U-Net, based on a deep convolutional neural network (CNN), has been clinically used to au-to-segment normal organs and potentially target volumes. However, CNNs with local geometric dependencies may limit the accuracy of segmentation. Additionally, the performance of CNNs can vary depending on the selection of network hyper-parameters, which was mitigated by the proposition of nnU-Net. We chose a vision transformer architecture called VT U-Net, which features a self-attention excluding the convolution layer, to overcome the limitations of CNNs by utilizing global geometric information of images. The VT U-Net v.2 became more powerful thanks to the adaptive hyper-parameter optimizer embedded in nnU-Net. However, despite leveraging the benefits of nnU-Net, VT U-Net v.2 still had additional network hyper-parameters that needed to be optimally chosen. Accordingly, among various hyper-parameters, this study attempted to find the optimal combination of the patch size and the embedded dimension regarding the transformer. From the 4-fold cross-validation, the modified VT U-Net v.2 showed the highest average performance for planning target volume (PTV) segmentation among the investigated networks. Though nnU-Net was based on convolution layers, the adaptive hyper-parameter optimizers turned out to enhance the performance. It was also confirmed that network hyper-parameters affected the segmentation accuracy of vision transformers.

The term "code smell" refers to an indication of a problem with the quality of source code. Numerous studies have been conducted to identify problematic features in source code. Initially, the focus was on utilizing metric-based and heuristic-based approaches. In recent years, however, there has been a shift towards using machine learning and deep learning (DL) techniques for smell detection. Nevertheless, the current algorithms are still considered to be in the early stages of development. Recognizing the challenges associated with identifying smells using DL methods, both academics and software developers have made efforts to address these obstacles. This work involves constructing and evaluating new DL models for code smell detection. Two models are built upon stacked autoencoders, employing a hybrid architecture that combines bidirectional long short-term memory and convolutional neural network components.

This paper explores the tuning and results of two-part models on rich datasets provided through the Casualty Actuarial Society (CAS). These data sets include BI (bodily injury), PD (property damage) and COLL (collision) coverage, each documenting policy characteristics and claims across a four year period. The datasets are explored, including summaries of all variables, then the methods for modeling are set forth. Models are tuned and the tuning results are displayed, after which we train the final models and seek to explain select predictions. All of the code will be made available on GitHub. Data was provided by a private insurance carrier to the CAS after anonymizing the data set. This data is available to actuarial researchers for well-defined research projects that have universal benefit to the insurance industry and the public. Our hope is that the methods demonstrated here can be a good foundation for future ratemaking models to be developed and tested more efficiently.

Botnet Attacks are one of the many types of ways to attack users in their day to day browsing, often of different trends and techniques to take your information without your control. Most firewalls can amply protect you against these trends and techniques, but scarily enough, recent articles and research have shown that they are starting to bypass said firewalls through layers of attacks, confusing your best line of defense. In this Report, we will be looking into exactly what are Botnets and the different subsets, what we can do to combat Botnet Attacks, where do they come from, their origin, the analysis of their kit and what we can put together from information collected. Through this we will be able to reach a conclusion of what we can use to possibly mitigate the effect they have on the internet and stop them from enacting their purpose.

Brain tissue segmentation is an important component of clinical diagnosis of brain diseases by means of multi-modal magnetic resonance imaging (MR). Brain tissue segmentation is developed by many unsupervised methods in literature. The most commonly used unsupervised methods are: K-Means, Expectation Maximization and Fuzzy Clustering. Fuzzy clustering methods offer considerable benefits compared with the aforementioned methods as they are capable of handling brain images which are complex, largely uncertain and imprecise in nature. However, this approach suffers from the intrinsic noise and intensity inhomogeneity (IIH) in the data resulted from the acquisition process. To resolve these issues, we propose a fuzzy consensus clustering algorithm that defines a membership function resulted from a voting schema to cluster the pixels. In particular, we first pre-process the MRI data and employ several segmentation techniques based on traditional fuzzy sets and intuitionistic sets. Then, we adopted a voting schema to fuse the results of the applied clustering methods. Finally, to evaluate the proposed method, we used the well-known performance measures (boundary measure, overlap measure and volume measure) on two publicly available datasets (OASIS and IBSR18). The experimental results show the superior performance of the proposed method in comparison with the recent state of the arts.

