months after the pathology, 59.3% of the patients already showed a regular exam; 12.3% normalized their function within six to twelve months, and 6.3% concluded a normal exam after twelve months of post-pathology evaluation. Only 3.6% of the patients still showed some alteration in this period.

(1) Background: To identify the association between the presence or absence of raphe and aortic valve dysfunction as well as the presence of aortopathy in patients with bicuspid aortic valve (BAV); (2) Methods: This retrospective study enrolled 312 participants (mean [SD] age, 52.7 [14.3] years; 227 men [72.8%]) with BAV. The BAVs were divided into those with presence (raphe+) or absence (raphe-) of raphe. Valvular function was classified as normal, aortic regurgitation (AR), or aortic stenosis (AS) using TTE. The pattern of BAV aortopathy was determined by the presence of dilatation at the sinus of Valsalva and the middle ascending aorta using CCT.; (3) Results: BAVs with raphe+ had a higher prevalence of AR (148 [79.5%] vs. 48 [37.8%], P < .001) but a lower prevalence of AS (90 [48.6%] vs. 99 [78.0%], P < .001) compared with those with raphe-. The types of BAV aortopathy were significantly different (P = 0.021) according to those with BAV-raphe+ and BAV-raphe-.; (4) Conclusions: The presence of a raphe was significantly associated with a higher prevalence of AR but a lower prevalence of AS and combined dilatation of the aortic root and middle ascending aorta. The presence of raphe was an independent determinant of AR.

Objective: To evaluate two different DECT postprocessing protocols for detection of MSU deposits in foot tendons of cadavers with verification by polarizing light microscopy as gold standard.Material and Methods: A total of 40 embalmed cadavers (15 male; 25 female; median age, 82 years; mean, 80 years; range, 52 - 99; SD ± 10.9) underwent DECT to assess MSU deposits in foot tendons.Two postprocessing DECT protocols with different Hounsfield unit (HU) thresholds 150/500 (=established) versus 120/500 (= modified) HU were applied to dual source acquisition with 80 kV for tube A and 140 kV for tube B.Six fresh cadavers (4 male; 2 female; median age, 78; mean, 78,5; range 61 - 95 ) were examined by DECT. Tendon dissection of 2/6 fresh cadavers with positive DECT 120 and negative DECT 150 studies were used to verify MSU deposits by polarizing light microscopy.Results: The tibialis anterior tendon was found positive in 57.5%/100% (DECT 150/120), peroneus tendon in 35%/100%, achilles tendon in 25%/90%, flexor halluces longus tendon in 10%/100%, and tibialis posterior tendon in 12.5%/97.5%. DECT 120 resulted in increased tendon MSU deposit detection, when DECT 150 was negative, with an overall agreement between DECT 150 and DECT 120 of 80 % (P = 0.013). Polarizing light microscope confirmed MSU deposits detected only by DECT 120 in tibialis anterior, achilles, flexor halluces longus and peroneal tendons.Conclusion: The DECT 120 protocol showed a higher sensitivity when compared to DECT 150.

: Background: The thymus gland is the first lymphoid organ formed to regulate a newborn's immunity. It reaches its maximum size during puberty, after which it undergoes an atrophic procedure called involution, but its ability to grow again in response to some stresses, such as infections, neoplasia, surgeries, chemotherapy, and radiotherapy is maintained. There is not any comprehensive study on computed tomographic features of thymus gland in dogs. So, the goal of the present study is to achieve some information about thymus gland using computed tomography as a non-invasive method. Methods: One hundred and fifty dogs classified in 5 age groups and 2 breed groups were entered to this study and the thymus gland was evaluated using 2-slice computed tomography machine. The inclusion criteria for the present study were having normal complete blood count, plain and post-contrast CT scan examination of thoracic region and no history of neoplasia, chemotherapy or radiotherapy. The visibility, density, enhancement, grade, size, volume, shape, borders and lateralization of the thymus were evaluated and statistical analysis were performed. The effect of obesity on thymic grade and volume were also investigated. Results: The visibility, density, dorsal length, volume and grade decreased with increasing age. The thymic shape and lateralization were mostly wedge-shaped and left sided respectively. The borders became concave with aging and increasing body fat content caused to increase fatty degeneration of thymus. Conclusions: Declining of thymic density, grade, size and volume with aging was related to thymic involution and fatty degeneration was accelerated by increasing body fat content. Females and Males were different only in thymic shape and small and large breeds were different only in thymic volume. The thymus was visible in some geriatric dogs with no underlying disease. We hope that the present work can be used by radiologists in reading thoracic computed tomography but investigation of thymic characteristics in dogs with neoplasia and history of chemotherapy, radiotherapy and thoracic surgeries can complete this study.

The optical properties and physiology of biological tissue, as well as how near-infrared (NIR) light interacts with the tissue, both play a significant role in interpreting the tissue probing optical measurements, and in solving the inverse problem of near-infrared spectroscopy (NIRS)-based medical imaging modalities such as diffuse optical tomography and functional near-infrared spectroscopy. This paper discusses the optical properties of tissue, specifically in the NIR wavelength range, which influence NIRS measurements in NIRS-based medical imaging. There is an easy-to-understand explanation given in this paper of the NIR light-tissue interaction phenomenon. The mathematical explanation, the processes involved in the interaction, and the rationale for a few approximations are described. Various types of chromophores present in the tissue, their composition in the tissue, and how these chromophores overall affect the scattering and absorption of NIR light are presented. The absorption spectra of these chromophores are shown. Finally, the paper concludes with the author’s perspective on two NIRS-based medical imaging modalities, diffuse optical tomography, and functional near-infrared spectroscopy.

In the field of 18F-chemistry for the development of radiopharmaceuticals for positron emission tomography (PET), various labeling strategies by the use of prosthetic groups have been im-plemented, including chemoselective 18F-labeling of biomolecules. Among those, chemoselec-tive 18F-fluoroglycosylation methods focus on the sweetening of pharmaceutical radiochemistry by offering a highly valuable tool for the synthesis of 18F-glycoconjugates with suitable in vivo properties for PET imaging studies. A previous review covered the various 18F-fluoroglycosylation methods that have been developed and applied as of 2014 [Maschauer and Prante, BioMed. Res. Int. 2014, 214748]. This paper is an updated review, providing the recent progress in 18F-fluoroglycosylation reactions and the preclinical application of 18F-glycoconjugates, including small molecules, peptides, and high-molecular-weight proteins.

Tomography based on cosmic muon absorption is a rising technique because of its versatility and its consolidation as geophysics tool over the past decade. It allows to address major societal issues such as long-term stability of natural and man-made large infrastructures or sustainable underwater management. Traditionally, muon trackers consist of hodoscopes or multilayer detectors. For applications with challenging available volumes or wide field of view required, a thin time projection chamber (TPC) associated with a Micromegas readout plane can provide a good tradeoff between compactness and performance. This paper details the design of such a TPC aiming at maximizing primary signal and minimizing track reconstruction artifacts. The results of the measurements performed during a case study addressing the aforementioned applications are discussed. The current works lines and perspectives of the project are also presented.

The paper proposes a novel methodology for the stabilization of shallow foundations, with a simplified model combined with 3D Electrical resistivity tomography (ERT-3D) and conso- lidation injections. To determine its usefulness, the method has been applied in a case located in Estepona (southern Spain). The chosen tomography model is the dipole-dipole configuration, with an optimized distance between electrodes of 0.80 m for a better visualization of the foundation subsoil; with this parameterization, a total of 72 electrodes were installed in the analyzed case. In this work, the depth of the anomaly in the building's supporting subsoil was detected ranging from 2.00 m to 3.90 m deep. The study also delineates areas of high resistivity variations (50-1,000 Ω m) in the middle and eastern end of the field. These data have been validated and corroborated with a field campaign. The results of the ERT-3D monitoring are presented, once the investment data has been processed with the RES3DINV software, from the beginning to the end of the stabilization intervention. The novelty occurs with the interaction between the tomography and the foundation consolidation injections, until the final stabilization; very useful methodology in case of emergency consolidation, where there is a need to minimize damage to the building. Thus, people using this combined system; will be able to practically solve the initial anomalies of the subsoil that caused the damages, in a non-invasive way, considerably lowering the value of the resistivities.

Crystallization is a significant procedure in the manufacturing of many pharmaceutical and solid food products. In-situ Electrical Resistance Tomography (ERT) is a novel Process Analytical Tool (PAT) to provide a cheap and quick way to test, visualize, and evaluate the progress of crystallization processes. In this work, the spatial accuracy of the non-conductive phantoms in low conductivity solutions was evaluated. Gauss-Newton, Linear Back Projection, and iterative Total Variation reconstruction algorithms were used to compare the phantom reconstructions for tap water, industrial-grade saturated sucrose solution, and demineralized water. Cylindrical phantom measuring 10 mm in diameter and a cross-section area of 1.5 % of the total beaker area was detected at the center of the beaker. Two phantoms with a 10 mm diameter were visualized separately in non-central locations. The quantitative evaluations were done for the phantoms with radii ranging from 10 mm to 50 mm in demineralized water. Multiple factors such as ERT device and sensor development, FEM mesh density and simulations, image reconstruction algorithms, number of iterations, segmentation methods, and morphological image processing methods were discussed and analyzed to achieve spatial accuracy. The development of ERT imaging modality for the purpose of monitoring crystallization in low conductivity solutions was performed satisfactorily.

Multiple Myeloma (MM) is the second most common type of hematological disease and, although it is rare among patients under 40 years of age, its incidence rises in elderly subject. MM manifestations are usually known with the abbreviation CRAB (hyperCalcemia, Renal failure, Anaemia, and lytic Bone lesions). In particular, the extent of the bone disease is negatively related to a decreased patients’ quality of life and, in general, bone disease in MM increases both morbidity and mortality. The detection of lytic bone lesions on imaging, especially CT and MRI, is becoming crucial from the clinical viewpoint to separate asymptomatic from symptomatic MM patients and the detection of focal lytic lesion in these imaging data is becoming relevant even when no clinical symptoms are present. Therefore, radiology is pivotal in the staging and accurate management of patients with MM even in early phases of the disease. In this review we describe the opportunities offered by quantitative imaging and radiomics in multiple myeloma. At present time there is still high variability in the choice between various imaging methods to study MM patients and high variability in image interpretation with suboptimal agreement among readers even in tertiary centres. Therefore, the potential of medical imaging for patients affected by MM is still to be completely unveiled. In the next years, new insights to study MM with medical imaging will derive from artificial intelligence (AI) and radiomics usage in different bone lesions and from the wide implementations of quantitative methods to report CT and MRI. Eventually, medical imaging data can be integrated with the patient's outcomes with the purpose to find radiological biomarkers for predicting the disease prognostic flow and its therapeutic response.

