The rapid growth of the Information and Communications Technology (ICT) sector requires additional infrastructure, such as more micro-datacenters and telecom stations, to support the higher internet speeds and low latency requirements of 5G net-works. The increased power requirements of the new ICT technologies necessitate the proposal of new power supplies in an attempt to retain the increase in energy demand and running costs. This work provides an in-depth theoretical analysis on the losses of the individual stages of commercially available PSU and proposes a new multicell PSU, Buck-PFC converter, which offers a higher overall efficiency at varying load levels. The theoretical results are verified using simulation results, via PSIM Thermal Module, and using experimental data. The results indicate that multi-cell structures can improve the overall PSU ef-ficiency by 1.2% at 50% rated power and more than 2.1% at full power. Finally, taking into consideration the economic implica-tions of this study, it is shown that the proposed multicell structure may increase the PSU costs by 10.78% but the payback pe-riod is in the order of just 3.3 years.

Substantial research is required to ensure that micro-mobility ride sharing provides a better fulfillment of user needs. This study proposes a novel crowdsourcing model for the ride-sharing system where light vehicles such as scooters and bikes are crowdsourced. The proposed model consists of three entities: suppliers, customers, and a management party responsible for receiving, renting, booking, and demand matching with offered resources. It can allow suppliers to define the location of their private e-scooters/e-bikes and the period of time they are available for rent. Using a dataset of over 9 million e-scooter trips in Austin, Texas, we ran an agent-based simulation six times using three maximum battery ranges (i.e., 35, 45, and 60 km) and different numbers of e-scooters (e.g., 50 and 100) at each origin. Computational results show that the proposed model is promising and might be advantageous to shift the charging and maintenance efforts to a crowd of suppliers.

Minerals play many important functions in plant and animal metabolism. Therefore, we investigated the concentration of Se and other minerals and their relationships in soils and fodder plants in Kosovo. Seventy-three samples of each soil and fodder plants (grass, maize, and wheat) from 30 farms were collected. Both soil and plant samples, after processing and digestion, were analyzed for mineral concentration by ICP-MS. Mineral concentrations in soil and fodder crops, and the best predicting/explanatory models for micro minerals concentration, achieved by stepwise linear regression, are presented. Results showed very low concentration of Se in most of the soil and all fodder samples. In addition, the concentration of Co, Zn and Fe was not sufficient to satisfy requirements for all categories of farm animals. Plant Se concentration showed a positive relationship with Se concentration in soils. Plant Zn, Mo, Mn, Fe and Pb, in general, showed no significant relationship with their concentration in soil, while plant Co and Cd showed positive relationship only in maize, and Cu in wheat grain. Among the soil properties, pH had the highest effect on the concentrations of Co, Mo, Mn, Cd and Pb in fodder crops.

A phosphate/molybdate and cerium-modified phosphate/molybdate conversion coatings were deposited on a carbon steel surface and their protective and self-healing abilities were evaluated. Surface morphology and inner structure of the coatings were examined using FE-SEM-FIB and TEM techniques, chemical composition and element distribution depth profiles in conversion layers were determined using EDX measurements, whereas XPS was applied for the analysis of Mo and Ce oxidation states. Voltammetric measurements and EIS were performed to assess the corrosion behavior of the samples. The higher protective and stronger self-healing abilities were found for phosphate/molybdate/cerium conversion coating deposited in a sulphate-containing solution. This was attributed to higher values of both: total cerium and Ce(IV) content in the conversion layer as well as to lower number of structural defects in the coating. It was demonstrated that the micro-structural characteristics of protective coatings are also important in determining self-healing abilities.

Biological micro-dissection has a wide range of applications in the field of molecular pathology. The current laser-assisted dissection technology is expensive, and laser radiation can lead to sample contamination. As an economical and pollution-free micro-dissection method, piezoelectric ultrasonic micro-dissection has a wide application prospect. However, the performance of the current piezoelectric ultrasonic micro-dissection technology is unsatisfactory. In this paper, a novel piezoelectric ultrasonic micro-dissection device based on a flexure mechanism is proposed in order to solve the problems of low dissecting precision and excessive wear of the dissecting needle caused by the harmful lateral vibration of the current piezoelectric ultrasonic micro-dissection device. By analyzing the flexibility of flexure hinge, the type of flexure beam and the optimal design parameters are determined. Through comparing the harmonic response simulation analysis of the micro-dissection device based on a flexure mechanism and the traditional micro-dissection device without the flexure mechanism, the newly designed micro-dissection device achieves the best vibration effect when the driving frequency is 28kHz, compared with the traditional micro-dissection device, the lateral vibration suppression effect is improved by 68%. Then, based on the 3D printing technology, a prototype of a novel micro-dissection device was produced, and its performance was tested. It was found that the flexure mechanism did indeed suppress the lateral vibration of the needle tip. Finally, the experiments of 5μm thick paraffin-embedded rat liver sections were carried out, and the effects of different dissecting parameters on the dissecting effect were analyzed, and the optimal dissecting parameters were obtained. By comparing the dissecting effects of the tissue sample and the wear condition of the needle tip between the novel micro-dissection device and the traditional micro-dissection device under their optimal dissecting parameters, it is proved that the suppression of harmful lateral vibration not only significantly improves the dissecting effect, but also improves the service life and durability of the dissecting needle, which is beneficial to reduce the equipment costs.

The flipped classroom is gaining prominence as an active learning pedagogy to engage a new generation of students. However, all courses do not lend themselves to a fully flipped design and instructors are often reluctant to flip lectures. In this study, I experimented with a “partial” flipped classroom design in a first-year undergraduate economics course. In this partial flipped format, traditional lectures were substituted with micro-lectures and the remaining class time was devoted to activities like quizzes, group work and student presentations. The full lectures were panopto recorded and put up on the e-learning site, Blackboard. This format enabled me to combine the benefits of a traditional lecture with a flipped classroom design. In order to evaluate the effectiveness of the partial flipped classroom format, I compared the final exam scores of students in the partial flipped classroom with those in the control group, which followed a traditional lecture-based approach. The key results from the analysis revealed that students in the partial flipped classroom performed better in the final exams vis-à-vis students in the traditional classroom format. Furthermore, the partial flipped classroom format was associated with lower odds of students failing in the module. This format also resulted in better student engagement, more flexibility and enhanced student-tutor interaction within the classroom.

The Neotropical region is one of the most diverse regions of the globe in terms of macro-organismic species. Regarding the microbial world, however, little is known about the diversity and biogeography patterns of micro-organisms in the Neotropics. In this context, the study of several microbial taxonomic groups is still missing and/or incomplete, such as the protists. Our goal here was to summarize the available information of Neotropical protists, focusing on molecular data from environmental continental samples, to explore what these data evidence on their ecology and biogeography. For this, we reviewed the findings from all articles that focused on or included the terrestrial protists using metabarcoding approach and identified the gaps and future perspectives in this research field. We found that Neotropical protists diversity patterns seem to be, at least in part, congruent with that of macro-organisms and, different than plants and bacteria, just weakly explained by environmental variables. We argue that studies with standardized protocols including different biomes are necessary to fully characterize the ecology and biogeography on Neotropical protists. Furthermore, dismember evolutionary lineages and functional guilds of protists are important to better understand the relationship between diversity, dispersal abilities and functionality of particular taxa of protists in their habitats.

The evolution of metals micro/nano-structure upon severe plastic deformation (SPD) is still far to be theoretically explained, while experimental datasets are persistently growing for several decades. Major problem associated with understanding of SPD is related to a fact that the latter is a synergetic product of several competing physical effects which alter the material micro/nano-structure. In attempt to find deformational boundaries, where predominantly one mechanism determines the micro/nano-structure, in this paper we propose a continuous piecewise model for the analysis of experiments on material hardness vs strain of SPD processed materials. The novelty of this approach lies in its ability to find, as free-fitting parameters, the strain breakpoints which separate different micro/nano-structure modes generated upon SPD process. The model is applied to analyse experimental data for polycrystalline samples of pure iron and two distinctive strain breakpoints are revealed with good accuracies. This finding is in a good agreement with our earlier results on TEM microscopy studies on pure iron polycrystals after SPD treatment.

This study evaluated the mechanical strengths of three types of orthodontic micro-implants by analyzing their structural configurations. Thirty micro-implants of three types (diameter 1.5 mm, Types A, B, C) were assessed. All micro-implants were manually driven into artificial bones at an 8-mm depth. The insertion torque (IT), pullout strength (PS), and gripping volume (GV) of each type were measured. Intergroup comparisons and intragroup correlation were investigated by statistical analysis. Type B had the greatest inner–outer diameter ratio (0.67), and Type A had the smallest (0.53). The IT of Type A (5.26 Ncm) was significantly (p = 0.038) lower than that of Type C (8.8 Ncm). There was no significant difference in the pullout strength (p = 0.868). The GV of Type A (9.7 mm3) was significant (p < 0.01) greater than Type C (8.4 mm3). Type C was significant (p < 0.01) greater than Type B (7.2 mm3). Spearman’s rho rank correlation test showed that PS of Type B was correlated significantly with GV. In conclusion, the design of thread and its GV were the important factors on the mechanical strengths of micro-implant.

The Wolfram (W), Silicium (Si) and Molybdenum (Mo) doped Co-Cr biomedical alloy were fabricated by additive manufacturing method, which is part of powder metadology. The mixture of Wolfram (W), Silicium (Si), Chrome (Cr) and Cobalt (Co) alloy is known good wear and corrosion resistance among of biomedical applications. By addition of Molybdenum (Mo) into the structure of alloy, the structure become more stbale also increase the corrosion and wear resistance. In addition, the effects of secondary annealing process on the alloy were investigated. The microstructure of the produced alloy was analyzed by X-ray diffraction method XRD, Energy Dispersive X-Ray Analysis EDX and scanning electron microscope SEM. Moreover, Electrochemical corrosion test, micro hardness and density measurements were performed to investigate the mechanical properties of the alloy. As a result of the analyzes, the effects of Molydenum (Mo) doped and secondary annealing on the microstructure and mechanical properties of bioalloying were determined.

Optical micro-angiography (OMAG) is a new method of detecting flow rate and widely used for in vivo imaging. Although OMAG can distinguish between flowing and stationary parts, it cannot obtain accurate flow rate information. This study proposed a range formula for OMAG and the ultrahigh-sensitivity OMAG (UHS-OMAG) method to quantify the measurement range of an entire system. The parameters of the angle between beam scanning and flow directions, the angular velocity of the galvanometer, and the offset of incident light were introduced, and a formula for calculating the range was derived. Experiments were conducted to measure fine and ultra-fine flow rates by using OMAG and UHS-OMAG methods. The minimum measured flow rate was approximately 30 μm/s, and the maximum measured flow rate was approximately 8 mm/s. Experimental results are in good agreement with the preset results.

Natural events such as floods, fires, tsunamis, earthquakes and others have nowadays caused serious damage to human beings and nature. The precise detection of these natural events and especially the earthquake has nowadays become the focus of many computer and geoscientific researchers. Computer science and machine learning algorithms have revolutionized early detection and prediction of these events. Hence, a fuzzy method has been initially used in this article to enhance the authenticity of data based on application of effective variables and then combination of neural network algorithms of the MLP perceptron and radial network of RBF in form of a collective learning system in order to more accurately identify seismic events on a small scale. It was observed after simulating the proposed method that the proposed method has significantly improved based on actual error and root-mean-square error (RMSE) criteria compared to basic methods.

Ti and its alloys are the most commonly used materials for biomedical applications. However, bacterial infection after implant placement is still one of the significant rising complications. Therefore, the application of the antimicrobial agents into implant surfaces to prevent implant-associated infection has attracted lots of attention. Scientific papers have shown that inorganic antibacterial metal element (e.g. Ag, Cu, Zn) can be introduced to implant surfaces with the addition of metal nanoparticles or metallic compounds into electrolyte via micro-arc oxidation (MAO) technology. In this review, the effects of the composition and concentration of electrolyte and process parameters (e.g. voltage, current density, oxidation time) on morphological characteristics (e.g. surface morphology, bonding strength), antibacterial ability and biocompatibility of MAO antimicrobial coating were discussed in detail. Anti-infection and osseo-integration can be simultaneously accomplished with the selection of the proper antibacterial elements and operating parameters. Besides, MAO assisted by magnetron sputtering (MS) to endow Ti-based implant materials with superior antibacterial ability and biocompatibility was also discussed. Finally, the development trend of MAO technology in the future was forecasted.