Auto-labeling is one of the main challenges in 3D vehicle detection. Auto-labeled datasets can be used to identify objects in LiDAR data, which is a challenging task due to the large size of the dataset. In this work, we propose a novel methodology to generate new 3D based auto-labeling datasets with a different point of view setup than the one used in the most recognized datasets (KITTI, WAYMO, etc.). The performance of the methodology has been further demonstrated with the development of our own dataset with the auto-generated labels and tested under boundary conditions on a bridge in a fixed position. The proposed methodology is based on the YOLO model trained with the KITTI dataset. From a camera-LiDAR sensory fusion, it is intended to auto-label new datasets while maintaining the consistency of the Ground Truth. The main contribution of this work is a novel methodology to auto-label autonomous driving datasets using YOLO as the main labelling system. The performance of this approach is measured retraining the contrast models of the KITTI benchmark.

We describe a multi-resolution approach for audio classification and illustrate its application to the open data set for environmental sound classification. The proposed approach utilizes a multi-resolution based ensemble consisting of targeted feature extraction of approximation (coarse scale) and detail (fine scale) portions of the signal under the action of multiple transforms. This is paired with an automatic machine learning engine for algorithm and parameter selection and the LSTM algorithm, capable of mapping several sequences of features to a predicted class membership probability distribution. Initial results show an improvement in multi-class classification accuracy.

Identification and segmentation of rock particles is very important in geology, mining, engineering construction, and environmental monitoring. Traditional methods for recognizing the rock particle characteristics are time-consuming, labor-intensive, and limited by the geographical scope of the sampling sites, which makes it more difficult to represent the spatial distribution of the rock particles accurately. Recent advancements in deep learning techniques offer promising solutions to automate this process. This study aims at utilizing state-of-the-art (SOTA) Mask R-CNN deep learning algorithm from the Detectron2 framework, to capture global features of rocks that will enable the recognition of rock particles more efficiently, just from having the rock images. These images are subject to image processing techniques such as a Gaussian filter, to denoise and smoothen the image, and an Illumination Adaptive Transformer (IAT) framework, to adjust the lighting exposure; all of which add to improve the quality of the image dataset. Afterward, the Mask R-CNN and Detectron2 models are utilized in training the images using transfer learning. Experimental results from evaluating the performance of the proposed algorithms showcase the effectiveness of the approach, thereby highlighting its potential to revolutionize rock particle segmentation across various domains.

Measuring pulmonary nodules accurately can help with early diagnosis of lung cancer, which can improve a patient’s chances of survival. Many methods for segmenting nodules have been developed, but they all rely on input from radiologists in the form of a 3D volume of interest (VOI) or use a constant region of interest (ROI) and only consider the presence of nodule within the given VOI. These approaches limit the networks’ ability to detect nodules outside the given VOI and can also include unnecessary structures in the VOI, leading to potentially inaccurate segmentation. In this work, we propose a novel approach for 3D lung nodule segmentation by using 2D region of interest (ROI) inputted from radiologist or computer-aided detection (CADe) system. Particularly, we design a dual-encoder-based hard attention network (DEHA-Net) which incorporates the full slice of thoracic computed tomography scan along with the ROI mask to produce an accurate segmentation mask of lung nodule in the given slice. The proposed architecture exploits the adaptive region of interest (A-ROI) algorithm to automatically investigates the penetration of lung nodule into surrounding slices while eliminating the need to drawing separate ROIs in each slice. Further, the framework performs the multi-view analysis, i.e., in sagittal and coronal views, to improve the segmentation performance. The proposed scheme has been rigorously evaluated on the lung image database consortium and image database resource initiative (LIDC/IDRI) dataset and an extensive analysis of results have been performed. The quantitative analysis shows that the proposed method not only improves the existing state-of-the-art in term of dice score but also, significantly robust against the different types, shape and dimensions of lung nodules.

Wi-Fi based localization has become one of the most practical methods for mobile users in location-based services. However, due to the interference of multipath and high-dimensional sparseness of fingerprint data, the localization system based on received signal strength (RSS) is hard to obtain high accuracy. In this paper, we propose a novel indoor positioning method, named JLGBMLoc (Joint denoising auto-encoder with LightGBM Localization). Firstly, because the noise and outliers may influence the dimensionality reduction on high-dimensional sparseness fingerprint data, we propose a novel feature extraction algorithm, named joint denoising auto-encoder (JDAE), which reconstructs the sparseness fingerprint data for a better feature representation and restores the fingerprint data. Then, the LightGBM is introduced to the Wi-Fi localization by scattering the processed fingerprint data to histogram, and dividing the decision tree under leaf-wise algorithm with depth limitation. At last, we evaluated the proposed JLGBMLoc on UJIIndoorLoc dataset and Tampere dataset, experimental results show that the proposed model increases the positioning accuracy dramatically comparing with other existing methods.