Air filtration mechanisms in the composite filter media used in practical applications are important and challenging to understand because the component fibers could have various size scales and morphologies. In this work, a three-dimensional digital model of nanofiber-based filter media was reconstructed for the first time based on the X-ray tomography data for the cellulose substrate and the Focused Ion Beam-Scanning Electron Microscope (FIB-SEM) image analysis for the several microns thick (3.82-7.90 μm) electrospun polyvinylidene fluoride (PVDF) nanofiber membrane. Besides the high-resolution model where the details of the fibrous structures were fully resolved, another low-resolution model with approximated unresolved structures was also established. Filtration simulations utilizing these models were conducted considering the drag force, Brownian diffusion and aerodynamic slip. The simulated filtration efficiencies agreed well with the experiments for particles of 70-400 nm, including the most penetrating particle size (MPPS, 100-200 nm). Moreover, the structure-resolved models had higher accuracy but higher computational costs, while the unresolved simulations saved much running time but over-predicted the filtration efficiency, especially for smaller particles (<100 nm). Our study presents a comprehensive strategy for investigating the composite filter media with multiscale complex structures using a combination of advanced characterization technologies and modular simulation models.

This article offers an overview of congenital and acquired vascular anomalies involving the portal venous system in dogs and cats, as determined by multidetector-row computed tomography angiography. Congenital absence of the portal vein, portal vein hypoplasia, portal vein thrombosis and portal collaterals are described. Portal collaterals are further discussed as high- and low-flow connections, and categorized in hepatic arterioportal malformation, arteriovenous fistula, end-to-side and side-to-side congenital portosystemic shunts, acquired portosystemic shunts, cavoportal and porto-portal collaterals. Knowledge of different portal system anomalies helps understand the underlying physiopathological mechanism and is essential for surgical and interventional approaches.

The Square Kilometre Array (SKA) will be both the largest radio telescope ever constructed and the largest Big Data project in the known Universe. The first phase of the project will generate on the order of 5 zettabytes of data per year. A critical task for the SKA will be its ability to process data for science, which will need to be conducted by science pipelines. Together with polarization data from the LOFAR Multifrequency Snapshot Sky Survey (MSSS), we have been developing a realistic SKA-like science pipeline that can handle the large data volumes generated by LOFAR at 150 MHz. The pipeline uses task-based parallelism to image, detect sources, and perform Faraday Tomography across the entire LOFAR sky. The project thereby provides a unique opportunity to contribute to the technological development of the SKA telescope, while simultaneously enabling cutting-edge scientific results. In this paper, we provide an update on current efforts to develop a science pipeline that can enable tight constraints on the magnetised large-scale structure of the Universe.

The technique of Faraday tomography is a key tool for the study of magnetised plasmas in the new era of broadband radio polarisation observations. In particular, observations at metre-wavelengths provide significantly better Faraday depth accuracies compared to traditional cm-wavelength observations. However, the effect of Faraday depolarisation makes the polarised signal very challenging to detect at metre wavelengths (MHz frequencies). In this work, Faraday tomography is used to characterise the Faraday rotation properties of polarised sources found in data from the LOFAR Two-Metre Sky Survey (LoTSS). Of the 76 extragalactic polarised sources analysed here, we find that all host a radio-loud AGN. The majority of the sources (∼64%) are large FRII radio galaxies with a median projected linear size of 710 kpc and median radio luminosity at 144 MHz of 4 × 10^26 W/Hz. In several cases, both hotspots are detected in polarisation at an angular resolution of ∼20". One such case allowed a study of intergalactic magnetic fields on scales of 3.4 Mpc. Other detected source types include an FRI radio galaxy and at least 8 blazars. Most sources display simple Faraday spectra, however, we highlight one blazar that displays a complex Faraday spectrum, with two close peaks in the Faraday dispersion function.

It is important for researchers in material domain to reconstruct and visualize the microstructure of alloy, which helps discover morphologies and properties that can only be found in three dimensional and microscopic space. However, because of the limitation of state-of-the-art sensors, the internal microstructure of the material is not easy to obtain. In this paper, a novel automatic 3D reconstruction method is proposed using diffraction contrast tomography technology to capture the 3D microstructure of Al-La alloy. The pipeline of the proposed method starts from the imaging of Al-La alloy with the LabDCT technique from Carl Zeiss AG, which produces a sequence of 2D microstructure sections. Then, a segmentation algorithm based on superpixel and lifted multicut is proposed to extract the 2D microstructure in an image section. Finally, 2D segmentations are joined together to reconstruct and visulize the 3D microstructure. As a result, a novel morphology of Al-La alloy is recovered with both dendrite and lamellar morphologies. The proposed method has the advantage of the ability to losslessly recover the internal microstructure.

Attempts to use computers to aid in the detection of breast malignancies date back more than 20 years. Despite significant interest and investment, this has historically led to minimal or no significant improvement in performance and outcomes with traditional computer aided detection. However, recent advances in artificial intelligence and machine learning are now starting to deliver on the promise of improved performance. There are at present more than 20 FDA approved AI applications for breast imaging, but adoption and utilization are widely variable and overall low. Breast imaging is unique and has aspects that create both opportunities and challenges for AI development and implementation. Breast cancer screening programs worldwide rely on screening mammography to reduce the morbidity and mortality of breast cancer and many of the most exciting research and available AI applications focus on cancer detection for mammography. There are however multiple additional potential applications for AI in breast imaging including decision support, risk assessment, breast density quantitation, workflow and triage, quality evaluation, response to neoadjuvant chemotherapy assessment, and image enhancement. In this review the current status, availability, and future directions of investigation of these applications are discussed, as well as the opportunities and barriers to more widespread utilization.

In the digital age, Artificial Intelligence (AI) is emerging as a transformative force in various sectors, in-cluding medicine. This article explores the potential of AI, akin to the magical genie of Aladdin's lamp, particularly within thoracic surgery and lung cancer management. It examines AI applications like ma-chine learning and deep learning in achieving more precise diagnoses, preoperative risk assessment, and improved surgical outcomes. The challenges and advancements in AI integration, especially in computer vision and multi-modal models, are discussed alongside their impact on robotic surgery and operating room management. Despite its transformative potential, implementing AI in medicine faces challenges regarding data scarcity, interpretability issues, and ethical concerns. Collaboration between AI and medi-cal communities is essential to address these challenges and unlock the full potential of AI in revolution-izing clinical practice. This article underscores the importance of further research and interdisciplinary collaboration to ensure the safe and effective deployment of AI in real-world clinical settings.

This research aims to introduce a model, SectraBank, designed to mitigate cyber fraud attacks, specifically targeting SIM Swapping and Fake App schemes in mobile banking users. A quantitative methodology with an experimental design was meticulously employed to examine the rise of cyber fraud within mobile banking. The study involved a sample of 100 professionals with advanced knowledge in Information and Communication Technologies (ICTs). Surveys were utilized to measure awareness of threats and perceptions of security before and after the implementation of the proposed model. SectraBank leverages unique user identifiers such as fingerprint authentication and the International Mobile Equipment Identity (IMEI) number, in addition to geolocation and One Time Passwords (OTP) for validating electronic transactions in mobile banking. The effectiveness of the proposed model was notable, achieving a 96.1% efficacy rate in mitigating Fake App attacks and a 90.2% success rate in countering SIM Swapping attacks. These findings underscore the potential of SectraBank as a robust solution to enhance cybersecurity measures in the realm of mobile banking.

Use of MS Excel as a platform for teaching simple iterative solution of partial differential equations runs into issues of reliability of the computation because of the large number of calculations required. This article documents the problem and an empirical solution. The cause of this unreliability was found by detailed examination of the numerical results from three simultaneous iterations. Computers of several types from different manufacturers were found to fail occasionally in updating variables in the numerical iteration. A simple work-around is suggested and was tested on several platforms.

The production of high-quality castings without foundry defects at minimal production costs is a constant priority for foundries. Innovation and optimization of production processes are key to achieving this goal. Computer simulation of foundry processes offers a modern alternative to expensive and time-consuming experiments in real foundries and provides a reliable representation and analysis of casting and solidification processes. A detailed analysis of the casting and solidification simulation results allows the prediction of various risks that can cause defects in cast castings, thereby reducing their quality and, last but not least, the cost of their production. The paper deals with the analysis of a computer simulation of the casting of a brake disc in the Slovak foundry. This brake disc has had shrinkages and micro shrinkages that reduce the internal quality of the casting. These defects occurred in the ribs in the upper part of the casting under the feeders. A computer simulation of the casting and solidification of this casting was made according to real conditions. It turned out that the designed ingate system with a system of feeders was not sufficient to eliminate emerging defects. A new layout of the feeders was proposed, which ultimately eliminated the occurrence of defects based on the results of computer simulation. The input parameters were set to be as close as possible to the actual needs of the foundry. 3D models of the assemblies were designed in SolidWorks CAD software, and filling and solidification simulations were performed using the NovaFlow &amp; Solid CV 4.6r42 simulation program.

This paper introduces an innovative approach to lipreading, leveraging a web application designed to generate subtitles for videos where the speaker's mouth is visible and a comprehensive literature review that precedes the discussion, encompassing a thorough examination of various lipreading methods employed over the past decade. Our method employs a powerful deep learning model, featuring a 3D-convolution network and bidirectional LSTM, enabling accurate sentence-level predictions based solely on visual lip movements. With an impressive accuracy of 97%, our model is trained using pre-segmented lips regions, transformed into animated GIFs for effective pre-training. This work stands as a significant contribution to the evolving landscape of lipreading research, offering a practical and accurate solution for real-world applications.