The ability to detect the presence as well as classify the activities of individuals behind visually obscuring structures is of significant benefit to police, security and emergency services in many situations. This paper presents the analysis from a series of experimental results generated using a through-the-wall (TTW) Frequency Modulated Continuous Wave (FMCW) C-Band radar system named Soprano. The objective of this analysis was to classify whether an individual was carrying an item in both hands or not using micro-Doppler information from a FMCW sensor. The radar was deployed at a standoff distance, of approximately 0.5 m, outside a residential building and used to detect multiple people walking within a room. Through the application of digital filtering, it was shown that significant suppression of the primary wall reflection is possible, significantly enhancing the target signal to clutter ratio. Singular Value Decomposition (SVD) signal processing techniques were then applied to the micro-Doppler signatures from different individuals. Features from the SVD information have been used to classify whether the person was carrying an item or walking free handed. Excellent performance of the classifier was achieved in this challenging scenario with accuracies up to 94%, suggesting that future through wall radar sensors may have the ability to reliably recognize many different types of activities in TTW scenarios using these techniques.

Microscopic and ultra-microscopic vascular sutures are indispensable in the surgical procedures such as arm transplantation and finger reattachment. The state of the blood vessels after suturing, such as vascular patency, narrow, and blocked, determines the success rate of the operation. If we can grasp the golden window period after blood vessel suture and before muscle tissue suture to achieve accurate and objective assessment of blood vessel status, it can not only reduce medical costs but also improve social benefits. Doppler optical coherence tomography enables high-speed, high-resolution imaging of biological tissues, especially microscopic and ultra-microscopic blood vessels. Using Doppler optical coherence tomography to image the sutured blood vessels, not only the three-dimensional structure of the blood vessels, but also the blood flow information can be obtained. By extracting the contour of blood vessel wall and the contour of blood flow area, the three-dimensional shape of blood vessel can be reconstructed in three dimensions, which provides parameter support for the assessment of blood vessel status. In this work, we propose a neural network-based multi-classification deep learning model that can simultaneously and automatically extract blood vessel boundaries from Doppler OCT vessel intensity images and the contours of blood flow regions from corresponding Doppler OCT vessel phase images. Compared with the traditional random walk segmentation algorithm and cascade neural network method, the proposed model has better performance. This method is easier to realize system integration and has great potential for clinical evaluation. It is expected to be applied to the evaluation of microscopic and ultra-microscopic vascular status in microvascular anastomosis.

The fusion of global contextual information with local cropped block details is crucial for segmenting ultra-high resolution images. In this study, we introduce a novel fusion mechanism termed Global-Local Deep Fusion (GL-Deep Fusion) based on an enhanced transformer architecture, which efficiently integrates global contextual information and local details. Specifically, we propose the Global-Local Synthesis Networks (GLSNet), a dual-branch network where one branch processes the entire original image, while the other branch handles cropped local patches as input. The feature fusion of different branches in GLSNet is achieved through GL-Deep Fusion, significantly enhancing the accuracy of ultra-high resolution image segmentation. Particularly effective is GLSNet in identifying tiny overlapping items. To optimize GPU memory utilization, we meticulously design a dual-branch architecture that proficiently leverages the features it extracts, seamlessly integrating them into the enhanced transformer framework of GL-Deep Fusion. Extensive experiments conducted on challenging benchmarks, including DeepGlobe and Vaihingen datasets, demonstrate that GLSNet achieves a new state-of-the-art performance in terms of GPU memory utilization and segmentation accuracy tradeoff.

In recent years, the scientific and technological developments led to an explosion of available videos on the web, increasing the necessity of fast and effective video analysis and summarization. Video summarization methods aim to generate a synopsis by selecting the most informative parts of the video content. The user’s personal preferences, often involved in the expected results, should be taken into account in the video summaries. In this paper, we provide the first comprehensive survey on personalized video summarization relevant to the techniques and datasets used. In this context, we classify and review personalized video summary techniques based on the type of personalized summary, on criteria, on the video domain, on the source of information, on the time of summarization, and on the machine learning technique. Depending on the type of methodology used by the personalized video summarization techniques for the summary production process, we classify the techniques into five major categories, which are feature-based video summarization, key frame selection, shot selection-based approach, video summarization using trajectory analysis, and personalized video summarization using clustering. We also compare personalized video summarization methods and present 37 datasets used to evaluate personalized video summarization methods. Finally, we analyze opportunities and challenges in the field and suggest innovative research lines.

Semantic segmentation of high-resolution remote sensing images provides detailed and precise feature information, playing a pivotal role in decision-making and analysis in sectors such as water management, agriculture, military, and environmental protection. However, most methods merely combine features from various branches directly, without a mechanism for spatial location feature screening, and treat all extracted features as equally important. To overcome these limitations, we introduce a novel spatially adaptive interaction network (SAINet) for dynamic interaction across different features in remote sensing semantic segmentation task. Specifically, we propose a spatial refined module that leverages local context information to filter spatial locations and extract salient regions. Following this, we introduce an innovative spatial interaction module that uses a spatial adaptive modulation mechanism to dynamically select and allocate spatial position weights. This facilitates interaction between local salient areas and global information, allowing the network to focus more on relevant regions. This flexible approach enables the network to capture more informative features, thereby enhancing segmentation accuracy. Experiments conducted on the DeepGlobe, Vaihingen, and Potsdam public datasets confirm the effectiveness and capability of SAINet. Our code and models will be publicly available

Femur length (FL) is a biometric measurement of ultrasound images used to identify the growth patterns and abnormalities of the foetus. Automatic segmentation of FL can improve the efficiency and convenience of inexperienced users. The femur region in a low-cost ultrasound image is a small area with low contrast intensity compared with the non-femur region. This study proposed a fully automated framework for segmenting and measuring the FL in a portable ultrasound image. We utilized statistical modeling, employing Gaussian mixture functions for thresholding to extract the femur area from the background. We also used the localizing region-based active contour method to segment the femur region accurately. We also proposed a refinement step in this framework to obtain a more accurate femur area in the ultrasound image. Because the length and position of the femur are the main factors affecting foetal biometric measurement accuracy, we not only evaluated segmentation results using region-based methods, such as sensitivity, specificity, and dice similarity. We also applied the FL measurement approach to evaluate the angle and length accuracy relative to the ground truth. In terms of region-based segmentation performance, the proposed method provided the best average performance with a sensitivity of 0.78, specificity of 0.87, and dice similarity of 0.81. For FL measurement performance, the proposed framework achieved an average angle accuracy of 0.99, distance accuracy of 0.88, and length accuracy of 0.93.

In this paper, we present a general version of polygonal fitting problem called Unconstrained Polygonal Fitting (UPF). Our goal is to represent a given 2D shape S with an N-vertex polygonal curve P with a known number of vertices, so that the Intersection over Union (IoU) metric between S and P is maximized without any assumption or prior knowledge of the object structure and the location of the N-vertices of P that can be placed anywhere in the 2D space. The search space of the UPF problem is a superset of the classical polygonal approximation (PA) problem, where the vertices are constrained to belong in the boundary of the given 2D shape. Therefore, the resulting solutions of the UPF may better approximate the given curve than the solutions of the PA problem. For a given number of vertices N, a Particle Swarm Optimization (PSO) method is used to maximize the IoU metric, which yields almost optimal solutions. Furthermore, the proposed method has also been implemented under the equal area principle so that the total area covered by P is equal to the area of the original 2D shape to measure how this constraint affects IoU metric. The quantitative results obtained on more than 2,800 2D shapes included in two standard datasets quantify the performance of the proposed methods and illustrate that their solutions outperform baselines from the literature.

Accurate weight measurement is pivotal for monitoring the growth and well-being of cattle. However, the conventional weighing process, which involves physically placing cattle on scales, is labor-intensive and distressing for the animals. Hence, the development of automated cattle weight prediction techniques assumes critical significance. This study proposes a weight prediction approach for Korean cattle using 3D segmentation-based feature extraction and regression machine learning techniques from incomplete 3D shapes acquired from real farm environments. In the initial phase, we generated mesh data of 3D Korean cattle shapes using a multiple-camera system. Subsequently, deep learning-based 3D segmentation with the PointNet network model was employed to segment two dominant parts of the cattle. From these segmented parts, three crucial dimensions of Korean cattle were extracted. Finally, we implemented five regression machine learning models (CatBoost regression, LightGBM, Polynomial regression, Random Forest regression, and XGBoost regression) for weight prediction. To validate our approach, we captured 270 Korean cattle in various poses, totaling 1190 poses of 270 cattle. The best result was achieved with mean absolute error (MAE) of 25.2 kg and mean absolute percent error (MAPE) of 5.81% using the random forest regression model.

Nowadays, semantic segmentation is increasingly used in exploration by underwater robots, for example in autonomous navigation, so that the robot can recognise the nature and elements of its environment during the mission and act according to this classification to avoid collisions. Other applications can be found in the search for archaeological artefacts, in the inspection of underwater structures or in species monitoring. Therefore, it is necessary to try to improve the performance in these tasks as much as possible. To this end, we compare some methods for improving image quality and for data augmentation and test whether higher performance metrics can be achieved with both strategies. The experiments are performed with the SegNet implementations and the SUIM dataset with 8 common underwater classes to compare the obtained results with the already known ones. The results obtained with both strategies show that they are beneficial and lead to better performance results by achieving a mean IoU of 56% and an increased overall accuracy of 81.8%. The single result shows that there are 5 classes with an IoU value above 60% and only one class with an IoU value below 30%, which is a more reliable result and easier to use in real contexts.

As we all know, many more dynamic objects appear almost continuously in real world, which are immensely able to impair the performance of the majority of vision-based SLAM systems that are based on the static-world assumption. In order to improve the robustness and accuracy of visual SLAM in the high dynamic environment, a real-time and robust stereo SLAM system for dynamic scenes was proposed. To weaken influences of dynamic content, the moving object detection method was put forward in our visual odometry, then the semantic segmentation network was combined into our stereo SLAM to extract pixel-level contours of dynamic objects. Then influences of dynamic objects were extremely weaken and the performance of our system was increased markedly in dynamic, complex and crowed city spaces. Experiment with both on KITTI Odometry dataset and in a real-life scene, the results show that our method can dramatically decrease the tracking error or drift, improve the robustness and stability of our stereo SLAM in high dynamic outdoor scenarios.

Recently, new semantic segmentation and object detection methods have been proposed for direct processing of three-dimensional (3D) LiDAR sensor point clouds. LiDAR can produce highly accurate and detailed 3D maps of natural and man-made environments and is used for sensing in many contexts due to its ability to capture more information and its robustness to dynamic changes in the environment. In addition, the cost of LiDAR sensors has decreased in recent years, which is an important factor for many application scenarios. The challenge with 3D LiDAR sensors like the Velodyne HDL-64E S2 is that they can output large 3D data at up to 1,300,000 points per second, which is difficult to process in real time when applying complex algorithms and models for efficient semantic segmentation. Most existing approaches are either only suitable for relatively small point clouds or rely on computationally intensive sampling techniques to reduce their size. As a result, most of these methods do not work in real-time in realistic field robotics application scenarios, making them unsuitable for practical applications. Systematic point selection is a possible solution to reduce the amount of data to be processed, but although it is memory and computationally efficient, it selects only a small subset of points, which may result in important features being missed. To address this problem, we propose a new approach to semantic segmentation in forestry that uses a systematic sampling method in which the local neighbors of each point are retained to preserve geometric details. Our approach has been shown to process up to 1 million points in a single pass. It outperforms the state of the art in efficient semantic segmentation in large datasets such as Semantic3D. We also present a preliminary study on the performance of LiDAR-only data, i.e., intensity values from LiDAR sensors without RGB values for semi-autonomous robot perception.

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.