With the fast development of the mobile Internet, the online platforms of social networks have rapidly been developing for the purpose of making friends, sharing information, etc. In these online platforms, users being related to each other forms social networks. Literature reviews have shown that social networks have community structure. Through the studies of community structure, the characteristics and functions of networks structure and the dynamical evolution mechanism of networks can be used for predicting user behaviours and controlling information dissemination. Therefore, this study proposes a deep community detection method which includes (1) matrix reconstruction method, (2) spatial feature extraction method and (3) community detection method. The original adjacency matrix in social network is reconstructed based on the opinion leader and nearer neighbors for obtaining spatial proximity matrix. The spatial eigenvector of reconstructed adjacency matrix can be extracted by an auto-encoder based on convolution neural network for the improvement of modularity. In experiments, four open datasets of practical social networks were selected to evaluate the proposed method, and the experimental results show that the proposed deep community detection method obtained higher modularity than other methods. Therefore, the proposed deep community detection method can effectively detect high quality communities in social networks.

This study presents an instant preview and analysis system implementation of intelligent stereo cameras (ISCs). A parameter optimization prototype adopted the instant preview and analysis system of the ISCs has been achieved the automatic alignment function, and obtained optimal stereo films with the automatic alignment function by adjusting gap and angle between dual cameras. The instant preview and analysis system of the ISCs with parameter optimization can enhance the quality of stereo films effectively and reduce filmed errors and save retouched cost and time in harsh filmed environment.

This paper compares a series of traditional and deep learning methodologies for the segmentation of textures. Six well-known texture composites first published by Randen and Hus{\o}y were used to compare traditional segmentation techniques (co-occurrence, filtering, local binary patterns, watershed, multiresolution sub-band filtering) against a deep-learning approach based on the U-Net architecture. For the latter, the effects of depth of the network, number of epochs and different optimisation algorithms were investigated. Overall, the best results were provided by the deep-learning approach. However, the best results were distributed within the parameters, and many configurations provided results well below the traditional techniques.

We propose a novel unsupervised semantic segmentation method for fast and accurate flood area detection utilizing color images acquired from Unmanned Aerial Vehicles (UAVs). To the best of our knowledge, this is the first fully unsupervised method for flood area segmentation in color images captured by UAVs, without the need of pre-disaster images. The proposed framework addresses the problem of flood segmentation based on parameter-free calculated masks and unsupervised image analysis techniques. First, a fully unsupervised algorithm gradually excludes areas classified as non-flood utilizing calculated masks over each component of the LAB colorspace, as well an RGB vegetation index and the detected edges of the original image. Unsupervised image analysis techniques, such as distance transform, are then applied, producing a probability map for the location of flooded areas. Finally, flood detection is obtained by applying the hysteresis thresholding segmentation. The proposed method is tested and compared with variations, and other supervised methods in two public datasets, consisting of 953 color images in total, yielding high-performance results, with 87.4% and 80.9% overall accuracy and F1-Score, respectively. The results and computational efficiency of the proposed method show that it is suitable for on board data execution and decision-making during UAVs flight.

Facial acne is a prevalent dermatological condition regularly observed in the general population. This study introduces a novel deep learning model for facial acne segmentation utilizing a semi-supervised learning method known as bidirectional copy-paste, which synthesizes images by interchanging foreground and background parts between labeled and unlabeled images during the training phase. To overcome the lower performance observed in the labeled image training part compared to the previous methods, a new framework was devised to directly compute the training loss based on labeled images. The effectiveness of the proposed method was evaluated against previous semi-supervised learning methods using images cropped from facial images at acne sites. The proposed method achieved a Dice score of 0.5205 in experiments utilizing only 3% of labels, marking an improvement of 0.0151 to 0.0473 Dice score over previous methods. The proposed semi-supervised learning approach for facial acne segmentation demonstrates improvement in performance, offering a novel direction for future acne analysis.