Commonly, professors, students and researchers from universities around the world use software distributed under a license agreement for computer simulation purposes, which requires a computer with considerable hardware capabilities. Consequently, this implies a high cost to conduct simulations that require implementing numerical methods in all areas of engineering, particularly in the field of robotics and nonlinear control. This paper presents the design and results analysis of a low-cost and open-source frugal computer simulation tool with applications to robotic nonlinear control, for instance, for numerical simulations of manipulator robot control based on dynamic models. Using a single board minicomputer with with reduced computing power, Raspberry Pi, together with free software, GNU-Octave, trajectory tracking control simulations in the joint space of a Selective Conformal Assembly Robot Arm (SCARA) are achieved by solving a system of nonlinear differential equations, represented in matrix form, which includes the control law and the system model. The results of the proposed alternative are compared by running the same simulation code on a laptop computer using MATLAB and GNU Octave, which show minimal deviations and reasonable time complexity. Moreover, considering the frugality curve calculated for this approach, in addition to the low acquisition cost of the simulation software tool, it would allow the creation of a simulation laboratory in some universities with budgetary constraints for educational and research purposes.

Macrophytes and seagrasses play a crucial role with a variety of the functions in the marine ecosystem and respond synchronized-promptly to the changing climate, followed by ecological status. Monitoring of the seagrasses was one of the paramount topics at the marine environment. One of the fast monitoring techniques is the vegetation acoustics with the advantages compared to the other remote sensing techniques. The acoustic method alone is ambitious to sea-truth identities of the backscatterers at the sea. Therefore, a package of computer programs was developed to identify, estimate leaf biometrics (leaf length and biomass) of one of the common seagrasses, Posidonia oceanica. Some troubleshooting in the acoustical data were fixed and then solved to reach the estimates regarding to the matters encountered for the vegetation as well as fisheries and plankton acoustics. One of the trouble was the “Lost” bottom which occurred during the data collection and post-processing due to occurrence of the acoustical noises, reverberations, interferences and intense scatterers suchlike fish schools. Another problem to remove was the occurrence as studying the near-bottom echoes belonging to submerged vegetations such as seagrasses, followed by spurious echoes. Last one was recognition of the seagrass to estimate leaf length and biomass calibrating the sheaths/vertical rhizome of the seagrass and establishing relationships between acoustical units and biometrics, respectively. As a consequence, an autonomous package of the code written in language MatLab was developed to perform all processes, and the name of the package was abbreviated as POSIBIOM, POSIdonia BIOMass. This study presented the algorithms, methodology, acoustics-biometrics relation, and mapping of the biometrics for the first time, and discussed advantages and disadvantages of the package compared to the software purposed for the bottom types, habitat and vegetation acoustic. The future studies were recommended to improve the package.

The point cloud is a form of three-dimensional data that comprises various detailed features at multiple scales. Due to this characteristic and its irregularity, point cloud analysis based on deep learning is challenging. While previous works utilize the sampling-grouping operation of PointNet++ for feature description and then explore geometry by means of sophisticated feature extractors or deep networks, such operations fail to describe multi-scale features effectively. Additionally, these techniques have led to performance saturation. And it is difficult for standard MLPs to directly "mine" point cloud. To address above problems, we propose the Detail Activation (DA) module, which encodes data based on Fourier transform after sampling and grouping. We activate the channels at different frequency levels from low to high in the DA module to gradually recover finer point cloud details. As training progresses, the proposed Point-MDA can uncover local and global geometries of point cloud progressively. Our experiments show that Point-MDA achieves superior classification accuracy, outperforming PointNet++ by 3.3% and 7.9% in terms of overall accuracy on the ModelNet40 and ScanObjectNN dataset, respectively. Furthermore, it accomplishes this without employing complicated operations, while exploring the full potential of PointNet++.

In the realm of computer vision, semantic segmentation is the task of recognizing objects in images at the pixel level. This is done by performing a classification of each pixel. The task is complex and requires sophisticated skills and knowledge about the context to identify objects’ boundaries. The importance of semantic segmentation in many domains is undisputed. In medical diagnostics, it simplifies the early detection of pathologies, thus mitigating the possible consequences. In this work, we provide a review of the literature on deep ensemble learning models for polyp segmentation and we develop new ensembles based on convolutional neural networks and transformers. The development of an effective ensemble entails ensuring diversity between its components. To this end, we combine different models (HarDNet-MSEG, Polyp-PVT, and HSNet) trained with different data augmentation techniques, optimization methods, and learning rates, which we experimentally demonstrate to be useful to form a better ensemble. Most importantly, we introduce a new method to obtain the segmentation mask which is more suitable for combining transformers in an ensemble. In our extensive experimental evaluation, the proposed ensembles exhibit state-of-the-art performance.

A single paragraph of about 200 words maximum. For research articles, abstracts should give a pertinent overview of the work. We strongly encourage authors to use the following style of structured abstracts, but without headings: (1) Background: place the question addressed in a broad context and highlight the purpose of the study; (2) Methods: describe briefly the main methods or treatments applied; (3) Results: summarize the article’s main findings; (4) Conclusions: indicate the main conclusions or interpretations. The abstract should be an objective representation of the article, it must not contain results which are not presented and substantiated in the main text and should not exaggerate the main conclusions.

Objective A trained T1 class Convolutional Neural Network (CNN) model will be used to examine its ability to successfully identify motor imagery when fed pre-processed electroencephalography (EEG) data. In theory, and if the model has been trained accurately, it should be able to identify a class and label it accordingly. The CNN model will then be restored and used to try and identify the same class of motor imagery data using much smaller sampled data in an attempt to simulate live data. Approach PyCharm, a Python platform, will be used to house and process the CNN. The raw data used for the training of the CNN will be sourced from the PhysioBank website. The EEG signal data will then be pre-processed using Brainstorm software that is a toolbox used in conjunction with MATLAB. The sample data used to validate and test the trained CNN, will be also be extracted from Brainstorm but in a much smaller size compared to the training data which is comprised of thousands of images. The sample size would be comparable to a person wearing a Brain Computer Interface (BCI), offering approximately 20 seconds of motor imagery signal data. Results The raw EEG data was successfully extracted and pre-processed. The deep learning model was trained using the extracted image data along with their corresponding labels. After training, it was able to accurately identify the T1 class label at 100 percent. The python coding was then modified to restore the trained model and feed it test sample data in which it was found to recognise 6 out of 10 lines of T1 signal image data. The result suggested that the initial training of the model required a different, more varying approach, so that it would be able to detect varying sample signal image data. The outcome of which could mean that the model could be used in applications for multiple patients wearing the same BCI hardware to control a device or interface.

Recent progress in microfabrication technique allowed the rapid development of neural implants. They are getting categorized as effective tools for clinical practice, especially to treat traumatic and neurodegenerative disorders. Microelectrode arrays already have been used in numerous neural interface devices. Basically, almost all neural implants have been developed based on BCI (Brain Computer Interface) system. When BCI system falls under invasive technique, it is referred as BMI or Brain Machine Interface. BMIs hold promises for neurorehabilitation of motor and sensory function, cognitive state evaluation and treatment of neurological chaos. A directed overview of the field of neural implants is discussed in this article. The aim of this review is to give a brief introduction of neural prosthetics as well as their exciting applications in treating neurological disorders and a deep discussion on their functionality are mentioned. BCI system and their different types, their functionality, their pros and cons, how other neural implants developed, and their present status have been covered. Different possibilities and possible future of deep brain stimulation (DBS), Neuralink, motor and sensory neural prosthetics are further discussed.

The use of Attitude and Heading Reference Systems (AHRS) for orientation estimation is now common practice in a wide range of applications, e.g., robotics and human motion tracking, aerial vehicles and aerospace, gaming and virtual reality, indoor pedestrian navigation and maritime navigation. The integration of the high-rate measurements can provide very accurate estimates, but these can suffer from errors accumulation due to the sensors drift over longer time scales. To overcome this issue, inertial sensors are typically combined with additional sensors and techniques. As an example, camera-based solutions have drawn a large attention by the community, thanks to their low-costs and easy hardware setup; moreover, impressive results have been demonstrated in the context of Deep Learning. This work presents the preliminary results obtained by DOES , a supportive Deep Learning method specifically designed for maritime navigation, which aims at improving the roll and pitch estimations obtained by common AHRS. DOES recovers these estimations through the analysis of the frames acquired by a low-cost camera pointing the horizon at sea. The training has been performed on the novel ROPIS dataset, presented in the context of this work, acquired using the FrameWO application developed for the scope. Promising results encourage to test other network backbones and to further expand the dataset, improving the accuracy of the results and the range of applications of the method.

Steel is one of the essential materials in the world's civilization. It is essential to produce many products such as pipelines, mechanical elements in machines, vehicles, profiles, and beam sections for buildings in many industries. Until the '50s of the 20th century, steel products required a complex process known as ingot casting; for years, steelmakers focused on developing and simplifying this process. The result was the con-tinuous casting process (CCP); it is the most productive method to produce steel. The CCP allows producing significant volumes of steel sections without interruption and is more productive than the formal ingot casting process. The CCP begins by transferring the liquid steel from the steel-ladle to a tundish. This tundish or vessel distributes the liquid steel, by flowing through its volume, to one or more strands having wa-ter-cooled copper molds. The mold is the primary cooling system, PCS, solidifying a steel shell to withstand a liquid core and its friction forces with the mold wall. Further down the mold, the rolls drive the steel section in the SCS. Here the steel section is cooled, solidifying the remaining liquid core, by sprays placed in every cooling segment all around the billet and along the curved section of the machine. Finally, the steel strand goes towards a horizontal-straight free-spray zone, losing heat by radiation mechanism, where the billet cools down further to total solidification. A moving torch cutting-scissor splits the billet to the desired length at the end of this heat-radiant zone.

Adhesion systems are very important in robots for infrastructure inspection (especially in vertical walls). They present the challenge of optimizing the ratio vacuum/power consumption in battery-powered robots. In this paper a CFD (Computer Fluid Dynamics) modelling and optimization process of a robot adhesion system is carried out to determine the best performing configuration in terms of vacuum and power consumption. Analytical and numerical models were developed to predict the behaviour of the system for different configurations. The models were validated, using test rig measurements, by calibrating an arbitrary defined inlet height that simulates the leakage flow. Then, different geometric parameters were varied to determine the best performing configuration based on the vacuum/power consumption ratio value. The model presented in the paper was capable of predicting the behaviour of the system for different configurations, with a margin of error of 15% for the vacuum prediction and a 25% for the motor power calculation. Finally, the model was used to optimize parameters of the system, like the number of blades of the impeller. The adhesion system was conceived for the modular autonomous climbing legged robot ROMERIN.