Vehicle identification is an important task in traffic monitoring because it allows for efficient inference and provides a cause for action. Vehicle classification via deep learning and other approaches such as segmentation is a critical tool for re-identification. In this paper, instance segmentation is used to identify vehicle makes with license plate detection, allowing for better unique vehicle recognition for re-identification. A dataset is annotated and modified, for example, by segmenting it with polygonal bounding boxes that capture the vehicle's unique frontal features. In addition, license plate localization is performed. The results showed improved classification as well as a high mAP for the dataset when compared to previous approaches based on CNN and deformed CNN. Furthermore, a deep residual network and fully connected layer-based classification were utilized as the backbone for feature representation. Instance segmentation detects objects by segmenting and classifying regions of interest. The imbalance in the dataset is resolved using a mosaic-tiled approach, which produces greater precision than other approaches.

Translation of basic animal research to find effective methods of diagnosing and treating human neurological disorders requires parallel analysis infrastructures. Small animals such as mice provide exploratory animal disease models. However, many interventions developed using small animal models fail to translate to human use due to physical or biological differences. Recently, large-animal minipigs have emerged in neuroscience due to both brain similarity and economic advantages. Medical image processing is a crucial part of research as it allows researchers to monitor their experiments and understand disease development. However, although many algorithms are created and optimized for MR analysis of human data, those tools are not directly applicable or sufficiently sensitive to measure minipig data. In this work, we propose PigSNIPE - a pipeline for the automated handling, processing, and analyzing of large-scale data sets of minipig MR images. The pipeline allows for image registration, AC-PC alignment, landmark detection, skull stripping, brainmasks and intracranial volume segmentation (DICE 0.98), tissue segmentation (DICE 0.82), and caudate-putamen brain segmentation (DICE 0.8) in under two minutes. To the best of our knowledge, this is the first automated pipeline tool aimed at large animal images.

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.

In order to solve the labor-intensive and time-consuming problem in the process of measuring yak body ruler and weight in yak breeding industry in Qinghai Province, a non-contact method for measuring yak body ruler and weight was proposed in this experiment, and key technologies based on semantic segmentation, binocular ranging and neural network algorithm were studied to boost the development of yak breeding industry in Qinghai Province. Main conclusions: (1) Study yak foreground image extraction, and implement yak foreground image extraction model based on U-net algorithm; select 2263 yak images for experiment, and verify that the accuracy of the model in yak image extraction is over 97%. (2) Develop an algorithm for estimating yak body ruler based on binocular vision, and use the extraction algorithm of yak body ruler related measurement points combined with depth image to estimate yak body ruler. The final test shows that the average estimation error of body height and body oblique length is 2.6%, and the average estimation error of chest depth is 5.94%. (3) Study the yak weight prediction model; select the body height, body oblique length and chest depth obtained by binocular vision to estimate the yak weight; use two algorithms to establish the yak weight prediction model, and verify that the average estimation error of the model for yak weight is 10.7% and 13.01% respectively.

The impact of the cell community on its individual components in the prokaryotic realm is often overlooked. However, in the case of intracellular pathogens, where each infected cell can be considered as a single community, understanding how a population adapts to its environment to evolve and successfully propagate is key. Chlamydia infections are characterised by a silent propagation of the bacteria within individual hosts and the wider population. Chlamydia are strict intracellular pathogens residing within a specialised membrane-bound compartment called the inclusion. The life cycle of Chlamydia involves altering between the invasive elementary bodies (EBs) and replicative reticulate bodies (RBs). We have used cryo-soft X-ray tomography to observe individual inclusions, combining excellent resolution (40 nm) and large volume imaging (up to 16 µm). Combined with a semi-automated segmentation pipeline, we were able to consider each inclusion as an individual bacterial niche. Within the inclusion, we identified and classified different forms of the bacteria and confirmed the recent finding that RBs have a variety of volumes (small, large and abnormal). Moreover, we demonstrate that the proportions of these different RB forms depend on the bacterial concentration in the cell demonstrating the impact of the group on its individual component. We conclude that each inclusion operates as an autonomous community which regulates the characteristics of individual bacteria within the inclusion

Segmentation of Magnetic Resonance Images (MRI) of abdominal organs is useful for analysis prior to surgical procedures and for further processing. Deep Learning (DL) has become the standard, researchers have proposed improvements that include multiple views, ensembles and voting. Loss function alternatives, while being crucial to guide automated learning, have not been compared in detail. In this work we analyze limitations of popular metrics and their use as loss, study alternative loss variations based on those and other modifications and search for the best approach. An experimental setup was necessary to assess the alternatives. Results for the top scoring network and top scoring loss show improvements between 2 and 11 percentage points (pp) in Jaccard Index (JI), depending on organ and patient (sequence), for a total of 22 pp over 4 organs, all this being obtained just by choosing the best performing loss function instead of cross-entropy or dice. Our results apply directly to MRI of abdominal organs, with important practical implications for other architectures, as they can be applied easily to any of them. They also show the worth of variants of loss function and loss tuning, with future work needed to generalize and test in other contexts.

It has remained a hard nut for years to segment sonar images, most of which are noisy images with inevitable blur after noise reduction. For the purpose of solutions to this problem, a fast segmentation algorithm is proposed on the basis of the gray value characteristics of sonar images. This algorithm is endowed with the advantage in no need of segmentation thresholds to be calculated. To realize this goal, it follows the undermentioned steps: first, calculate the gray matrix of the fuzzy image background. After adjusting the gray value, segment the region into the background region, buffer region and target regions. After filtering, reset the pixels with gray value lower than 255 to binarize images and eliminate most artifacts. Finally, remove the remaining noise from images by means of morphological image processing. The simulation results of several sonar images show that the algorithm can segment the fuzzy sonar image quickly and effectively, with no problem of incomplete image target shape. Thus, the stable and feasible method is testified.

This article presents a new method of segmenting images with gray levels. The method is based on determining several thresholds for separation of gray levels. The determination of these thresholds is done using the certainty of the neutrosophic information. The concept of this method can be stated simply: to choose the local maximums for the neutrosophic certainty.

The cultural and historical heritage of a city is a major resource to attract tourists. Therefore, reaching out to perceive and identify the characteristics of persons visiting a locality attracted by their property is relevant for the purpose of better meeting their expectations and needs. This research focuses on knowing the perceptions, motivations and satisfaction of women visiting Cordoba (Spain). Thus, on the basis of the questionnaire carried out on women visiting Cordoba during the months of June and November 2019, a statistical analysis has been made. Using various multivalent case-grouping techniques, tourist segments with similar perceptions of cultural heritage have been detected. Moreover, non-parametric statistical techniques have showed up significant differences between the valuations obtained in the various segments. This analysis has exposed a segment of women who, known as absorbent tourists, are characterized by the high cultural motivation to visit the city of Cordoba linked to the heritage they have visited. The conclusions obtained should be useful in adjusting the city's tourist supply to the specific demand of a population sector such as women visiting the city.

3D-mapping-aided (3DMA) global navigation satellite system (GNSS) positioning that improves positioning performance in dense urban areas has been under development in the recent years, but it still faces many challenges. This paper details a new algorithm that explores the potential of using building boundary for positioning. Rather than applying complex simulations to analyze and correct signal reflections by buildings, the approach utilizes a convolutional neural network to differentiate between the sky and building in a sky-pointing fisheye image. A new skymask matching algorithm is then proposed to match the segmented fisheye images with skymasks generated from a 3D building model. Each matched skymask holds a latitude and longitude coordinate to determine the precise location of the fisheye image. The results are then compared with the conventional GNSS and advanced 3DMA GNSS positioning methods. The aims of the proposed algorithm are to increase positioning and heading accuracy in a rich urban environment.

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.

Worldwide, hundreds of thousands of people are diagnosed with kidney cancer and this disease is more common in developed and industrialized countries. Previously, kidney cancer was known as an elderly disease and was seen in people over a certain age; nowadays it is also seen in younger individuals and it is easier to diagnose thanks to new radiological diagnostic methods. A kidney tumor is a type of cancer that is extremely aggressive and needs surgical treatment rapidly. Today, approximately 30% of patients diagnosed with kidney cancer are unfortunately noticed at the stage of metastatic disease (spread to distant organs). The biggest factor that pushes us to this study is that kidney tumors progress unlike other cancer types with little or no symptoms. Therefore, conducting such studies is extremely important for early diagnosis. In this study, we compare the Unet3D models in order to help people who are dealing with difficulties in the diagnosis of kidney cancer. Unet, Unet+ResNet and Unet++ models were compared for image segmentation.

Clinically, knowing the number of red blood cells (RBCs) and white blood cells (WBCs) helps doctors to make the better decision on accurate diagnosis of numerous diseases. The manual cell counting is a very time-consuming and expensive process, and it depends on the experience of specialists. Therefore, a completely automatic method supporting cell counting is a viable solution for clinical laboratories. This paper proposes a novel blood cell counting procedure to address this challenge. The proposed method adopts SegNet - a deep learning semantic segmentation to simultaneously segment RBCs and WBCs. The global accuracy of the segmentation of WBCs, RBCs, and the background of peripheral blood smear images obtains 89% when segment WBCs and RBCs from the background of blood smear images. Moreover, an effective solution to separate grouped or overlapping cells and cell count is presented using Euclidean distance transform, local maxima, and connected component labeling. The counting result of the proposed procedure achieves an accuracy of 93.3% for red blood cell count using dataset 1 and 97.38% for white blood cell count using dataset 2.

Springs play a significant role in maintaining hydrological balance in the mountain ecosystem. The communities living in the mountain tops rely entirely on spring water for their daily needs. In recent decades, spring water discharges have decreased drastically in the Himalayan regions and become seasonal. Remote sensing and geographical information system techniques have proved to be essential for understanding the sustainable development of groundwater, particularly where people rely solely on spring water in the mountainous regions of the Himalayas. This study employs the Analytical Hierarchy Process (AHP) to identify groundwater potential zones. It involves overlaying seven thematic layers concerning elements of physical features and land-use/land-cover of the region, using the weighted overlay toolbox in ArcGIS, with each layer being assigned a weight based on its importance. Based on the results, groundwater potential zones have been classified into five categories: poor, fair, good, very good, and excellent. The study found that poor groundwater potential zones cover 1.1% of the area, fair zones cover 27.8%, good zones cover 23.3%, very good zones cover 26.6%, and excellent zones cover 21.2% of the total area. The excellent to very good potential zones are associated with perennial springs that have higher discharge (4.30-30.92 l/m), lineaments, rainfall, forested land, and porous soils, favoring the potentiality of the springs. The fair and poor groundwater potential zones are associated with seasonal flowing springs, consisting of barren land, less rainfall, and low fracture density, which influence the potentiality of groundwater. The validation of the groundwater potential zones indicated an Area Under Curve (AUC) value of 0.88, which shows good agreement with observed spring water locations. The identified groundwater potential zones are valuable for prioritizing the area for the sustainable development of spring water. Particularly, it is helpful for policymakers and government bodies to be involved in developing strategies for sustainable water management at the micro-watershed level and safeguarding spring water resources using integrated watershed management in the headwater region of the Himalayas.

The aim of this research is to investigate the influence of model height employed in the deep drawing of orthodontic aligner sheets on force transmission and aligner thickness. Forty sheets (Zendura FLX) were thermoformed over four models of varying heights (15, 20, 25, and 30 mm). Normal contact force generated on the facial surface of the upper right central incisor (Tooth 11) was measured using pressure-sensitive films. Aligner thickness around Tooth 11 was measured at five points. A digital caliper and a micro-computed tomography (µ-CT) were employed for thickness measurements. The normal contact force exhibited an uneven distribution across the facial surface of Tooth 11. Model 15 displayed the highest force (88.9±23.2 N), while Model 30 exhibited the lowest (45.7±15.8 N). The force distribution was more favorable for bodily movement with Model 15. Thickness measurements, conducted using a digital caliper and µ-CT, revealed substantial thinning of the aligner after thermoforming. This thinning was most pronounced at the incisal edge (50% of the original thickness) and least at the gingivo-facial part (85%). Additionally, there was a progressive reduction in aligner thickness with increasing model height, which was most significant on the facial tooth surfaces. We conclude that the thermoplastic aligner sheets undergo substantial thinning during the thermoforming process, which becomes more pronounced as the height of the model increases. As a result, there is a decrease in both overall and localized force transmission, which could lead to increased tipping by the aligner and a diminished ability to achieve bodily movement.