Auto checkout has received more and more attention in recent years and this system automatically generates a shopping bill by identifying the picture of the products purchased by the customers. However, the system is challenged by the domain adaptation problem, where each image of the training set contains only one commodity, whereas the test set is a collection of multiple commodities. The existing solution to this problem is to resynthesize the training images to enhance the training set. Then the composite images are rendered using CycleGAN to make the image distribution of the training set and the test set more similar. However, we find that the detection boxes given by the ground truth of the common dataset contain a large part of the background area, the area will affect the training process as noise. To solve this problem, we propose a mask data priming method. Specifically, we redo the large scale Retail Product Checkout (RPC) dataset and add segmentation annotation information to each item in the training set image based on the original dataset using pixel-level annotation. Secondly, a new network structure is proposed in which we train the network using joint learning of detectors and counters, and fine-tune the detection network by filtering out suitable images from the test set. Experiments on the RPC dataset have shown that our method yields better results. we used an approach that reached 81.87% compared to 56.68% for the baseline approach which demonstrates that pixel-level information helps to improve the detection results of the network.

Spike shape and morphometric characteristics are among the key characteristics of cultivated cereals associated with their productivity. Identification of the genes controlling these traits requires morphometric data harvesting and analysis for numerous plants, which is automatable using technologies of digital image analysis. A method for wheat spike morphometry utilizing 2D image analysis is proposed. Digital images are acquired in two variants: a spike on a table (one projection) or fixed with a clip (four projections). The method identifies spike and awns in the image and estimates their quantitative characteristics (area in image, length, width, circularity, etc.). Models of sections, quadrilaterals, and radial model are proposed for describing spike shape. Parameters of these models are used to predict spike shape type (spelt, normal, or compact) by machine learning. The mean error in spike density prediction for the images in one projection is 4.61 (~18%) versus 3.33 (~13%) for the parameters obtained using four projections. F1 measure in automated spike classification into three types is 0.78 using logistic regression (one projection) and 0.85 using random forest method (four projections). The proposed method is implemented in Java; examples of images and user guide are available at http://wheatdb.org/werecognizer.

Heat emitters constitute the primary devices used in space heating and cover a fundamental role in the energy efficient use of buildings. In the search for an optimized design, heating devices should be compared with a benchmark emitter with maximum heat emission efficiency. However, such an ideal heater still needs to be defined. In this paper we perform an analysis of heat transfer in a European reference room, considering room side effects of thermal radiation and computing the induced operative temperature both analytically and numerically. By means of functional optimization, we analyse trends such as the variation of operative temperature with radiator panel dimensions, finding optimal configurations. In order to make our definitions as general as possible, we address panel radiators, convectors, underfloor (UFH) and ceiling heater. We obtain analytical formulas for the operative temperature induced by panel radiators and identify the 10-type as our ideal radiator, while the UFH provides the best performance overall. Regarding specifically UFH and ceiling heaters, we find optimal sizes that identify the according ideal emitters. The analytical method and quantitative results reported in this paper can be generalized and adopted in most studies concerning the efficiency of different heat emitter types in building enclosures.

We consider a random dynamical system arising in a model of associative memory. This system can be seen as a small (stochastic and deterministic) perturbation of a determinstic system having two weak attractors which are destroyed after the perturbation. We show, with a computer aided proof, that the system has a kind of chaotic itineracy. Typical orbits are globally chaotic, while they spend relatively long time visiting attractor's ruins.

The aim of the present study is to investigate both the performance and preferences of males and females Computer Science (CS) graduates. In order to attain the above goal, a quantitative case study was conducted regarding 89 degrees, acquired from 2006 to 2012, from the Department of Computer Science and Technology, University of Peloponnese, Greece. The analysis of the data revealed that in terms of performance, no significant differences between the mean grades of males and females exist, in almost most of the courses included in the curriculum of the aforementioned CS department. Any statistically significant differences in performances were present in almost equal number of courses in favor of males and females. It seems also, that females performed better in the courses they selected more than males. Regarding preferences, in CS courses, it seems that gender differences are existent. Males preferred more than females did core programming courses and advanced topics of Software Systems, computer networks, computer engineering, robotics and mathematics, whereas females preferred more the study of algorithms and security issues, computer fractals, data management, computer architecture, and mobile communication. In addition, females preferred courses in reference with humanities and social sciences, CS terminology, and career opportunities. Yet, females did not select any of programming lab-based courses, computer engineering, computer network issues and robotics.

Background/Objectives: This study aims to investigate the influence of root canal morphology and various treatment variables on the outcomes of root canal treatments (RCT) in mandibular second molars, assessed through cone-beam computed tomography (CBCT) imaging. Methods: A total of 150 CBCT images were examined, comprising 100 cases of persistent endodontic infections and 50 from previously treated root canals with normal apices in mandibular second molars. CBCT was utilized to evaluate root canal configuration, the radiographic quality of coronal restorations and treated canal systems, and the presence of periapical lesions. Statistical analyses were performed to explore correlations between these factors. Results: The presence of a C-shaped root canal configuration did not demonstrate a significant correlation with periapical lesions (p=0.05). Factors influencing endodontic treatment outcomes included the presence of missing canals (p=0.018), underfilling or overfilling (p=0.045), and inadequate coronal restoration (p=0.006). The presence of a missing canal was identified as the variable most significantly associated with periapical lesions (OR=3.103). Leaky canals were more commonly observed in C-shaped root canals (p&lt;0.001). Conclusions: Regardless of the root canal morphology of mandibular second molars, successful RCT depends on thorough disinfection to eliminate any untreated canals, precise three-dimensional filling of the canals at the correct working length, and a securely sealed coronal restoration to prevent leakage.

This research investigates the fatigue behaviour and fracture mechanics of high-performance concrete (HPC), including various compositions such as HPC with basalt aggregates (HPC-B), HPC with gravel (HPC-G), and high-strength coarse mortar (CM) static and cyclic tensile loading within the special priority program SPP 2020. The study aims to integrate fracture mechanics into structural analysis to enhance design guidelines for slender cross-sections and safety-related high-performance structural components. The experimental investigations reveal HPC-B's re-markable superiority, displaying higher compressive strength, modulus of elasticity, and tensile strength compared to HPC-G and CM. A modified disk-shaped compact tension (MDCT) based on ASTM standards, aided by digital image correlation (DIC) unveils fracture behaviour, empha-sizing fracture energy as a crucial parameter. HPC-B exhibits improved crack resistance and notch sensitivity reduction attributed to crushed basalt aggregates and enhanced interfacial transition zone (ITZ). The research scrutinizes factors like material characterization, aggregate morphology, stress levels, and displacement rate on crack formation. High-cycle fatigue tests show HPC-B's superior performance, and post-fatigue analysis reveals enhanced residual fracture toughness attributed to nano-level structural changes, stress redistribution and aggregate-matrix interac-tion. 3D image analysis via Computed Tomography (CT) scans captures mesostructural crack propagation and provide quantitative insights. This study advances the understanding of HPC fatigue behaviour, emphasizing the interplay of aggregate types, morphologies, and their dy-namic response to cyclic loading, offering valuable insights for optimizing design guidelines and fostering innovation in structural engineering.

Although ovarian cystic teratoma is the most common ovarian tumor, complications are quite rare. However, it is important to be recognized by the radiologist in order to avoid inaccurately diagnosing them as malignant lesions. This case report describes a 61-year-old postmenopausal woman, who presented to the emergency room with abdominal pain following a minor blunt abdominal trauma. In this context, a CT scan was performed, which showed the presence of round, hypodense masses randomly distributed in the peritoneum, with coexisting ascites in moderate amount; ovarian carcinoma with peritoneal carcinomatosis was suspected. The patient was hospitalized and an MRI of the abdomen and pelvis was recommended for a more detailed lesion characterization. Following this examination, the patient was diagnosed with mature cystic ovarian teratoma complicated by rupture. Surgery was performed, and the outcome was favorable. The cases of ruptured cystic teratomas are rare, and to our knowledge, this is the first occurrence described in literature. Special attention must be paid when confronting with such a case in medical practice, since it can easily misdiagnosed as peritoneal carcinomatosis

This research aimed to compare the measurements recorded by a traditional PCI technology biometer (Partial Coherence Interferometry) and by a SS-OCT (Swept Source Optical Coherence Tomography) technology machine in preoperative screening of patients with age-related cataract. Optical biometry was performed with the IOLMaster 500 (version 5.5, Carl Zeiss Meditec, Germany) and the ANTERION (Heidelberg Engineering, Germany) in a total sample of 144 eyes, from 80 patients, (37 men and 43 women), with a mean age of 70.54 ± 0.739 years (range: 45-89 years) and the values of the Axial Length (AL), two meridians of the cornea (Kf, Kflat and Ks, Ksteep), astigmatism (Ast) as well as the Anterior Chamber Depth (ACD) were compared with the program IBM SPSS Statistics 27. The IOLMaster500 and ANTERION devices did not have statistically significant differences in terms of axial length and flat corneal meridian Kf, while they differed statistically significantly in terms of steep corneal meridian Ks, astigmatism and anterior chamber depth. This study suggests that a thorough pre-operative check must be performed, sometimes with more than one device, aiming at greater accuracy in the measurements of the ocular biometrics, so that we achieve more successful postoperative outcomes and ultimately more satisfied patients.

The black hole (BH) phenomenon is an intraluminal restenotic lesion. It was identified by intravascular ultrasound (IVUS) and optical coherence tomography (OCT) after intracoronary brachytherapy and drug-eluting stent implantation. Despite the similarity in the mode of action of brachytherapy and drug-eluting stent implantation, the BH phenomenon appears to be uncommon after drug-eluting stent implantation. Specifically, the BH phenomenon is better identified by OCT than by IVUS. Herein, we present a case of in-stent restenosis with suspected BH phenomenon on IVUS confirmed by OCT.