In vitro fertilization (IVF) has revolutionized the field of assisted reproductive technologies (ART) by offering hope to individuals and couples struggling with infertility. Nevertheless, traditional IVF methods are not exempt from drawbacks, such as suboptimal success rates, intrusive procedures, and ethical considerations. The introduction of micro/nanorobotics in IVF offers a revolutionary chance to tackle these difficulties. This paper presents a short review of the utilization of micro/nanorobotics in IVF, investigating progress in the manipulation of sperm, retrieval of oocytes, culture of embryos, and potential future developments in this fast progressing area. In this discussion, we explore the fundamental concepts, advantages, difficulties, and possible influence of micro/nanorobotics in transforming IVF processes and enhancing patient outcomes.

Engineering Education needs to be approached in different, innovative ways to meet the needs of society, learners, and education providers. This ranges from new educational programs and innovative pedagogies in individual classrooms, to online and immersive learning, to micro-credentials and modularity along with how to enable rapid adaptation for reskilling and upskilling, to entirely new pathways of restructuring education. Gamification is the application of game elements and digital game design techniques to non-game problems, such as learning challenges. It is about using game-based mechanics, aesthetics, and game thinking to enhance users’ engagement, motivate action, and support learning. At first view, the concept of gamification does not contain game design elements, but with the addition of additional elements such as the video game component that is applied in different contexts, the users are encouraged to participate in learning activities and complete learning challenges successfully. The first step in the process of designing a gamification activity is to think like a game designer. According to Cook (2013), any process can be gamified when the following requirements are covered: (i) the gamified activity is easy to learn, (ii) user progress can be measured, (iii) continuous feedback is provided to users.

Objective To observe the effect of roxadustat on blood pressure and micro-inflammatory response in patients with hemodialysis anemia, and to provide a viable technique for the treatment of hemodialysis anemia patients. Methods A total of 100 hemodialysis anemia patients admitted to the Nephrology Department of our hospital from July 2020 to July 2021 were enrolled and randomly divided into an observation group (roxadustat) and a control group (human recombinant erythropoietin (rhEPO). The clinical efficacy, blood lipid metabolism, inflammatory factor levels, iron metabolism-related indicators, blood biochemical indicators, anemia indicators, adverse reactions and blood pressure were recorded and compared. Results There was no significant difference in baseline data and serum indicators (P>0.05). The study group demonstrated superior performance to the control group in terms of clinical efficacy, blood lipid metabolism, inflammatory factor levels, iron metabolism-related indicators, blood biochemical indicators, anemia indicators, adverse reactions and blood pressure (all P<0.05). Conclusion Compared with rhEPO treatment, roxadustat exhibits a promising outcome in treating anemia and has slight impact on blood pressure of patients.

Micro-gyroscopes based on the Coriolis principle are widely employed in inertial navigation, motion control, and vibration analysis applications. This paper presents our main contributions which include a novel dual-frame optomechanical gyroscope, a unique photonic crystal cavity design, and advanced numerical simulation and optimization methods. The proposed design utilizes an optical cavity formed between dual oscillating frames, whereby input rotation induces a measurable phase shift via optomechanical coupling. Actuation of the frames is achieved electrostatically via an interdigitated comb-drive design. Through theoretical modeling based on cavity optomechanics and finite element simulation, the operating principle and performance parameters are evaluated in detail. Results indicate an expected angular rate sensitivity of 22.8 mV/°/s and angle random walk of 7.1×10-5 °/h1/2, representing superior precision than to existing micro-electromechanical systems gyroscopes of comparable scale. Detailed analysis of the optomechanical transduction mechanism suggests this dual-frame approach could enable angular vibration detection with resolution exceeding state-of-the-art solutions.

The grinding process by friction at the micro-scale in a mill with stones is considered a variable combination of contacts: with two-body (the asperities of lower millstone in direct contact with the asperities of upper millstone) and the three-body (micro-particles of ground seeds trapped between the asperities of lower and the upper stones of the mill). Three elements are described: (1) the mechanic contact of the asperities of the lower and upper millstone, to predict pressures on asperities, by modeling; (2) tests on a millstone sample covered with grinding particles, and (3) tests on a wafer sample formed by the millstones with the grinding particles between them. The paper highlights the combined effects of the micro-scale friction by individual measurements and to sum these effects an analytical model was used, and to validate the model, several experiments were performed. A suitable grind by friction assumes the grain’s movement and the interaction between the seeds and solid surfaces and is highlighted through theoretical and experimental studies. Topography analysis of the surface of the millstones revealed the model of microscopic frictional force. Endpoint measurements (the traces of the surface topography evolution), enable model verification in the grinding process.

Active transportation, such as walking, cycling, and micro-mobility modes, has received a lot of attention in recent years due to its potential benefits to urban residents, such as less traffic, better air quality, more opportunities to get exercise, and an overall higher quality of life. In this study, we used Classification and Regression Trees (CART) to compare and contrast three mobility options: shared micro-mobility, individual micro-mobility, and walking. We surveyed 219 people living in Budapest, Hungary, to learn more about their travel habits and investigate the demographic elements that influence people's mode choice, such as age, gender, ownership of micro-mobility modes, education, job, and income. Results showed that ownership of personal micro-mobility modes, and age as important predictors of active travel mode choice. Males seem to prioritize cost and weather conditions when choosing shared micromobility modes, while females value safety and weather conditions. Our findings can guide policy decisions and urban planning initiatives by identifying the most significant predictors of mode choice and evaluating the possible benefits and drawbacks of each mode.

This manuscript presents a study on the spatial relationships between bike accidents, the built environment, land use, and transportation network characteristics in Budapest, Hungary using Geographic Weighted Regression (GWR). The sample period included bike crash data between 2017 and 2022. The findings provide insights into the spatial distribution of bike crashes and their severity, which can be useful for designing targeted interventions to improve bike safety in Budapest and be useful for policymakers and city planners in developing effective strategies to reduce the severity of bike crashes in urban areas. The study reveals that the built environment features, such as traffic signals, road crossings, and bus stops, are positively correlated with the bike crashes index, particularly in the inner areas of the city. However, traffic signals have a negative correlation with the bike crash index in the suburbs, where they may contribute to making roads safer for cyclists. The study also shows that commercial activity and PT stops have a higher impact on bike crashes in the northern and western districts. The GWR analysis further suggests that one-way roads and higher speed limits are associated with more severe bike crashes, while green and recreational areas are generally safer for cyclists. Future research should be focused on the traffic volume and bikes trips’ effects on the severity index.

About 90% of the Ataulfo mango (Mangifera indica L.) crops in Mexico are in the south of the country. This variety has significant amounts of antioxidant compounds. All the trees come from a small group of parents, however, the possible intravarietal variations and the micro-environments where it is grown can influence the compounds that contribute to the antioxidant capacity. The objective of this study was to quantify the antioxidant compounds of Ataulfo mango fruits of trees grown in Soconusco, Chiapas, Mexico (origin denomination), as well as fruits of the parent trees. In addition, possible associations between the contents of these compounds and the micro-environmental conditions collected were sought. In total, 465 fruits from 155 trees planted in 13 municipalities (locations) were analyzed. Fruits were collected at physiological maturity and stored at 25 °C until reaching commercial maturity. The contents of total phenolic compounds (TPC), antioxidant capacity (AC by DPPH, ABTS and FRAP methods), total anthocyanins (TA) and ascorbic acid (AA) were determined. The fruits from Huehuetán, presented the highest contents of PC (0.89 mg GAE g-1); however, the highest AC was found in the fruits harvested in Frontera Hidalgo, with 128.29 µmol TE g-1 (ABTS). The fruits obtained from the parents are within the average range of total TPC and AC, without significant differences between their fruits and those cultivated. The micro-environments where the Ataulfo mango trees are grown do not have a significant effect on antioxidant compounds (TPC, AC, TA and AA) and the only variables that allow segregation by localities are relative humidity, environmental temperature and altitude.

Severe respiratory syncytial virus (RSV) infections in early life have been linked to the development of chronic airway disease. RSV is a potent inducer of reactive oxygen species (ROS) which contributes to inflammation and enhanced clinical disease. NF-E2-related factor 2 (Nrf2) is an evolutionary conserved redox-responsive protein that helps to protect cells and whole organisms from oxidative stress and injury. The role of Nrf2 in the context of viral-mediated chronic lung injury is not known. Herein, we show that RSV experimental infection of adult Nrf2 deficient BALB/c mice (Nrf2-/-; Nrf2 KO) is characterized by enhanced disease, increased inflammatory cell recruitment to the bronchoalveolar compartment, and a more robust upregulation of innate and inflammatory genes and proteins, compared to wild type Nrf2+/+ competent mice (WT). These events that occur at very early time points, lead to increased peak RSV replication in Nrf2 KO compared to WT mice (day 5). To evaluate longitudinal changes of the lung architecture, mice were scanned weekly by high-resolution micro-computed tomography (micro-CT) imaging up to 28 days after initial viral inoculation. Based on micro-CT qualitative 2D imaging and quantitative reconstructed histogram-based analysis of lung volume and density, we found that RSV infected Nrf2 KO mice developed significantly greater and prolonged fibrosis compared to WT mice. Results of this study underscore the critical role of Nrf2-mediated protection from oxidative injury not only in acute pathogenesis of RSV infection, but also in its long-term consequences of chronic airway injury.

GaN-based micro-size light-emitting diodes (µLEDs) have a number of appealing and distinctive benefits for display, visible-light communication (VLC), and other novel applications. The smaller size of LEDs affords them the benefits of enhanced current expansion, less self-heating effects, and higher current density bearing capacity. Low external quantum efficiency (EQE) resulting from non-radiative recombination and quantum confined stark effect (QCSE) is the serious barrier for applications of µLEDs. In this work, the reasons for the poor EQE of µLEDs are reviewed, as well as the optimization techniques for improving the EQE of µLEDs.

Dehydroaromatization of methane (MDA) is of great interest as a promising process for processing natural and associated petroleum gases, the main component of which is methane. The rapid loss of catalyst activity because of coke formation hinders the introduction of the DHA methane process into industry. Therefore, the aim of the research was to find ways to improve Mo/ZSM-5 catalysts for MDA. The paper presents the results of the synthesis of high-silica zeolites of the ZSM-5 type with a microporous and micro-mesoporous structure, the preparation of Mo/ZSM-5 catalysts based on them, and the study of the physicochemical and catalytic properties of the obtained samples during the non-oxidative conversion of methane into aromatic hydrocarbons. Zeolite catalysts were investigated by IR spectroscopy, X-ray diffraction, TPD-NH3, SEM, HR-TEM, N2-adsorption. It was found that the addition of carbon black at the stage of synthesis of zeolite type ZSM-5 does not lead to structural changes, the obtained samples have a crystallinity equal to 100%. The creation of the micro-mesoporous structure in Mo/ZSM-5 catalysts lead to an increase in their activity and stability in the process of methane dehydroaromatization. The highest conversion of methane is observed on a 4.0%Mo/ZSM-5 catalyst prepared based on of zeolite synthesized using 1.0% carbon black, and is 13.0% in 20 minutes of reaction, while the benzene yield reaches 7.0%. It has been shown by HR-TEM that a more uniform distribution of the active metal component is observed in a zeolite catalyst with a micro-mesoporous structure than in a microporous zeolite.

Controlled deposition of CoCrFeNiMo0.2 high entropy alloy (HEA) micro-particles was achieved using laser induced forward transfer (LIFT). Ultra-short laser pulses, 230 fs of 515 nm wavelength, were tightly focused into ∼ 2.4 μm focal spots on the ∼50 nm thick plasma-sputtered films of CoCrFeNiMo0.2. The HTA films were transferred onto glass substrates by magnetron sputtering in vacuum (10−8 atm) from the thermal spray coated substrates. The absorption coefficient of CoCrFeNiMo0.2 α ≈ 6 × 105 cm−1 was determined at 600 nm wavelength. The real and imaginary parts of refractive index (n + iκ) of HEA were determined from reflectance and transmittance using nano-films.