(1) Background: This study evaluated the spatial position and anatomical characteristics related to impacted third molars by map-reading strategy using cone beam computed tomography (CBCT). (2) Methods: To determine the positioning of impacted third molars on CBCT it was used Winter's and Pell &amp; Gregory's classifications, and the presence of external root resorption in mandibular second molars were based on Herman´s classification. The relationship between the mandibular third molar root apex and the mandibular canal was also analyzed. Fisher’s exact test was used to comparative statistical analysis. The significance level considered was 5%. (3) Results: The results showed that according to Winter's classification, 48.06 % of impacted teeth were in the mesioangular position. Using Pell &amp; Gregory's classification, 43.22% of the impacted molars were in the position B and C, and 54.2% of the teeth were class II. 69.7% of teeth showed an absence of contact between the root apex and the mandibular canal and there was no occurrence of external root resorption in the distal of second molar in 88.7%. (4) Conclusions: The map-reading strategy using CBCT scans for anatomical positions and characteristics of impacted third molars increases professional confidence and establishes a parameter of quality and safety in the surgical procedure for the patient.

About half of the transcatheter aortic valve replacement (TAVR) recipients exhibit some degree of coronary artery disease (CAD), and controversial results have been reported regarding the impact of the presence and severity of CAD on clinical outcomes post-TAVR. In addition to coronary angiography, promising data has been recently reported on the use of both cardiac computed tomography angiography and the functional invasive assessment of coronary lesions whether by FFR or iFR in the work-up pre-TAVR. Despite mitigated available data, percutaneous revascularization of significant coronary lesions has been the routine strategy in TAVR candidates with CAD. Also, scarce data exists on the incidence, characteristics and management of coronary events post-TAVR, and increasing interest exist on potential coronary access challenges in patients requiring coronary angiography/intervention post-TAVR. This review provides an updated overview of the knowledge of CAD in TAVR recipients, focusing on its prevalence, clinical impact, pre- and post-procedural evaluation and management.

Electrocardigraphy remains as a first-line evaluation method for cardiac function, recording the electrical activity of the heart from the body surface. Since atrial activation is seen on the ECG as P-wave, several factors are known to impact the appearance of the P-wave, such as direction of electric impulse, conduction abnormalities and anatomical characteristics of the atria. The aim of this retrospective study was to find statistically significant associations between anatomy of pulmonary veins (PVs) osberved in cardiac computed tomography (CT) and P-wave appearance during sinus rhythm on resting ECG. For each patient, a resting 12-lead ECG was recorded, the field of analysis was P wave – its’ duration, morphology and axis. The evaluation of the CT scan recordings was performed by creating 3D models of the left atrium and analyzing anatomy of the PVs and left atrial appendage (LAA). Noteworthy correlations were found: anatomy of the left PVs showed an association with LAA volume, LAA morphology and P-wave notching in lead II. The right PVs demonstrated relation with P wave axis and amplitude. Although these correlations cannot be classified as strong, they may play a role in significant scientific discoveries in future research projects.

.Purpose: This paper presents a comparative analysis of state-of-the-art DIR algorithms in the context of head and neck squamous cell carcinoma (HNSCC) radiation therapy. Materials and Methods: We used a dataset of head and neck cancer patients within the Cancer Image Archive, which includes 31 patients with 3D CT image data from pre-treatment, mid-treatment, and post-treatment stages of radiotherapy. We applied DIR algorithms to two datasets, one for pre-treatment to mid-treatment registration and another for mid-treatment to post-treatment registration, by aligning one CT image to another CT image. To quantitatively analyze the patient data, we focused on the spinal cord, optic nerve, brain stem, cochlea, and PTV as the OAR datasets. To verify the DIR algorithm, we used two non-learning-based methods, SyN and NiftyReg, as well as three deep learning-based methods, Voxelmorph, Cyclemorph, and Transmorph. We trained a deep learning model by adjusting the ratio of the training dataset, validation dataset, and test dataset to 7:1:2. Results: The average DSCs of SyN and NiftyReg, the non-learning-based methods, were 0.74±0.06 and 0.70±0.12, respectively. The deep learning-based methods, Voxelmorph, Cyclemorph, and Transmorph, had average DSCs of 0.72±0.08, 0.68±0.11, and 0.69±0.13, respectively. The deep learning DIR algorithm produced transformed outputs of OAR/PTV in a shorter time than other models, including commercial and conventional mathematical algorithms (At Inference(sec/images), Voxelmorph: 0.36, Cyclemorph: 0.3, Transmorph: 5.1, SyN: 140, NiftyReg: 40.2). Conclusions: In conclusion, our study provides a comprehensive comparison of commercial DIR algorithms with traditional and deep learning-based DIR methods. Our results demonstrate that commercial DIR algorithms outperform traditional DIR methods in terms of accuracy and efficiency. However, we also show that deep learning-based DIR methods have the potential to achieve similar performance to commercial algorithms with proper training and optimization. Our findings suggest that both commercial and deep learning-based DIR methods have their respective advantages and limitations, and the choice of method should depend on the specific requirements of the clinical application. Overall, our study contributes to ongoing efforts to improve the accuracy and efficiency of DIR methods for better patient outcomes.

Introduction: CT perfusion (CTP) is an alternative tool to assess cerebral hemodynamics in brain trauma. As traumatic acute subdural hematomas (ASH) are severe lesions commonly associated with poor outcome, we aimed to evaluate the brain hemodynamics in this population. Methods: Five patients admitted at the emergency department sustaining traumatic acute subdural hematoma were evaluated. Preoperative CTP was performed immediately after nonenhanced head CT scan. Postoperative CTP was performed in four patients. The outcome was assessed 6 months after surgery using the extended Glasgow Outcome Scale. Results: 4 male and 1 female were evaluated. Mean age was 46y (SD: 8.1). Mean preoperative midline brain shift was 10.1 mm (SD: 1.8). The main mechanism of trauma was falling (four patients). There was a general improvement in cerebral blood flow (CBF) after surgery from 23.9 (SD: 6.1) to 30.7 ml/100g/min, (SD: 5.1) and in mean transit time (MTT) from 7.3 (SD: 1.3) to 5.8s (SD:1.0), although it is not statistically significant (p=0.06 and p=0.06, respectively). There was still a reduction in the cerebral blood volume (CBV) media when compared to the value after surgery, from 2.63 (SD: 1.10) to 2.34 ml/100g (SD: 0.67), which is not statistically significant (p=0.31). Spearman correlation test of postoperative and preoperative CBF ratio with outcome was 0.94 (p=0.054). Only one patient died (three days after surgery). This patient was victim of car crash and had the highest preoperative MTT (9.97 seconds) and CBV (4.51 ml/100 g). Conclusion: Post-operative improvement of hemodynamic CTP parameters may be correlated with outcomes after ASH. Further studies with larger samples are required to confirm this hypothesis.

Using the OCT platform, we can generate high-resolution data on retinal nerve fiber layer (RNFL) thickness in a given eye at a large number of angular-points defined on a circular coordinate system. However, insightful characteristics of OCT RNFL data such as its circularity and granularity generally remain unutilized in its common downstream statistical analyses. We present a new circular statistical framework that defines an Angular Decay function and thereby provides a directional representation of an eye in terms of its focused RNFL loss. By applying to a clinical cohort of Asian Indian eyes, the generated circular data was modeled with a finite mixture of von Mises distributions, which led to unsupervised identification in different age-groups of 2 recurrent clusters of glaucomatous eyes with distinct directional signatures of RNFL decay. New indices of global and local RNFL loss were computed for comparing the structural differences between these glaucoma clusters across the age-groups.

Background: As coronavirus (COVID-19) continues to pose a threat to the entire world, it is critical to developing strategies for containing its spread. The purpose of this study was to assess the demographic characteristics, brain tomography characteristics, and diffusion magnetic resonance findings of COVID-19 positive individuals. Material and Method: Between January 1 and December 31, 2021, 317 patients over the age of 18 were admitted to the emergency department with symptoms consistent with COVID-19. Three groups were formed based on clinical findings in patients, divided into light, medium, and severe, and four groups were formed based on radiological imaging findings. Results: The mean age of the 317 patients included in the study was 67.28±12.06 years, with a range of 28-91 years. The clinical classification of the patients was based on laboratory parameters and radiological imaging, not on their age or gender. Mild cases were classified as CO-RADS 0-4; moderate and severe cases were classified as CO-RADS 5-6 (p=0.001). While 60 (18.9%) of patients were followed outpatient, 144 (45.4%) were admitted to the hospital, 73 (23%) were admitted to the intensive care unit, and 40 (12.7%) died (p=0.001). Direct radiographs revealed bilateral involvement in 224 (70.7%) cases, peripheral involvement in 259 (81.7%) cases, and mid-lower lobe lung involvement in 194 (61.2%) cases (p=0.001). Brain tomography revealed infarction in 42 (13.2%) of the patients who were followed and hospitalized and hemorrhage in 22 (6.9%) of the patients. Magnetic resonance imaging revealed diffusion involvement in 68 (21.5%) of the cases (p=0.001). Conclusion: A standardized reporting system for COVID-19 data is required, and it must be simple to use, quick to understand, and focused on determining the risk of pneumonia. Additionally, the diagnostic role of radiological imaging, prognosis prediction, and severity scoring of lung involvement should be included.

Deep Learning is developing interesting tools which are of great interest for inverse imaging applications. In this work, we consider a medical imaging reconstruction task from subsampled measurements, which is an active research field where Convolutional Neural Networks have already revealed their great potential. However, the commonly used architectures are very deep and, hence, prone to overfitting and unfeasible for clinical usages. Inspired by the ideas of the green-AI literature, we here propose a shallow neural network to perform an efficient Learned Post-Processing on images roughly reconstructed by the filtered backprojection algorithm. The results obtained on images from the training set and on unseen images, using both the non-expensive network and the widely used very deep ResUNet show that the proposed network computes images of comparable or higher quality in about one fourth of time.

Higher-risk myelodysplastic syndrome (HR-MDS) has a poor prognosis in the absence of efficient therapy. The evaluation of new therapies in animal models of HR-MDS is hampered by the absence of accurate in vivo biomarkers of the disease. In this study we compared [18F]Fluoro-desoxyglucose Positron Emission Tomography (FDG-PET) and [18F]Fluoro-thymidine (FLT)-PET imaging for disease follow-up in a triple transgenic MMTVtTA/TetoBCL-2/MRP8NRASD12 mouse model of HR-MDS. Normal control FVB/N mice (G1,n=9) and HR-MDS mice (G2,n=12) underwent both FDG- and FLT-PET procedures at 2-day intervals, on a dedicated small animal device. Blood cell counting, BCL-2 and Mac-1hi/Gr-1lo expression measurements in blood were performed before each PET procedure. Visually, PET images of G2 mice demonstrated homogeneous FDG uptake in the whole skeleton similar to that observed in G1 mice, and abnormal FLT hot spots in bone marrow not observed in G1 mice. The intensity of FLT hot spots in bone marrow was higher in 3-months old G2 mice than in 2-months old G2 mice, concordant with a higher percentage of cells expressing Mac-1hi/Gr-1lo and lower platelets counts. We conclude that FLT-PET/CT imaging is a more valuable surrogate non-invasive quantitative marker of HR-MDS bone marrow involvement than FDG-PET/CT in our mouse model of HR-MDS.