Around 14% of the global population does not have access to electricity. About 95% of those are living in rural Sub-Saharan Africa. Often in these regions, diesel generators are the only source of electricity. The operating cost of these diesel generators is high. However, solar and wind energy are available in most of African countries. This study presents the analysis of designing an off-grid hybrid system with a wind turbine, PV, diesel generator, and battery to power a hospital, school, and 200 household village in four locations across Somalia. The research investigated the availability of wind-solar resources in selected locations. Designing of the system and economic-technical calculations were performed using HOMER. The selection of the optimum design was based on the Cost of Electricity and Net Present Cost. The results show that for Kabaal and Ceel Buur, a WT-PV-DG-Battery is the optimal system as the wind resource in these regions is high. For Saakov and Baki, a PV-DG-Battery system proves to be optimum as the wind resource is limited here. The study also evaluated the control strategy and proved that combined dispatch was the most cost-effective for these locations. The study concluded that hybrid systems are more economical than diesel systems.

Two types of trenches cross-section in conventional vertical and brand new reverse-V-shape have fabricated on SCD substrate by micro-jet water-assist laser, the epitaxial lateral overgrowth technique has applied by microwave plasma chemical vapor deposition system in forming multiple micrometer-size channels. Raman and SEM techniques have applied in analyze both types growth layer characterization. Optical microscope has used to test microchannels hollowness. As a result, with the brand new reverse-V-shape trench, epitaxial lateral overgrowth layer reaches higher SCD surface morphology and crystal quality.

This study deals with vibrational and crystallographic aspects of the thermally induced transformation of serpentine-like garnierite into quartz, forsterite, and enstatite occurring at about 620 °C. Powder specimens of garnierite have been annealed in static air between room temperature and 1000 °C. The resulting products from the transformations detected based on thermogravimetric and differential thermal analysis, have been extensively characterized via microRaman spectroscopy, and X-ray diffraction. Our study shows that serpentine-like garnierite consists of a mixture of different mineral species. Furthermore, these garnierites and their composition can provide details based on the mineralogy and the crystalline phases resulting from the thermal treatment.

We review recent work on narrowband orthogonally polarized optical RF single sideband generators as well as dual-channel equalization, both based on high-Q integrated ring resonators. The devices operate in the optical telecommunications C-band and enable RF operation over a range of either fixed or thermally tuneable frequencies. They operate via TE/TM mode birefringence in the resonator. We achieve a very large dynamic tuning range of over 55 dB for both the optical carrier-to-sideband ratio and the dual-channel RF equalization for both the fixed and tunable devices.

This paper presents a novel micro-segmented genetic algorithm (μsGA) to identify the best solution for the locomotion of a quadruped robot designed on a rectangular ABS plastic platform. We compare our algorithm with three similar algorithms found in the specialized literature: a standard genetic algorithm (GA), a micro-genetic algorithm (μGA), and a micro artificial immune system (μAIS). The quadruped robot prototype guarantees the same conditions for each test. The platform was developed using 3D printing for the structure and can accommodate the mechanisms, sensors, servomechanisms as actuators. It also has an internal battery and a multicore embedded system (mES) to process and control the robot locomotion. This research proposes a μsGA that segments the individual into specific bytes. μGA techniques are applied to each segment to reduce the processing time; the same benefits as the GA are obtained, while the use of a computer and the high computational resources characteristic of the GA are avoided. This is the reason why some research in robot locomotion is limited to simulation. The results show that the performance of μsGA is better than the three other algorithms (GA, μGA and AIS). The processing time was reduced using a mES architecture that enables parallel processing, meaning that the requirements for resources and memory were reduced. This research solves the problem of continuous locomotion of a quadruped robot, and gives a feasible solution with real performance parameters using a μsGA bio-micro algorithm and a mES architecture.

In-situ nanoindentation experiment has been widely adopted to characterize material behaviors of microelectronic devices. This work introduces the latest developments of nanoindentation experiment in characterizing nonlinear material properties of 3D integrated microelectronic devices with through-silicon-vias (TSVs). The elastic, plastic, and interfacial fracture behavior of the copper via and matrix-via interface have been characterized using small scale specimens prepared with focused-ion-beam (FIB) and nanoindentation experiment. A brittle interfacial fracture was found at the Cu/Si interface under mixed-mode loading with a phase angle ranging from 16.7 to 83.7 degrees. The mixed-mode fracture strengths were extracted using the linear elastic fracture mechanics (LEFM) analysis and a fracture criterion was obtained by fitting the extracted data with the power-law function. The vectorial interfacial strength and toughness were found to be independent with mode-mix.

Micro Injection molding combined with the use of removable inserts is one of the most promising manufacturing process for microfluidic devices, such as Lab-on-a-chip, that have the potential to revolutionize the healthcare and diagnosis system. In this work we have designed, fabricated and tested a compact and disposable plastic optical stretcher. To produce the mould inserts, two micro manufacturing technologies have been used. Micro Electro Discharge machining was used to reproduce the inverse of the capillary tube connection characterized by high aspect ratio. Thanks to the high accuracy of femtosecond laser machining, instead, we manufactured insert with perfectly aligned microfluidic channels and fiber slots, facilitating the final composition of the optical manipulation device. The optical stretcher operation is tested using microbeads and red blood cells solutions. The prototype presented in this work demonstrates the feasibility of this approach that should guarantee a real mass production of ready-to-use- Lab-on-a-chip.

In the paper, the effect of voltage increasing (from 500 VDC up to 650 VDC) on the structure and chemical composition of porous coating on titanium made by Plasma Electrolytic Oxidation, is presented. In the present paper, phosphates based coatings enriched with calcium, magnesium, zinc and copper in electrolyte based on 1 L of 85% concentrated H3PO4 with additions of Ca(NO3)2·4H2O, and Mg(NO3)2∙6H2O, and Zn(NO3)2∙6H2O, and Cu(NO3)2∙3H2O, are described. The morphology, chemical and phase composition, are evaluated using SEM, EDS, XRD, XPS, GDOES. Based on all the analyses, it was found out that the PEO coatings are porous and enriched with calcium, magnesium, zinc and copper. They consist mainly of the amorphous phase, which is more visible for higher voltages, and it is correlated with the increasing of the total PEO coating thickness (the higher the voltage, the thicker the PEO coating). However, for 650 VDC an amorphous phase and titanium substrate was also recorded with a signal from Ti2P2O7 crystalline, that was not observed for lower voltages. It was also found out that all the obtained coatings may be divided in three sub-layers, i.e. porous, semiporous, and transition one.

Various natural disasters such as floods, fires, earthquakes, etc. have affected human life. Detection and classification of large and small earthquakes caused by natural or abnormal events have been always important to Earth scientist. One of the most important research challenges in this field is the lack of an effective method for identifying and categorizing various types of seismic events at less important and important levels. Based on latest achievements of Data Mining international institutions such as Rexer-KDnugget-Gartner and also newest authentic articles, SVM, KNN, C4.5, MLP are from most important and popular and leading classifiers in data world.Therefor in present study, a boost learning system consisting support vector machine algorithms with linear regression, MLP Neural Network ، C4.5 decision tree and KNN near neighborhood have been utilized in a combined form to detect and categorize micro seismic events. In general, the steps involved in the proposed method are: 1) performing artificial seismic tests, 2) data gathering and analysis, 3) conducting preprocessing and separating training and testing samples, 4) generating relevant models with training samples and detecting and categorizing test samples and 5) extracting a cluster with the maximum candidate using boost learning. After simulations, it was observed that the accuracy of proposed boost method to the best answer was about 6.1% higher compare to other methods and the error rate was 0.082% of recalling. Accuracy of detection and classification to the best answer were also improved compare to other methods up to 2.31% and 6.34%, respectively.

Stenting is an alternative to endarterectomy for the treatment of carotid artery stenosis. However, stenting is associated with a higher risk of procedural stroke secondary to distal thromboembolism. Hybrid stents with a micromesh layer have been proposed to address this complication. We developed a micropatterned thin film nitinol (M-TFN) covered stent designed to prevent thromboembolism during carotid intervention. This innovation may obviate the need or work synergistically with embolic protection devices. The proposed double layered stent is low-profile, thromboresistant, and covered with a M-TFN that can be fabricated with fenestrations of varying geometries and sizes. The M-TFN was created in multiple geometries, dimensions, and porosities by sputter deposition. The efficiency of various M-TFN to capture embolic particles was evaluated in different atherosclerotic carotid stenotic conditions through in vitro tests. The covered stent prevented emboli dislodgement in the range of 70-96% during 30min duration tests. In vitro vascular cell growth study results showed that endothelial cell elongation, alignment and growth behaviour silhouettes significantly enhance specifically on the diamond-shape M-TFN with the dimensions of 145µm×20µm and a porosity of 32%. Future studies will require in-vivo testing. Our results demonstrate that M-TFN has a promising potential for carotid artery stenting.

(1) Background: Stereological estimations significantly contributed to our anatomical and physiological understanding of the lung by providing an average distribution of measured parameters over the entire lung parenchyma. However, most structural lung diseases show a very inhomogeneous pattern of alterations. (2) Methods: We developed a novel protocol for the analysis of all pulmonary airspaces. Our pipeline starts with high-resolution synchrotron radiation-based X-ray tomographic microscopy (SRXTM) and consists of (i) image segmentation with the combination of the free machine-learning tool Ilastik and ImageJ and (ii) calculation of the airspace diameter distribution of an entire lung using a diameter map function. To evaluate the new pipeline, lungs from adult mice with cystic fibrosis (CF)-like lung disease (ENaC-transgenic mice) or mice with elastase-induced emphysema were compared to healthy controls. (3) Results: We were able to show the distribution of airspace diameters throughout the entire lung, as well as separately for the conducting airways and the gas-exchange area. In the pathobiological context, we observed an irregular widening of parenchymal airspaces in mice with CF-like lung disease and elastase-induced emphysema. Comparable results were obtained when analyzing lungs imaged with μCT, suggesting that our pipeline is applicable to different kinds of imaging modalities. (4) Conclusions: We conclude that the airspace diameter map is well suited for a detailed analysis of unevenly distributed structural alterations in chronic muco-obstructive lung diseases such as cystic fibrosis and COPD.

Coffee is one of the most valuable agricultural products worldwide, and it is crucial to have efficient tools to obtain reliable information about production. This study aims to estimate coffee plantation production using segmentation and deep learning techniques in RGB images. Photographs of coffee plants were taken in Tabaconas, San Ignacio-Cajamarca, to create a dataset of crops during the harvest stage. The images were segmented to detect coffee fruits. A deep learning method was developed with YOLOv5 to detect the fruits and OpenCV to count them. The results showed that YOLOv5 achieved an accuracy of 97.25%, a recall of 95.77%, and an F1-Score of 96.37%, demonstrating high reliability in detecting coffee fruits. The average detection time per image was 17.9 seconds. The metrics were evaluated using a confusion matrix, highlighting the model's good performance. In conclusion, segmentation and deep learning techniques, along with counting algorithms developed with OpenCV, proved effective for estimating coffee production. This approach provides a valuable tool for farmers, improving crop management and facilitating decision-making in precision agriculture.

Accurate segmentation of skin lesions from dermoscopic images is crucial for early skin cancer detection, yet variations in lesion appearance and image artifacts present challenges. This study proposes two deep learning models, UCM-NetV2 and BNN-UCM-NetV2, to improve accuracy and computational efficiency. UCM-NetV2 enhances the UCM-Net architecture with a novel "cyber-structure" combining Multilayer Perceptron and CNN layers, improving prediction accu-racy without increasing the model's parameter count. BNN-UCM-NetV2 further optimizes for mobile deployment by binarizing activations and weights into 1-bit values, reducing computa-tional complexity and model size. Evaluations on the ISIC2017 and ISIC2018 datasets demonstrate that UCM-NetV2 outperforms existing methods in both accuracy and computational efficiency, achieving this with less than 0.04 GFLOPs. These models have the potential to make skin lesion analysis accessible to a broader population, particularly in resource-limited settings, allowing for proactive skin health monitoring and facilitating teledermatology. To foster further innovation in mobile health diagnostics, the source code for UCM-NetV2 will be available on GitHub: https://github.com/chunyuyuan/UCMV2-Net.

Aiming at the problems of inaccurate segmentation of long object and information loss of small object in real-time semantic segmentation algorithm, this paper proposes a lightweight multi-branch real-time semantic segmentation network based on BiseNetV2. The new auxiliary branch makes full use of spatial details and context information to cover the long object in the field of view. Meanwhile, in order to ensure the inference speed of the model, the asymmetric convolution is used in each stage of the auxiliary branch to design a structure with low computational complexity. In the multi-branch fusion stage, the alignment and fusion module is designed to provide guidance information for deep and shallow feature mapping, so as to make up for the problem of feature misalignment in the fusion of information at different scales, and thus reduce the loss of small target information. In order to further improve the model’s awareness of key information, a global context module is designed to capture the most important features in the input data. The proposed network uses NVIDIA GeForce RTX 3080 Laptop GPU experiment, on the road street view data set Cityscapes and CamVid average occurring simultaneously ratio reached 77.1% and 78.4% respectively, with running speed of 127 frames/s respectively and 112 frames/s. The experimental results show that the proposed algorithm can achieve real-time segmentation and improve the accuracy significantly, showing good semantic segmentation performance

Utilizing deep learning for semantic segmentation of cropland from remote sensing imagery has become a crucial technique in land surveys. Cropland illustrates diverse morphologies and degrees of fragmentation on the Earth’s surface, underscoring the importance of accurately perceiving the complex boundaries of cropland which are crucial for effective segmentation. This paper introduces a UNet-like boundary-aware compensation model BAFormer. Cropland boundaries typically exhibit rapid transformations in pixel values and texture features, often appearing as high-frequency features in remote-sensing images. To enhance the recognition of these high-frequency features as represented by cropland boundaries, the proposed BAFormer integrates a Feature Adaptive Mixer (FAM) and develops a Deep Wide Large Kernel Multi-Layer Perceptron (DWLK-MLP) to enrich the global and local cropland boundaries features separately. Specifically, FAM adaptively mixes high-frequency and low-frequency features through the advantages of convolution and self-attention; DWLK-MLP expands the convolutional receptive field by deeply decomposing large kernel convolutions. The efficacy of BAFormer has been evaluated on the Vaihingen, Potsdam, and LoveDA public datasets, as well as the Mapcup dataset. It has demonstrated advanced performance, achieving mIoU scores of 84.5%, 87.3%, 53.5%, and 83.1% on these datasets respectively. Notably, BAFormer-T, the lightweight iteration of the model, surpasses other lightweight models on the Vaihingen dataset with scores of 91.3% F1 and 84.1% mIoU. The source code is available at https://github.com/WangYouM1999/BAFormer.

In this paper we propose a module that uses features learned by a deep convolutional neural network to infer areas of corrosion and segment pixels to corrosion areas of inspection interest. Our segmentation module is based on eigen tree decomposition and information based decision criteria. To interrogate performance we use several state-of-the-art deep learning architectures and compare to our approach. The results indicate that our method produces better results in terms of accuracy and precision, whilst maintaining good (f-score) significance over the entire dataset.

Deep learning is widely used in image segmentation, effectively identifying crops and weeds and contributing to the reduction of herbicide use. Traditional methods of applying pesticides over large areas are inefficient in dealing with weeds as needed, leading to massive waste of pesticides, high-cost production, and serious environmental pollution. This affects crop yield and quality. Although weed recognition using conventional deep learning methods has evolved over time, there are still challenges in weed extraction, detection, and segmentation. Accurate recognition and detection of weeds are essential prerequisites for implementing variable spraying. This paper proposes a semantic segmentation method based on UNet++ for complex environments where accurate identification of plants and weeds is challenging, targeting weeds in sugar beets, peas, and rice. An attention module is integrated into the upsampling process of UNet++, and UNet++ is used as a backbone network to effectively integrate multi-scale information, efficiently suppressing external noise interference. The UNet++ model with an integrated attention mechanism module achieves higher IOU than the general UNet++ model used in medical image analysis. This method effectively detects crops and weeds in complex backgrounds, providing reference material for the accurate application of robotic herbicides.

The research of object classification and part segmentation is a hot topic in computer vision. A considerable number of studies have been carried out about deep learning on 3D point clouds. However,it is challenging to achieve effective feature learning due to sparsity of point clouds. Recently, a variety of Transformers have been adopted to improve point cloud processing and display great potential. Nevertheless, large numbers of Transformer layers tend to incur huge computational and memory costs. PointNet++ is one of the most influential neural architectures for point cloud understanding. Although the accuracy of PointNet++ has been largely surpassed by recent networks, this does not mean that PointNet++ has no potential.Thus, this paper offer two major contributions that significantly improve PointNet++ performance. Firstly, we introduce a novel contextual feature extraction (CFE) block that significantly enhances the feature extraction capabilities of PointNet++ networks. Secondly, to further enhance feature fusion, we seamlessly integrate a mutual learning (ML) block into the network architecture. By embedding these two innovative blocks within each layer of the network, we not only enrich the network's functionality but also impart it with greater robustness and adaptability. The specific experiments were conducted on the S3DIS (6-fold cross-validation) and Modelnet40 datasets with 86.5% and 92.7% accuracy, respectively, which proved that our model is comparable or even better than most existing methods for classification and segmentation tasks.

Skin cancer is a prevalent type of malignancy on a global scale, and the early and accurate diag-nosis of this condition is of utmost importance for the survival of patients. The clinical assessment of cutaneous lesions is a crucial aspect of medical practice, although it encounters several obsta-cles, such as prolonged waiting time and misinterpretation. The intricate nature of skin lesions, coupled with variations in appearance and texture, presents substantial barriers to accurate clas-sification. As such, skilled clinicians often struggle to differentiate benign moles from early ma-lignant tumors in skin images. Although deep learning-based approaches such as convolution neural networks have made significant improvements, their stability and generalization continue to confront difficulties, and their performance in accurately delineating lesion borders, capturing refined spatial connections among features, and using contextual information for classification is suboptimal. To address these limitations, we propose a novel approach for skin lesion classification which combines snake models of Active Contour (AC) Segmentation, ResNet50 for feature ex-traction and a Capsule Network with a fusion of lightweight attention mechanisms, to attain the different feature channels and spatial regions within feature maps, enhance the feature discrimi-nation, and improve accuracy. We employed the Stochastic Gradient Descent (SGD) optimization algorithm to optimize the model's parameters. The proposed model is implemented on publicly available datasets, namely HAM10000 and ISIC 2020. The experimental results showed that the proposed model achieved an accuracy of 98% and AUC-ROC of 97.3%, showcasing substantial potential in terms of effective model generalization compared to existing state-of-the-art (SOTA) approaches. These results highlight the potential for our approach to reshape automated derma-tological diagnosis and provide a helpful tool for medical practitioners.

Street view images can help us better understand the city environment and potential characteristics. With the development of computer vision and deep learning, the technology of semantic segmentation algorithms has become more mature. However, DeeplabV3+, which is commonly used in semantic segmentation, has shortcomings such as a large number of parameters, high requirements for computing resources, and easy loss of detailed information. Therefore, this paper proposes LM-DeeplabV3+, which aims to greatly reduce parameters and computations of the model while ensuring the segmentation accuracy. Firstly, the lightweight network MobileNetV2 is selected as the backbone network, and the ECA attention mechanism is introduced after MobileNetV2 extracts shallow features to improve the ability of feature representation; secondly, the ASPP module is improved, and on its basis, the EPSA attention mechanism is introduced to achieve cross-dimensional channel attention and important feature interaction; thirdly, a loss function named CL loss is designed to balance the training offset of multiple categories and better indicate the segmentation quality. This paper conducted experimental verification on the Cityspaces dataset, and the results showed that the mIoU reached 74.9%, which was an improvement of 3.56% compared to DeeplabV3+; the mPA reached 83.01%, which was an improvement of 2.53% compared to DeeplabV3+.

Fire outbreaks continue to cause damage despite the improvements in fire-detection tools and algorithms. It is still challenging to implement a well performing and optimized approach, which is sufficiently accurate, and has tractable complexity and low false alarming rate. Small amount of fire and identification of fire from a long distance is also a challenge in previously proposed techniques. In this study, we propose a novel hybrid model based on Convolutional Neural Networks (CNN) to detect and analyze fire intensity. 21 convolutional layers, 24 Rectified Linear Unit (ReLU) layers, 6 pooling layers, 3 fully connected layers, 2 dropout layers, and a softmax layer are included in the proposed 57-layer CNN model. Our proposed model performs instance segmentation in order to distinguish between fire and non-fire events. To reduce the intricacy of the proposed model, we also propose a key-frame extraction algorithm. The proposed model uses Internet of Things (IoT) devices to alert the relevant person by calculating the severity of fire. Our proposed model is tested on a publicly available dataset having fire and normal videos. The achievement of 95.25 % classification accuracy, 0.09% False Positive Rate (FPR), 0.65 percent False Negative Rate (FNR), and a prediction time of 0.08 seconds validates the proposed system.

Current conventional methods of evaluating microstructures are characterized by a high degree of subjectivity and a lack of reproducibility. Modern machine learning (ML) approaches have already shown great potential in overcoming these challenges. Once trained with representative data in combination with an objective ground truth, the ML model is able to perform a task properly in a reproducible and automated manner. However, in highly complex use cases, it is often not possible to create a definite ground truth. This study addresses this problem using the underlying showcase of microstructures of highly complex quenched and quenched and tempered (Q/QT) steels. A patch-wise classification approach combined with a sliding window technique provides a solution for segmenting entire microphotographs where pixel-wise segmentation is not applicable due to the problem of reproducibly creating unambiguous training masks. Using correlative microscopy, consisting of light optical microscope (LOM) and scanning electron microscope (SEM) micrographs as well as corresponding data from electron backscatter diffraction (EBSD), a training dataset of reference states that covers a wide range of microstructures was acquired in order to train accurate and robust ML models. Despite the enormous complexity associated with the steels treated here, classification accuracies of 88.8% in the case of LOM images and 93.7% for high-resolution SEM images were achieved. These high accuracies are close to super-human performance, especially in consideration of the reproducibility of the automated ML approaches compared to conventional methods based on subjective evaluations through experts.

Skin detection, the process of distinguishing between skin and non-skin regions in a digital image, is widely used in a variety of applications ranging from hand gesture analysis to body part tracking to facial recognition. Skin detection is a challenging problem that has received a lot of attention from experts and proposals from the research community in the context of intelligent systems, but the lack of common benchmarks and unified testing protocols has hampered fairness among approaches. Comparisons are very difficult. Recently, the success of deep neural networks has had a major impact on the field of image segmentation detection, resulting in various successful models to date. In this work, we survey the most recent research in this field and propose fair comparisons between approaches using several different datasets. The main contributions of this work are: (i) a comprehensive literature review of approaches to skin color detection and a comparison of approaches that may help researchers and practitioners choose the best method for their application; (ii) a comprehensive list of datasets that report ground truth for skin detection; (iii) a framework for evaluating and combining different skin detection approaches. Moreover, we proposed an ensemble of convolutional neural networks and transformers that obtains state of the art performance. All the code is made publicly available at https://github.com/LorisNanni

Video segmentation is crucial in a variety of practical applications especially in computer visions. Most of recent works in video segmentation are focusing on Deep learning based video segmentation, there are rooms for improvement in respect of the evolutionary algorithms. This paper aims to propose the novel method to video segmentation by using the optimization of segmentation parameters based on ensemble-based random forest and gradient boosting decision tree. The experimental results show Pareto front of segmentation parameters (hue, brightness, luminance, and saturation). Our optimization model yields accuracy: 85% +/-8.85 % (micro average: 85.00 %), average class precision: 84.88%, and average class recall: 85%. We also show the video segmentation results based on our optimization method and compare our results with Kinect-based video segmentation.