To investigate the impact of radiologic experience on the diagnostic accuracy of computed tomography CT vs. magnetic resonance imaging (MRI) reporting for liver metastases of pancreatic ductal adenocarcinoma (LM of PDAC). Intra-individual CT and MRI examinations of 112 patients with clinically proven LM of PDAC were included. Four radiologists with varying years of experience (A > 20, B > 5, C > 1 and D < 1) assessed liver segments affected by LM of PDAC, as well as associated metastases occurring in each patient. Their sensitivity and specificity in evaluating the segments were compared. Cohen's Kappa (κ) for diagnosed liver segments and Intra-class Correlation Coefficients (ICC) for the number of metastatic lesions in each patient were calculated. The radiologists’ sensitivity and specificity for the CT vs. MRI were, respectively: Reader A -94.4, 90.3% vs. 96.6, 94.8%; B - 86.7, 79.7% vs. 83.9, 82.0%; C - 78.0, 76.7% vs. 83.3, 78.9% and D - 71.8, 79.2% vs. 64.0, 69.5%. Reviewers A and B achieved greater agreement in assessing results from the MRI (κ = 0.72, p < 0.001; ICC = 0.73, p < 0.001) vs. the CT (κ = 0.58, p < 0.001; ICC = 0.61, p < 0.001), in contrast to readers C and D (MRI: κ = 0.34, p < 0.001; ICC = 0.42, p < 0.001, and CT: κ = 0.48, p < 0.001; ICC = 0.59, p < 0.001). Our results indicate that accurate diagnosis of LM of PDAC depends more on radiologic experience in MRI over CT scans.

Cachexia is a syndrome characterized by an ongoing loss of skeletal muscle mass associated with poor patient prognosis in non-small cell lung cancer (NSCLC). However, prognostic cachexia biomarkers in NSCLC are unknown. Here, we analyzed computed tomography (CT) images and tumor transcriptome data to identify potentially secreted cachexia biomarkers (PSCB) in NSCLC patients with low-muscularity. We integrated radiomics features (pectoralis muscle, sternum, and T10 vertebra) from CT of 89 NSCLC patients, which allowed us to identify an index for screening muscularity. Next, a tumor transcriptomic-based secretome analysis from these patients (discovery set) was evaluated to identify potential cachexia biomarkers in patients with low-muscularity. The prognostic value of these biomarkers for predicting recurrence and survival outcome was confirmed using expression data from eight lung cancer datasets (validation set). Finally, C2C12 myoblasts differentiated into myotubes were used to evaluate the ability of the selected biomarker, IL-8, in inducing muscle cell atrophy. We identified 75 over-expressed transcripts in patients with low-muscularity, which included IL6, CSF3, and IL8. Also, we identified NCAM1, CNTN1, SCG2, CADM1, IL8, NPTX1, and APOD as PSCB in the tumor secretome. These PSCB were capable of distinguishing worse and better prognosis (recurrence and survival) in NSCLC patients. IL8 was confirmed as a predictor of worse prognosis in all validation sets. In vitro assays revealed that IL-8 promoted C2C12 myotube atrophy. Tumors from low-muscularity patients presented a set of upregulated genes encoding for secreted proteins, including pro-inflammatory cytokines that predict worse overall survival in NSCLC. Among these up-regulated genes, IL8 expression in NSCLC tissues was associated with worse prognosis and the recombinant IL-8 was capable of triggering atrophy in C2C12 myotubes.

Cold gas-dynamic spray (cold spray) is an evolving coating deposition and restoration technology in which particles are deposited above the sonic speed. This paper presents the non-destructive three-dimensional characterization of cold sprayed stainless steel coating. The visualization of coating morphology and volumetric porosity, and the analyses of porosity size and spatial distributions confirmed that dense stainless steel coating with non-connected, micron-sized gradient porosity is successfully produced by cold spray. The suitability of X-ray tomography for characterizing cold sprayed coatings is assessed.

In high-risk railway construction, personal protective equipment monitoring is critical but challenging due to small and frequently obstructed targets. We propose YOLO-EA, an innovative model that enhances safety measure detection by integrating ECA into its backbone's convolutional layers, improving discernment of minuscule objects like hardhats. YOLO-EA further refines target recognition under occlusion by replacing GIoU with EIoU loss. YOLO-EA's effectiveness was empirically substantiated using a dataset derived from real-world railway construction site surveillance footage. It outperforms YOLOv5, achieving 98.9% precision and 94.7% recall, up 2.5% and 0.5% respectively, while maintaining real-time performance at 70.774 fps. This highly efficient and precise YOLO-EA holds great promise for practical application in intricate construction scenarios, enforcing stringent safety compliance during complex railway construction projects.

Through the refinement of approaches to applying visual augmentation to virtual environments, the possibilities of utilising this process in robotics continues to be explored. However these endeavours have only yielded a collaborative relationship between the two technologies, where the augmented reality (AR) component is separate from the robot functionality. Regarding telepresence robots, research has shown that their perceived usefulness wanes in comparison to that of video conferencing tools as they do not offer a level of immersion and modified visual experience to justify their use. Therefore this paper contributes a novel virtually augmented robot (VAR) model that embeds AR functionality into telepresence, through the use of augmentation and facial recognition sub-models and algorithms. Experimental results show that using pulse width modulation (PWM), duty cycles, digital signals and accelerometer angles provides an approach for stabilising robot motion and the transference of human to robot head movement. The results also show the benefit of having a robot model with intrinsic AR functionality, as it offers a greater level of immersion and visual control of an environment.

The purpose of this study is to ​​explore the use of a custom Transformer model in brain-computer interfaces (BCIs) that translate the neural activity present when an individual with limited verbal and fine-motor skills attempts to handwrite. As found in previous studies, Transformers have performed better than recurrent neural networks (RNNs) in translation tasks which are similar to its usage here in decoding neural signals into intended handwritten text. Due to the known benefits of a Transformer, the hypothesis was that the Transformer would show promise in the context of a BCI through the recorded metrics. The neural signals of a tetraplegic individual, when they attempted to handwrite, were provided by existing research. Four trials were conducted using data with or without augmentation which the model used when training to separately minimize training loss and validation loss. When comparing the results of a BCI with the implementation of a Transformer model with the original RNN BCI (the original data source), the Transformer model performed less favorably across all four trials. Although the results do not indicate that the Transformer model currently outperforms an RNN BCI, it is important to note that further testing of the model's capabilities (such as training it with a larger and more preferable dataset and/or for longer, comparing training times between the RNN and Transformer, and/or seeing how the Transformer is improved with an offline autocorrect feature) is necessary before determining whether Transformers can enhance communication in this manner.

Pedagogic Conversational Agents (PCAs) are interactive systems that engage the student in a dialogue to teach some domain. They can have the role of teacher, student, or companion, and adopt several shapes. In our previous work, a significant increase of students’ performance when learning programming was found when using PCAs in the teacher role. However, it is not common to find PCAs used in the classrooms. In this paper, it is explored whether teachers would accept PCAs to teach programming better if co-designed with them. An experiment with 35 pre-service Primary Education teachers was carried out during the 2021/2022 academic year to co-design a robotic PCA to teach programming. The experience validates the idea that involving the teachers in the design of the PCA facilitates that they integrate this technology in their classrooms. 97% of the pre-service teachers answered in a survey that they believed that the robot PCA could help children to learn programming and 80% answered that they would like to use them in their classrooms.

The overpopulation of feral pigeons in Hong Kong has significantly disrupted the urban ecosystem, highlighting the urgent need for effective strategies to control their population. In general, control measures should be implemented and re-evaluated periodically following accurate estimations of feral pigeon population in the concerned regions, which, however, is very difficult in urban envi-ronments due to the concealment and mobility of pigeons within complex building structures. With the advances in deep learning, computer vision can be a promising tool for pigeon monitoring and population estimation but has not been well investigated so far. Therefore, we propose an improved deep learning model based on Mask-RCNN (Swin-Mask R-CNN) for feral pigeon detection using computer vision techniques. Specifically, our model consists of a Swin transformer network (STN) as the backbone, a feature pyramid network (FPN) as the neck, and three decoupled detection heads. The STN is utilized to extract deep feature information of feral pigeons through local and cross-window attention mechanisms. The FPN is employed to fuse multi-scale features and enhance the multi-scale learning ability. Heads in the three branches are responsible for classification, pre-dicting best bounding boxes, and segmentation of feral pigeons, respectively. During the prediction phase, a Slicing Aided Hyper Inference (SAHI) tool is employed to zoom in on the feature infor-mation of small feral pigeon targets, and the segmentation head is frozen to expedite inference of large images. Experiments were conducted on feral pigeon dataset to evaluate model performance. The results reveal that our model is well-suited for detecting small targets in high-resolution images and achieves excellent recognition performance for feral pigeons with a mAP (mean average pre-cision) and an AP50 (average precision at 50% intersection over union) of 0.74 and 0.93, respectively. For small target feral pigeons, AP50 in small scale (AP50s) improved by 10% as compared to the Mask R-CNN (AP50s of 0.75), demonstrating its potential for dynamic pigeon detection and population estimation in the future.

Track fasteners play a pivotal role in infrastructure inspection for high-speed rail. Yet, images taken by drones often capture shadows cast by electrical towers flanking the high-speed rail tracks. These shadows can hinder the visibility of the track fasteners, thereby impacting detection efficiency and accuracy considerably. The present paper introduces an end-to-end shadow removal algorithm, rooted in generative adversarial network training. The comprehensive network framework is segmented into three sub-networks: pseudo-mask generation, shadow removal, and result refinement. We have integrated a Fourier convolutional residual module to bolster the feature extraction capability of the generator network. This integration ensures the network retains a global receptive field, even in its more superficial layers. By employing an overall weighted loss function, we enhance the quality of the images produced without shadows. Further, a perceptual loss function has been incorporated to retain the structural information of objects, setting the stage for subsequent defect detection. Our results highlight that Pse-ShadowNet adeptly eradicates fastener shadows while maintaining vital visual features, including object position, structure, texture, edges, and other key visual elements. Consequently, the reconstructed images are detailed and showcase superior image quality.

Developmental hazard evaluation is an important part of assessing chemical risks during pregnancy. Toxicological outcomes from prenatal testing in pregnant animals result from complex chemical-biological interactions, and while New Approach Methods (NAMs) based on in vitro bioactivity profiles of human cells offer promising alternatives to animal testing, most of these assays lack cellular positional information, physical constraints, and regional organization of the intact embryo. Here, we engineered a fully computable model of the embryonic disc in the compucell3d.org modeling environment to simulate epithelial-mesenchymal transition of epiblast cells and self-organization of mesodermal domains (chordamesoderm, paraxial, lateral plate, posterior/extraembryonic). Cell fate in the model is determined by an autonomous homeobox (HOX) clock driven by morphogenetic signals (e.g., FGF, WNT, ATRA, CDX). Executing the model renders a quantitative cell-level computation of mesodermal subpopulations and consequences of perturbation based on known embryogeny. For example, synthetic perturbation of the control network rendered altered phenotypes (cybermorphs) mirroring experimental mouse embryology, with 50% reductions in FGF4, FGF8 and BMP4 signaling resulting in 86%, 98% and 59% reductions, respectively in the posterior mesodermal population, while ATRA exposure also resulted in a 78% decrease in this population. This model enables integration of in vitro chemical bioactivity data for specific molecular targets with known embryology to test mechanistic veracity and quantitative prediction of altered development.

Human Action Recognition is widely used in multiple fields to recognize activities and extract spatial and temporal information. This paper focuses on analyzing various methods as well as provides extensive knowledge of the foundational concepts of the HAR. A dataset is also very crucial for any research study so we discussed the popular dataset and its features in this paper.

A single paragraph of about 200 words maximum. Electroencephalography (EEG) accumulates the electrical activities of human brain. It is an easy and cost effective tool to characterize motor imagery (MI) task used in brain computer interface (BCI) implementation. The MI task is represented by short time trial of multichannel EEG. In this paper, the raw EEG is decomposed into a finite set of narrowband signals obtained from individual EEG channels using Fourier transformation based bandpass filter. Each of the subband signals represents narrowband rhythmic components which characterize the brain activities related to motor imagery. The subband signals are arranged to extent the dimension of EEG trial in spatial domain. The spatial features are extracted from the set of extended trials using common spatial pattern (CSP). An optimum number of features are used to classify the motor imagery tasks represented by EEG trials. Artificial neural network is used to classify MI tasks. The performance of the proposed method is evaluated using two publicly available benchmark datasets. The experimental results show that it performs better than the recently developed algorithms.

With the advent of deep learning, significant progress has been made in low-light image enhancement methods. However, deep learning requires enormous paired training data, which is challenging to capture in real-world scenarios.To address this limitation, this paper presents a novel unsupervised low-light image enhancement method, which first introduces the frequency domain features of images in low-light image enhancement tasks. Our work is inspired by imagining a digital image as a spatially varying metaphoric “field of light”, then subjecting the influence of physical processes such as diffraction and coherent detection back onto the original image space via a frequency-domain to spatial-domain transformation (inverse Fourier transform). However, the mathematical model created by this physical process still requires complex manual tuning of the parameters for different scene conditions to achieve the best adjustment. Therefore, we proposed a dual-branch convolution network to estimate pixel-wise and high-order spatial interactions for dynamic range adjustment of the frequency feature of the given low-light image. Guided by the frequency feature from the “field of light” and parameter estimation networks, our method enables dynamic enhancement of low-light images. Extensive experiments have shown that our method performs well compared to state-of-the-art unsupervised, and its performance approximates the level of the state-of-the-art supervised methods qualitatively and quantitatively. At the same time, the light network structure design allows the proposed method to have an extremely fast inference speed(nearly 150 FPS on an NVIDIA 3090 Ti GPU for an image of size 600×400×3 ). Furthermore, the potential benefits of our method to object detection in the dark are discussed.

The use of mathematical models of physiological systems in medicine has allowed the development of diagnostic, treatment, and medical educational tools, but their application for predictive, preventive, and personalized purposes is restricted by their complexity. Although there are strategies that reduce the complexity of applying models by fitting techniques, they focus on a single instant of time, neglecting the effect of the system's temporal evolution. The aim of this work is to propose a dynamic fitting strategy of physiological models with large number of parameters and a constrained amount of experimental data, focused on obtaining better predictions based on the system's temporal trend and useful to predict future states. It was applied in a cardiorespiratory model as a case study. Experimental data from a longitudinal study of healthy adult subjects under aerobic exercise were used for fitting and validation. The model predictions obtained at steady-state using the proposed strategy and the nominal values of the parameters were compared. The best results corresponded mostly to the proposed strategy, mainly regarding the overall prediction error. The results evidenced the usefulness of the dynamic fitting strategy, highlighting its use for predictive, preventive, and personalized applications.

An extensive review of literature simulations of polymer melts is given, considering results that test aspects of the Rouse model in the melt. We focus on the mean-square amplitudes < (X_p(0))^{2} > and time correlation functions < X_p(0) X_p(t) > of the Rouse modes $X_p(t)$. Contrary to the Rouse model: (i) Mean-square Rouse mode amplitudes < (X_p(0))^2> do not scale as sin^{-2}(p \pi/2N), N being the number of beads in the polymer. For small p (say, p <= 3) < (X_p(0))^2> scales with p as p^{-2}$; for larger p it scales as p^{-3}. (ii) Rouse mode time correlation functions < X_p(t) X_p(0) > do not decay with time as exponentials; they instead decay as stretched exponentials exp(-a t^b)$. b depends on p, typically with a minimum near N/2 or N/4. (iii) Polymer bead displacements are not described by independent Gaussian random processes. (iv) For p not equal to q, < X_p(t) X_{q}(0) > is sometimes non-zero. (v) The response of a polymer coil to a shear flow is a rotation, not the affine deformation predicted by Rouse. Simulations thus conclusively demonstrate that the Rouse model is invalid in polymer melts. We also briefly consider the Kirkwood-Riseman polymer model.

Background Bone fracture fixation surgery is one of the most commonly performed surgical procedures in the orthopedic field. However, fracture healing complications occur frequently, and the choice of the most optimal surgical approach often remains challenging. In the last years, computational tools have been developed with the aim to assist preoperative planning procedures of bone fracture fixation surgery. Objectives The aims of this review are (1) to provide a comprehensive overview of the state-of-the-art in computer-assisted preoperative planning of bone fracture fixation surgery, (2) to assess the clinical feasibility of the existing virtual planning approaches, and (3) to assess their clinical efficacy in terms of clinical outcomes as compared to conventional planning methods. Methods A literature search was performed in the MEDLINE-PubMed, Ovid-EMBASE, Ovid-EMCARE, Web of Science, and Cochrane libraries to identify articles reporting on the clinical use of computer-assisted preoperative planning of bone fracture fixation. Results 79 articles were included to provide an overview of the state-of-the art in virtual planning. While patient-specific geometrical model construction, virtual bone fracture reduction, and virtual fixation planning are routinely applied in virtual planning, biomechanical analysis is rarely included in the planning framework. 21 of the included studies were used to assess the feasibility and efficacy of computer-assisted planning methods. The reported total mean planning duration ranged from 22 to 258 minutes in different studies. Computer-assisted planning resulted in reduced operation time (Standardized Mean Difference (SMD): -2.19; 95% Confidence Interval (CI): -2.87, -1.50), less blood loss (SMD: -1.99; 95% CI: -2.75, -1.24), decreased frequency of fluoroscopy (SMD: -2.18; 95% CI: -2.74, -1.61), shortened fracture healing times (SMD:-0.51; 95% CI: -0.97, -0.05) and less postoperative complications (Risk Ratio (RR): 0.64, 95% CI: 0.46, 0.90). No significant differences were found in hospitalization duration. Some studies reported improvements in reduction quality and functional outcomes but these results were not pooled for meta-analysis, since the reported outcome measures were too heterogeneous. Conclusions Current computer-assisted planning approaches are feasible to be used in clinical practice and have been shown to improve clinical outcomes. Including biomechanical analysis into the framework has the potential to further improve clinical outcome.

Objective tools to track medication adherence are lacking. A tool to monitor pill intake that can be implemented in mHealth apps without the need for additional devices was developed. We propose a pill intake detection tool that uses digital image processing to analyze images of a blister to detect the presence of pills. The tool uses the circular Hough transform as a feature extraction technique and is therefore primarily useful for the detection of pills with a round shape. This pill detection tool is composed of two steps. First, the registration of a full blister and storing of reference values in a local database. Second, the detection and classification of taken and remaining pills in similar blisters, to determine the actual number of untaken pills. In the registration of round pills in full blisters, 100% of pills in gray blisters or blisters with a transparent cover were successfully detected. In counting of untaken pills in partially opened blisters, 95.2% of remaining and 95.1% of taken pills were detected in gray blisters, while 88.2% of remaining and 80.8% of taken pills were detected in blisters with a transparent cover. The proposed tool provides promising results for the detection of round pills. However, the classification of taken and remaining pills need to be further improved, in particular for the detection of pills with non-oval shapes.

Computational neuroscience combines mathematics, computer science models, and neurosciences for theorizing, investigating, and simulating neural systems involved in the development, structure, physiology, and cognitive abilities of the brain. Computational models constitute a major stake in translational neuroscience: the analytical understanding of these models seems fundamental to consider a translation towards clinical applications. Method: We propose a minimal typology of computational models, which allows distinguishing between more realistic models (e.g., mechanistic models) and pragmatic models (e.g., phenomenological models). Result: Understanding the translational aspects of computational models goes far beyond the intrinsic characteristics of models. First, we assume that a computational model is rarely uniquely mechanistic or phenomenological. Idealization seems necessary because of i) the researcher’s perspectives on the phenomena and the purposes of the study (i.e., by the relativity of the model); ii) The complexity of reality across different levels and therefore the nature and number of dimensions required to consider a phenomenon. Especially, the use of models goes far beyond their function, and requires considering external characteristics rooted in path dependence, interdisciplinarity, and pluralism in neurosciences. Conclusion: The unreasonable use of computational models, which are highly complex and subject to a shift in their initial function, could be limited by bringing to light such factors.