Clinicians are often very sceptical about applying automatic image processing approaches, especially deep learning based methods, in practice. One main reason for this is the black-box nature of these approaches and the inherent problem of missing insights of the automatically derived decisions. In order to increase trust in these methods, this paper presents approaches that help to interpret and explain the results of deep learning algorithms by depicting the anatomical areas which influence the decision of the algorithm most. Moreover, this research presents a unified framework, TorchEsegeta, for applying various interpretability and explainability techniques for deep learning models and generate visual interpretations and explanations for clinicians to corroborate their clinical findings. In addition, this will aid in gaining confidence in such methods. The framework builds on existing interpretability and explainability techniques that are currently focusing on classification models, extending them to segmentation tasks. In addition, these methods have been adapted to 3D models for volumetric analysis. The proposed framework provides methods to quantitatively compare visual explanations using infidelity and sensitivity metrics. This framework can be used by data scientists to perform post-hoc interpretations and explanations of their models, develop more explainable tools and present the findings to clinicians to increase their faith in such models. The proposed framework was evaluated based on a use case scenario of vessel segmentation models trained on Time-of-fight (TOF) Magnetic Resonance Angiogram (MRA) images of the human brain. Quantitative and qualitative results of a comparative study of different models and interpretability methods are presented. Furthermore, this paper provides an extensive overview of several existing interpretability and explainability methods.

The recent rise of deep learning (DL) and its promising capabilities in capturing non-explicit detail from large datasets have attracted substantial research attention in the field of medical image processing. DL provides ground for technology development for computer-aided diagnosis and segmentation in radiology and radiation oncology. Amongst the anatomical locations where recent auto-segmentation algorithms have been employed, the pelvis remains one of the most challenging due to large intra- and inter-patient soft-tissue variabilities. This review provides a comprehensive and clinically-oriented overview of DL-based segmentation studies for bladder, prostate, cervical and rectal cancers, highlighting the key findings, challenges and limitations.

A pixel-based segmentation method was demonstrated to be confounded by developmental stage in estimation of flowering of mango. Categorization of panicles into three developmental stages was undertaken with a single and a two-stage deep learning framework (YOLO and R2CNN), using either upright or rotated bounding boxes. For a validation image set and for total panicle count, the models MangoYOLO(-upright), MangoYOLO-rotated, YOLOv3-rotated, R2CNN(-rotated) and R2CNN-upright achieved: (i) RMSEs of 25.6, 16.0, 15.4, 25.8 and 32.3 panicles per tree image, (ii) Mean average precision (mAP) scores of 72.2, 69.1, 65.0, 62.5 and 70.9% and (iii) weighted F1-scores of 76.5, 76.1, 74.9, 74.0 and 82.0, respectively. For a test set of images involving a different orchard and cultivar and use of a different camera, the R2 for machine vision to human count of panicles per tree was 0.86, 0.80, 0.83, 0.81 and 0.76 for the same models, respectively. Thus, models generalised well, but with no consistent benefit from use of rotated over upright bounding boxes. While the YOLOv3-rotated model was superior in terms of total panicle count, the R2CNN-upright model was more accurate for panicle stage classification. To demonstrate practical application, panicle counts were made weekly for an orchard of 994 trees, with a peak detection routine applied to document multiple flowering events.

This article presents a new method of segmenting grayscale images by minimizing Shannon's neutrosophic entropy. For the proposed segmentation method, the neutrosophic information components, i.e., the degree of truth, the degree of neutrality and the degree of falsity are defined taking into account the belonging to the segmented regions and at the same time to the separation threshold area. The principle of the method is simple and easy to understand and can lead to multiple thresholds. The efficacy of the method is illustrated using some test gray level images. The experimental results show that the proposed method has good performance for segmentation with optimal gray level thresholds.

Lung nodule segmentation in CT images and its subsequent volume analysis can help determinethe malignancy status of a lung nodule. While several efficient segmentation schemes have beenproposed, only a few studies evaluated the segmentation’s performance for large nodules. In thisresearch, we contribute a semi-automatic system which is capable of performing robust 3-D segmen-tations on both small and large nodules with good accuracy. The target CT volume is de-noisedwith an anisotropic diffusion filter and a region of interest is selected around the target nodule ona reference slice. The proposed model performs nodule segmentation by incorporating a mean in-tensity based threshold in Geodesic Active Contour model in level sets. We also devise an adaptivetechnique using image intensity histogram to estimate the desired mean intensity of the nodule.The proposed system is validated on both lung nodules and phantoms collected from publicly avail-able diverse databases. Quantitative and visual comparative analysis of the proposed work withthe Chan-Vese algorithm and statistic active contour model of 3D Slicer platform is also presented.The resulting mean spatial overlap between segmented nodules and reference nodules is 0.855, themean volume bias is 0.10±0.2 ml and the algorithm repeatability is 0.060 ml. The achieved resultssuggest that the proposed method can be used for volume estimations of small as well as large-sizednodules.

This paper presents a novel approach for semantic segmentation of building roof in dense urban environment with Deep Convolution Neural Network (DCNN) using imagery acquired by a Chinese Very High Resolution (VHR) satellite mission, i.e. GaoFen-2 (GF-2). To provide an operational end-to-end work flow for accurate build roof mapping with feature extraction as well as image segmentation, a fully convolutional DCNN with both convolutional and deconvolutional layers is designed to perform the VHR image analysis for labeling pixels. Since the diverse urban patterns and building styles in large areas, sample image data sets of building roof and non-building roof are collected over different metropolitan regions in China. We selected typical cities with dense urban environment in each metropolitan region as study areas for collecting training and test samples. High performance cluster with GPU-mounted workstations is employed to perform the model training and optimization. With the building roof samples collected over different cities, the predictive model with multiple NN layers is developed for building roof labeling. The validation of the building roof map shows that the overall accuracy(OA) and the mean Intersection Over Union( mIOU) of DCNN based segmentation are 94.67%, 0.85 respectively, while CRF-refined segmentation achieved OA of 94.69% and mIOU of 0.83. The results suggest that the proposed approach is a promising solution for building roof mapping with VHR images over large areas across different urban and building patterns. With the operational acquisition of GF2 VHR imagery, it is expected to develop an automated pipeline for operational built-up area monitoring and timely update of building roof map over large areas.

This paper investigates existing mathematical morphology based techniques applied for performing malaria parasites detection and identification in both Giemsa and Leishman stained blood smears images. Malaria is an epidemic health disease and a rapid, accurate diagnosis is necessary for proper intervention. Generally, pathologists visually examine blood stained slides for malaria diagnosis; this kind of visual inspection is subjective, errorprone and time consuming. In order to cope with such issues, computer-aided methods have been increasingly evolved for abnormal erythrocyte and/or parasites detection, segmentation and semi/fully automated classification. The aim of this paper is to present a review of recent mathematical morphology based methods for malaria parasite detection.

The increased availability of high resolution remote sensor data for precision agriculture 1 applications permits users to aquire deeper and more relevant knowledge about crops states that lead 2 inevitably to better decisions. The algorithm libraries being developed and evolved around these 3 applications rely on multi-spectral or hyper-spectral data acquired by using manned or unmanned 4 platforms. The current state of the art makes thorough use of vegetational indicies to guide the 5 operational management of agricultural land plots. One of the most challenging sub-problems is 6 to correctly identify and separate crop from soil. Thresholding techniques based on Normalized 7 Difference Vegetation Index (NDVI) or other such similar metrics have the advantage of being simple, 8 easy to read transformations of the data packed with useful information. Obvious difficulties arise 9 when crop/tree and soil have similar spectral responses as in case of grass filled areas in vineyards. 10 In this case grass and canopy are close in terms of NDVI values and thresholding techniques will 11 generally fail. Radiometric approaches could be integrated or replaced by a geometric approach that 12 is based on terrain data like Digital Surface Models (DSMs). These models are one of the ouputs 13 of orthorectification engines usually present in data acquired by using unmanned platforms. In 14 this paper we present two approaches based on DSM that are able to segment crop/tree from soil 15 while over gradient terrain. The DSM data are processed through a two dimensional data slicing or 16 reduction technique. Each slice is separately processed as a one dimensional time series to derive the 17 terrain and tree structures separately, here interpreted as object probability densities. In particular 18 the first approach is a Cartesian grid rasterization (CARSCAN) of the terrain and the second is its 19 immediate generalisation or radial grid rasterization of the DSM model (FANSCAN). The FANSCAN 20 recovers information from the original image at greater frequencies on the Fourier plane. These 21 approaches enable the identification of crop/tree from soil in case of slopes or hilly terrain without 22 any constraint on the displacement / direction of plant/tree row. The proposed algorithm uses pure 23 DSM information even if it is possible to fuse its output with other classifiers.

The information of seismic damage of buildings in SAR images of different time phase, especially in SAR images after earthquake, is easily disturbed by other factors, which affects the accuracy of information discrimination. In order to identify and evaluate the distribution information of the seismic damage accurately and make full use of the abundant texture features in the SAR image. The conventional method of change detection based on texture features usually takes the pixel as the calculating unit. In this paper, a method of texture feature change detection of SAR images based on watershed segmentation algorithm is proposed. Based on the optimization of texture feature parameters, the feature parameters are segmented by the watershed segmentation algorithm, and the feature object image is obtained. This method introduces the idea of object oriented, and carries out the calculation of the difference map at the object level, Finally, the classification threshold value of different types of seismic damage types is selected, and the recognition of building damage is achieved. Taking the ALOS data before and after the earthquake in Yushu as an example to verify the effectiveness of the method, the overall accuracy of the building extraction is 88.9%, Compared with pixel-based methods, it is proved that the proposed method is effective.

Cross-border e-commerce is an opportunity for micro, small and medium sized enterprise (MSMEs) in developing countries. Based on a resource-based approach, this research studied how to support resource lacking enterprises with export marketing strategy. It dealt with actual business cases of Mongolian entrepreneurs trying to export Mongolian products to Korean market. Multiple source data including interviews, internal documents, and group discussions, were matched with theories to come up with strategies and validated by supporting organizations in Mongolia and Korea. The research suggests that MSMEs should rely on third party digital platforms rather than setting up their own. For product strtategy of the marketing mix, sellecting competitive product categories and supporting them adjusting to foreign markets and quality assurance is needed. For price strategy, loccally high priced products should use a price penetration strategy with a lower price compared to competing foreign products. For place strategy, supporting organizations should partner with exporters for collective delivery. For promotion strategy, they need to support the capacity of MSMEs enabling them to use digital marketing tools effectivly. These strategies were validated and adopted by supporting organizations in Monglia and Korea.

It is very difficult to accurately divide farmland and woodland in Gaofen 2 (GF-2) remote sensing image, because their single plant coverage is very small, and their spectra are very similar. The ratio of spatial resolution and one plant’s coverage area must be fully taken into account when designing the Convolutional Neural Network structure for extracting them from GF-2 image. We establish a Convolutional Encode Neural Networks model (CENN), The first layer has two sets of convolution kernels to learn the characteristics of farmland and woodland respectively, while the second layer is the encoder to encode the characteristics by transfer function, which can map the results to the corresponding category number. In the training stage, samples of farmland, woodland, and other categories are categorically used to train CENN, as soon as training is accomplished, CENN would acquire enough ability to accurately extract farmland and woodland from remote sensing images. The final extraction result is obtained by implementing per-pixel segmentation of images used to train the CENN. CENN is compared and analyzed with others such as Deep Belief Network (DBN), Full Convolutional Network (FCN), Deeplab Model. The results of experiments show that CENN can more accurately mine the characteristics of farmland and woodland, and it achieves its goal of extracting farmland and woodland with high precision from GF-2 images.

Micro elastofluidics is a transformative branch of microfluidics, leveraging fluid-structure interaction (FSI) at the microscale to enhance the functionality and efficiency of various microdevices. This review paper elucidates the critical role of advanced computational FSI methods in the field of micro elastofluidics. By focusing on the interplay between fluid mechanics and structural responses, these computational methods facilitate the intricate design and optimisation of microdevices such as microvalves, micropumps, and micromixers, which rely on the precise control of fluidic and structural dynamics. In addition, these computational tools extend to the development of biomedical devices, enabling precise particle manipulation and enhancing therapeutic outcomes in cardiovascular applications. Furthermore, this paper addresses the current challenges in computational FSI and highlights the necessity for further development of tools to tackle complex, time-dependent models under microfluidic environments and varying conditions. Our review highlights the expanding potential of FSI in micro elastofluidics, offering a roadmap for future research and development in this promising area.