The chemical graph theory is a subfield of mathematical chemistry which applies classic graph theory to chemical entities and phenomena. Chemical graphs are main data structures to represent chemical structures in cheminformatics. Computable properties of graphs lay the foundation for (quantitative) structure activity and structure property predictions - a core discipline of cheminformatics. It has a historic relevance for natural sciences, such as chemistry, biochemistry and biology, and is in the heart of modern disciplines, such as cheminformatics and bioinformatics. This review first covers the history of chemical graph theory, then provides an overview of its various techniques and applications for CASE, and finally summarises modern tools using chemical graph theory for CASE.

Long-term continuous time series of SO2 emissions are considered critical elements of both volcano monitoring and basic research into processes within magmatic systems. One highly successful framework for computing these fluxes involves reconstructing a representative time-averaged SO2 plume from which to estimate the SO2 source flux. Previous methods within this framework have used ancillary wind datasets from reanalysis or numerical weather prediction (NWP) to construct the mean plume and then again as a constrained parameter in the fitting. Additionally, traditional SO2 datasets from ultraviolet (UV) sensors lack altitude information which must be assumed to correctly calibrate the SO2 data and to capture the appropriate NWP wind level which can be a significant source of error. We have made novel modifications to this framework which do not rely on prior knowledge of the winds and therefore do not inherit errors associated with NWP winds. To perform the plume rotation, we modify a rudimentary computer vision algorithm designed for object detection in medical imaging to detect plume-like objects in gridded SO2 data. We then fit a solution to the general time-averaged dispersion of SO2 from a point source. We demonstrate these techniques using SO2 data generated by a newly developed probabilistic layer height and column loading algorithm designed for the Cross-track Infrared Sounder (CrIS), a hyperspectral infrared sensor aboard the Joint Polar Satellite System’s Suomi-NPP and NOAA-20 satellites. This SO2 data source is best suited to flux estimates at high-latitude volcanoes and at low-latitude, but high-altitude volcanoes. Of particular importance, IR SO2 data can fill an important data gap in the UV-based record: estimating SO2 emissions from high-latitude volcanoes through the polar winters when there is insufficient solar backscatter for UV sensors to be used.

The objective of this paper is to assess the potential for potable water savings due to rainwater use in a precast concrete factory in southern Brazil. The economic feasibility and the rainwater quality were also assessed. The current water consumption, future water demand and rainwater demand in the factory were estimated. The future demand considered was two times higher than the current water consumption since there are plans to increase the production. Three scenarios were then simulated using the computer programme Netuno. The ideal rainwater tank capacity, the potential for potable water savings and the economic feasibility analysis for each scenario were estimated. Samples of rainwater were collected in the factory and tested for quality for manufacturing precast concrete. For a rainwater tank capacity equal to 25,000 litres, the potential for potable water savings for the first scenario was 55.4%, but the first scenario was considered economically unfeasible. For the same tank capacity, the second and third scenarios presented viable results regarding potable water savings and payback. As for the rainwater quality, it was proven to be adequate for manufacturing precast concrete. The main conclusion is that rainwater can be used to manufacture precast concrete in the factory studied herein.

The article describes a classification solution for amber stones. The problem of classifying amber is known for a long time among jewelers and artisans of amber art. Existing solutions can classify amber pieces according to color, but a need to classify by shape and texture is not satisfied up to now. The proposed solution is capable of classifying the gemstones according to a shape. Amber can be considered as a specific object since the form is difficult to define unambiguously. Data for amber experiments was gathered from amber art craftsmen. In the proposed solution amber form can be classified into 10 different classes (7 classes chosen during the experiment).

Ancient numismatics, that is, the study of ancient currencies (predominantly coins), is an interesting domain for the application of computer vision and machine learning, and has been receiving an increasing amount of attention in recent years. Notwithstanding the number of articles published on the topic, the variety of different methodological approaches described, and the mounting realisation that the relevant problems in the field are most challenging indeed, all research to date has entirely ignored one specific, readily accessible modality: colour. Invariably, colour is discarded and images of coins treated as being greyscale. The present article is the first one to question this decision (and indeed, it is a decision). We discuss the reasons behind the said choice, present a case why it ought to be reexamined, and in turn investigate the issue for the first time in the published literature. Specifically, we propose two new colour-based representations specifically designed with the aim of being applied to ancient coin analysis, and argue why it is sensible to employ them in the first stages of the classification process as a means of drastically reducing the initially enormous number of classes involved in type matching ancient coins (tens of thousands, just for Ancient Roman Imperial coins). Furthermore, we introduce a new data set collected with the specific aim of denomination-based categorisation of ancient coins, where we hypothesised colour could be of potential use, and evaluate the proposed representations. Lastly, we report surprisingly successful performances which goes further than confirming our hypothesis—rather, they convincingly demonstrate a much higher relevant information content carried by colour than even we expected. Thus we trust that our findings will be noted by others in the field and that more attention and further research will be devoted to the use of colour in automatic ancient coin analysis.

We propose a computer-generated hologram method for near-eye virtual reality and augmented reality 3D display. A 3D object located near the holographic plane is projected onto a projection plane to obtain a plurality of projected images with different angles. The hologram is calculated by superposition of projected image convolution with a specific PSF through the interference of reference wave with object wave. Holographic 3D display systems with LED as illumination, 4f optical filtering system and lens as eyepiece for near-eye VR display and HOE as combiner for near-eye AR display are designed. The results show that the proposed method is about 38 times faster than the conventional point cloud method. The proposed method is flexible to produce speckle noise free high-quality VR and AR images with efficient focus and defocus capabilities.

The beautiful and stable posture is essential for ballet. Especially the pirouette which dancers balance themselves on their one leg is one of the most impressive postures. During the pirouette motion, loads from the rotation and the body weight are concentrated to the one leg. Proper ballet shoes can reduce the muscle burden and improve the stability. Four types of shoes; bare feet, running shoes, pointe shoes, and dance sneakers are analyzed. The motion capture system and SIMM are used for the analysis of muscle burden and stability during pirouette. The major 6 muscles in the leg (beceps femoris long head, beceps femoris short head, soleus, rectus femoris, gastrocnemius medialis, and gastrocnemius lateralis) are analyzed, and the effect of rotating velocity is considered. Dance sneakers are outstanding for improving the stability and lessening the muscle burdens in all conditions for beginners. That comes from the design feature of the divided shoe soles and protecting the ankle of the axis leg. With the results and analysis, the direction for design optimization of ballet shoes is suggested. Consequently, this research is about the verification of sports equipment using computer simulation with the musculoskeletal model from a scientific viewpoint of biomechanics.

As the energy efficiency demands for future buildings become increasingly stringent, preliminary assessments of energy consumption are mandatory. These are possible only through numerical simulations, whose reliability crucially depends on boundary conditions. We therefore investigate their role in numerical estimates for the usage of geothermal energy, performing annual simulations of transient heat transfer for a building employing a geothermal heat pump plant and energy piles. Starting from actual measurements, we solve the heat equations in 2D and 3D using COMSOL Multiphysics and IDA-ICE, and discover a negligible impact of the multiregional ground surface boundary conditions. Moreover, we verify that the thermal mass of the soil medium induces a small vertical temperature gradient on the piles surface. We also find a roughly constant temperature on each horizontal cross-section, with nearly identical values if the average temperature is integrated over the full plane or evaluated at one single point. Calculating the yearly heating need for an entire building we then show that the chosen upper boundary condition affects the energy balance dramatically. Using directly the pipes’ outlet temperature induces a 54% overestimation of the heat flux, while the exact ground surface temperature above the piles reduces the error to 0.03%.

As education becomes more and more important in creating improved societies, many people who do not have access to it are falling behind. To help them catch up, many people, especially those in rural areas and developing countries, are turning to different methods of self-learning, especially those that utilize cheap technology and use interactive methods to teach. Our empirical study tests the effectiveness of an e-learning system that utilizes newer, less tested forms of interactivity and could potentially be used in these areas as a self-learning system and compares it to non-interactive video and textbook self-learning in two different topics. The results of the experiment showed that the increased interactivity provided by the e-learning system achieved significantly better learning performance over both non-interactive video and textbook self-learning. It was also found that students who learned through non-interactive video performed significantly better than those who used textbooks for self-learning.

The efficiency of data sorting algorithms is the key aspect which determines the speed of data processing and searching. The best known efficiency of sorting algorithm has been Log (N) if there are N terms. All of the well-known sorting algorithms use various techniques to sort data. The basis for most of these are comparing the data terms with each other. In this manuscript, we are introducing a new approach for sorting data. This method is postulated to have the highest efficiency ever achieved by any of the sorting algorithms. We achieve this by sorting data without comparing the data terms. Or achieving results of data comparison without comparing the terms explicitly.

Some evidence supports the influence of the implant macro-design and primary stability. Additionally, tactile perception can be used to assess implant stability when placing the implant. This research aimed to quantify the primary and secondary stability of three implant systems with two different macro geometries (cylindrical and conical) determined through the insertion torque and the implant stability quotient (ISQ) at the moment of implant placement as a function of implant-related factors (length, width, dental arch, and implant location in the arch), intraoperative factors (bone density determined subjectively by the clinician's tactile perception), and patient-related factors (age, gender and bone density determined objectively in the cone beam computed tomography (CBCT). Methods: 102 implants of three implant systems with two different macro geometries (conical and cylindrical) were placed in 53 patients. The insertion torque, the ISQ at the implant placement (ISQ0), and bone quality according to the clinician's tactile sensation were recorded on the day of the surgery. After a three-month healing period, the ISQ was re-evaluated (ISQ3). Results: Cylindrical implants exhibited significantly higher insertion torque and ISQ at the moment of the surgery and after three months than conical implants. Cylindrical implants also showed significantly lower indices of tactile evaluation of bone quality during the implant placement surgery. However, no differences were demonstrated in the bone density measured objectively in the CBCT. (4) Conclusions: The cylindrical implants achieved the highest values for primary stability (Ncm and ISQ) and secondary stability (ISQ after three months). Insertion torque was the variable that most influenced ISQ on the day of the surgery. Implant location (incisors-canines, bicuspids-molars) and the implant macro geometry were the variables that most influenced the secondary stability (ISQ at three months).