For concrete structures exposed to offshore areas, chloride ion erosion is one of the main factors affecting the durability. It is crucial to evaluate chloride ion permeability resistance of concrete structures. In this article, a finite element simulation of the chloride ion diffusion process in concrete is conducted. A mass diffusion finite element model based on random aggregate approach is established to investigate the influence of aggregate, interface transition zone, and micro-cracks on chloride ion diffusion coefficients in concrete. The results show that the mass diffusion finite element analysis based on the exponential function model and power function model can effectively simulate the chloride ion diffusion process in concrete. In addition, the data reveal that coarse aggregate is the most important factor affecting chloride ion diffusivity in concrete. However, the interface transition zone significantly accelerates chloride ion diffusion in concrete. Moreover, this acceleration effect exceeds the barrier effect of aggregate.

Micro satellites must survive severe mechanical conditions during their launch phase. Therefore, structural design requirements are imposed on the micro satellites. These requirements are the strength requirement and the stiffness requirement. Usually, the structural design of a micro satellite is performed using the internal stress analysis and the natural frequency analysis, which are based on a Finite Element Method (FEM). The validity of this structural design is evaluated through vibration tests. In an early stage of development, which has a FEM model of a satellite in the process of creation, presumption of the natural frequency of a satellite may be difficult. In this study, a simple method for determining the longitudinal and lateral minimum natural frequencies of the micro satellites during the ascent phase was clarified. The structure of the micro satellites used in this research is made of aluminum alloy, and they have a monocoque structure. The Young's modulus and moment of inertia of area used to calculate the minimum natural frequencies were determined using the area ratio of the monocoque structure to the entire satellite. When this method is used, the estimated minimum natural frequencies of the longitudinal direction and the lateral direction are in agreement with the measured values acquired by the vibration tests. In order to shorten the process of micro satellites development, this paper describes a practical estimation method of the minimum natural frequency for micro satellites.

Shut-in after fracturing is generally adopted for wells in shale oil reservoirs, and imbibition occurring in matrix nanopores has been proven as an effective way to improve recovery. In this research, the molecular dynamics (MD) simulation was used to investigate the effects of wettability and pressure on nanopores imbibition during shut-in for a typical shale reservoir Jimsar. The results indicate that the microscopic advancement mechanism of the imbibition front is the competitive adsorption between “interfacial water molecules” at the imbibition front and “adsorbed oil molecules” on the pore wall. The essence of spontaneous imbibition involves the adsorption and aggregation of water molecules onto the hydroxyl groups on the pore wall. The flow characteristics of shale oil suggest that the overall push of the injected water to the oil phase is the main reason for the displacement of adsorbed oil molecules. Thus, shale oil especially the heavy hydrocarbon component in the adsorbed layer tends to slip on the walls. However, the weak slip ability of heavy components on the wall surface is an important reason that restricts the displacement efficiency of shale oil during spontaneous imbibition. The effectiveness of spontaneous imbibition is strongly dependent on the hydrophilicity of the matrix pore's wall. The better hydrophilicity of the matrix pore's wall facilitates higher levels of adsorption and accumulation of water molecules on the pore wall and requires less time for “interfacial water molecules” to compete with adsorbed oil molecules. During the forced imbibition process, the pressure difference acts on both the bulk oil and the boundary adsorption oil, but mainly on the bulk oil, which leads to the occurrence of wetting hysteresis. Meanwhile, shale oil still existing in the pore always maintains a good stratified adsorption structure. Because of the wetting hysteresis phenomenon, as the pressure difference increases, the imbibition effect gradually increases, but the actual capillary pressure gradually decreases and there is a loss in the imbibition velocity relative to the theoretical value. Simultaneously, the decline in hydrophilicity further weakens the synergistic effect of pressure difference because of the more pronounced wetting hysteresis. Thus, selecting an appropriate well pressure enables cost savings and maximizes the utilization of the formation's natural power for EOR.

To achieve a micro-destructive and rapid measurement of the wood density of standing trees, this study investigated the feasibility of using the micro-drilling resistance method, formulated a mathematical model, explored the potential for a unified model across multiple tree species, and analyzed the influence of moisture content on measurement accuracy. First, 231 tree cores and drill resistance data were sampled from Pinus massoniana, Cunninghamia lanceolate, and Cryptomeria fortunei. The basic density and moisture content of each core were measured, and the average value of each resistance data record was calculated. Second, the average drill resistance, the natural logarithm of average drill resistance, and absolute moisture content were used as independent variables, while the wood basic density was used as the dependent variable. Third, the total model of the three tree species and sub-model for each tree species were established through a stepwise regression method. Finally, the accuracy of each model was compared and analyzed with that of using the average basic density of each tree species as an estimated density. The results revealed that the estimation accuracy of the sub-model for each tree species was 1.670 percentage points higher than the average value of each tree species used as the density estimation value for these tree species. Additionally, except for Cryptomeria fortunei, the natural logarithm of drill resistance significantly influenced the wood density model at a significance level of 0.05. Moreover, moisture content significantly affected the total model and sub-models of Pinus massoniana at a significance level of 0.05. The estimation accuracy of the total mathematical model was 2.125 percentage points lower than that achieved using the average basic density of each tree species to predict their density. The results indicated the feasibility of using the micro-drilling resistance method to measure the wood density of standing trees. Moreover, the relationship between wood density and drill resistance did not follow a linear pattern, and moisture content slightly influenced the drill needle resistance. Furthermore, the establishment of a mathematical model for each tree species was deemed essential. This study provides valuable guidance for measuring the wood density of standing trees through the micro-drilling resistance method.

Emerging applications of optical technologies are driving the development of miniaturised light sources, which in turn require the fabrication of matching micro-optical elements with sub-1 mm cross sections and high optical quality. This is particularly challenging for spatially-constrained biomedical applications where reduced dimensionality is required, such as endoscopy, optogenetics, or optical implants. Planarisation of a lens by the Fresnel lens approach was adapted for a conical lens (axicon) and was made by direct femtosecond 780 nm/100 fs laser writing in SZ2080™polymer with photo-initiator. Optical characterisation of the positive and negative fraxicons is presented. Numerical modeling of fraxicon optical performance under illumination by incoherent and spatially extended light sources is compared with the ideal case of plane wave illumination. Considering the potential for rapid replication in soft polymers and resists, this approach holds great promise for the most demanding technological applications.

Road traffic transportation has flourished in the process of urbanization by its advantages, but it also produces harmful environmental vibrations. The vibration problem is especially significant for production workshops with precision instruments. A field measurement was conducted to analyze the source characteristics and propagation laws of traffic-induced vibrations. Off the northern side of an urban highway lies a microelectronics workshop. When a large truck passes by, both the vibration responses on the ground and in the workshop considerably increase. Greater vibration is produced in the vertical direction than in the X and Y axes. The predominant frequency band of the vibration response caused by road traffic vehicles is lower than 20 Hz. The vertical vibration responses of the first and second floors in the workshop greatly exceed the VC-C limit because of the high daily traffic flow. Attribute to the excitation of the operation of the manufacturing equipment on the second floor, the vertical vibration level of the second floor is essentially higher than that of the first floor. Therefore, it is impossible to disregard the micro-vibration in the workplace produced by the manufacturing machinery as well as the ex-citement of the road traffic. The measured data can be used to test potential numerical models for forecasting vibrations caused by traffic on roads as well as to guide vibration assessment work throughout the planning and design stages of roads.

The present distribution examines the effects of nozzle diameter, inlet mass rate, and channel geometry on the fuel distribution in annular combustion chambers of micro gas turbines, taking into account the importance of more uniform fuel distribution in the nozzles connected to the fuel supply channels. A comparison has been made between the numerically calculated pressure drop between the inlet and outlet of the fuel supply nozzle and the experimental value obtained. All fuel supply nozzles with a diameter of 500 micrometers are considered for the micro gas turbine. A more uniform distribution results in better combustion and higher efficiency. A geometrical change in the design of the fuel supply nozzle improved the uniformity of the flow distribution without increasing the pressure drop.

The practical necessity of strengthening of reinforced concrete structure elements requires a choice of a method which would provide cost-effectiveness, simplicity of construction and durability of the chosen solution. One of the ways is strengthening using the material belonging to the group of micro-reinforced concretes called ferrocement. The paper presents the comparative analysis of some of the results of RC beams exposed mainly to flexure, strengthened with ferrocement elements (strips) applied by gluing on the on the tensed side of RC beams. The results are obtained using the experimental, analytical and numerical research on the adequate models. Strengthening of the beams was performed in the form of four types of ferrocement strips (four different strip widths and four different numbers of wire mesh layers). The numerical non-linear analysis using finite elements method (FEM) was employed, with the introduction of the corresponding characteristics of constitutive material obtained by the experiments on the test specimens. The analytical researches were performed using known analytical calculation methods in order to formulate the model for the calculation of the ultimate and serviceability limit states of the strengthened cross-section. The results presented in the paper, through their comparative compatibility, confirmed the applicability of this strengthening method.

In the field of clinical medicine, the real-time monitoring of carbon dioxide gas exhaled by the human body is of great significance. At present, the detection devices in the market are mainly detected by sucking a small amount of gas in the nasal cavity to the detection device, and there are some problems such as too long sampling tubes, easy blockage or distortion, and abnormal gas dispersion. In this paper, a micro-nano optical fiber sensor that can directly detect the concentration of end-tidal carbon dioxide is proposed. The measurement is achieved by using the principle of high evanescent field absorption, and the operating band is 2.004 μm. The sensor uses micro-nano optical fiber as the sensing area, and then detects the presence of carbon dioxide gas exhaled by human body through optical power attenuation. The function of micro-nano fiber is to realize the transmission of signal light and also serve as the absorption medium of the gas to be measured. In addition, the variation of light power also reflects the respiratory cycle of the human body. The sensor can realize rapid real-time response to carbon dioxide gas detection, with small size, low cost, and easy to replace. It has great application potential in clinical scenarios such as Gastrointestinal Endoscopes that require real-time monitoring of human respiration.

This paper presents a novel dynamic camera parameter control method for position and posture estimation of highly miniaturized AR markers (micro AR markers) using a low cost general camera. The proposed method performs iterative calculation of the marker’s position and posture to converge them to specified accuracy with dynamically updating the camera’s zoom, focus and other parameter values based on the detected marker’s depth distances. For a 10 mm square micro AR marker, the proposed system demonstrated recognition accuracy of better than ±1.0% for depth distance and 2.5∘ for posture angle with a maximum recognition range of 1.0 m. In addition, the iterative calculation time was at most 0.7 seconds in an initial detection of the marker. These experimental results suggest that the proposed method and system can be applied to a robotic precise handling of small objects with low cost.

The genus Eucalyptus is a globally captivated source of hardwood and is well known for its medicinal uses. The hybrid and wild species of Eucalyptus are widely used as exotic plantations due to their renowned potential of adapting to various systems and sites, furthermore, making the species the most extensively propagated. Despite unquestionable progression in biotechnological and tissue culture approaches, the productivity of plantations is still limited often due to the low efficiency of clonal propagation from cuttings. The obtained F1 hybrids yield high biomass and High-quality low-cost raw material for large-scale production, however, the development of hybrid, clonal multiplication, proliferation, and post-developmental studies are still major concerns. This riveting review describes the problems concerned with in-vitro and clonal propagation of Eucalypt plantation; recent advances in biotechnological and tissue culture practices for massive and rapid micro-propagation of Eucalyptus; as well, highlights the Eucalypt germplasm preservation techniques.

A micro energy harvesting device proposed in the literature, is numerically studied. It consists of two bluff bodies in a micro-channel and a flexible diaphragm at its upper wall. Vortex shedding behind bodies induces pressure fluctuation causing vibration of the diaphragm that converts me-chanical energy to electrical by means of a piezoelectric membrane. Research on enhancing vortex shedding is justified due to the low power output of the device. Amplitude and frequency of un-steady pressure fluctuation on the diaphragm center are numerically predicted. Vortex shedding severity is mainly assessed in terms of pressure amplitude. The CFD model set-up is described in detail and appropriate metrics to assess energy harvesting potential are defined. Several cases are simulated to study the effect of inlet Reynolds number and channel blockage ratio on the prospec-tive performance of the device. Furthermore, the critical blockage ratio leading to vortex shedding suppression is sought. Higher inlet velocity for a constant blockage ratio is found to enhance vor-tex shedding and pressure drop. Great blockage ratio values, but lower than the critical one, seem to provide great pressure amplitudes in the expense of moderate pressure drop. There is evidence that the field is fruitful for research and relevant directions are provided.