Currently, most deep learning methods cannot solve the problem of scarcity of industrial product defect samples and significant differences in characteristics. This paper proposes an unsupervised defect detection algorithm based on a reconstruction network, which is realized using only a large number of easily obtained defect-free sample data. The network includes two parts: image reconstruction and surface defect area detection. The reconstruction network is designed through a fully convolutional autoencoder with a lightweight structure. Only a small number of normal samples are used for training so that the reconstruction network can be A defect-free reconstructed image is generated. A function combining structural loss and L1 loss is proposed as the loss function of the reconstruction network to solve the problem of poor detection of irregular texture surface defects. Further, the residual of the reconstructed image and the image to be tested is used as the possible region of the defect, and conventional image operations can realize the location of the fault. The unsupervised defect detection algorithm of the proposed reconstruction network is used on multiple defect image sample sets. Compared with other similar algorithms, the results show that the unsupervised defect detection algorithm of the reconstructed network has strong robustness and accuracy.

Genomics involving tens of thousands of genes is a complex system determining phenotype. An interesting and vital issue is that how to integrate highly sparse genetic genomics data with a mass of minor effects into prediction model for improving prediction power. We find that deep learning method can work well to extract features by transforming highly sparse dichotomous data to lower dimensional continuous data in a non-linear way. This idea may provide benefits in risk prediction based on genome-wide data associated e.g. integrating most of the information in the genotype data. Hence, we developed a multi-stage strategy to extract information from highly sparse binary genotype data and applied it for risk prediction. Specifically, we first reduced the number of biomarkers via a univariable regression model to a moderate size. Then a trainable auto-encoder was used to extract compact representations from the reduced data. Next, we performed a LASSO problem process over a grid of tuning parameter values to select the optimal combination of extracted features. Finally, we applied such feature combination to two prognostic models, and evaluated predictive effect of the models. The results of simulation studies and real data applying indicated that these highly compressed transformation features could better improve predictive performance and did not easily lead to over-fitting.

Machine Learning has completely transformed health care system, which transmits medical data through IOT sensors. So it is very important to encrypt them to protect patient data. encrypting medical images from a performance perspective consumes time; hence the use of an auto encoder is essential. An auto encoder is used in this work to compress the image as a vector prior to the encryption process. The digital image passes across description function and a decoder to get back the image in the proposed work; various experiments are carried out on hyper parameters to achieve the highest outcome of the classification. The findings demonstrate that the combination of Mean Square Logarithmic Error as the loss function, ADA grad as an optimizer, two layers for the encoder, and another reverse for the decoder, RELU as the activation function generates the best auto encoder results. The combination of Mean square error (lose function), RMS prop (optimizer), three layers for the encoder and another reverse for the decoder, and RELU (activation function) has the best classification result. All the experiments with different hyper parameter has run almost very close to each other even when changing the number of layers. The running time is between 9 and 16 second for each epoch.

In this paper, a capacitor microphone system is presented to improve the conversion of mechanical energy to electrical energy using a nonlinear auto regressive moving average-L2 (NARMA-L2) and model predictive control (MPC) controllers for the analysis of the open loop and closed loop system. The open loop system response shows that the output voltage signal need to be improved. The comparison of the closed loop system with the proposed controllers have been analyzed and a promising result have been obtained using Matlab/Simulink.

The delineation of the clinical target volumes (CTVs) for radiation therapy is time-consuming, requires intensive training and shows high inter-observer variability. Supervised deep learning methods depend heavily on consistent training data, thus state-of-the-art research focuses on making CTV labels more homogeneous and strictly bounding them to current standards. International consensus expert guidelines standardize CTV delineation by conditioning the extension of the clinical target volume on surrounding anatomical structures. Training strategies that directly following the construction rules given in the expert guidelines or the possibility to quantify the conformance of manually drawn contours with the guidelines are still missing. 71 anatomical structures that are relevant for CTV delineation in head and neck cancer patients according to the expert guidelines were segmented on 104 CT scans to assess the possibility to automate their segmentation by state-of-the-art deep learning methods. nnU-Net models were trained to automatically segment those 71 structures on planning CT scans. We report the DICE, HD and sDICE for 71 + 5 anatomical structures for most of which no previous segmentation accuracies have been reported. For those structures, for that prediction values have been reported, our segmentation accuracy matched or exceeded the reported values. The predictions from our models were always better than those predicted by the TotalSegmentator. The sDICE with 2mm margin was larger than 80% for almost all structures. Individual structures with decreased segmentation accuracy are analyzed and discussed with respect to their impact on the CTV delineation following the expert guidelines. No deviation is expected to affect the rule-based automation of the CTV delineation.

The automatic diagnosis of cardiovascular diseases has received much attention in the deep learning field. In this context, the segmentation of the left ventricle endocardium constitutes a major task in diagnosing heart conditions such as health failure and hypertrophic cardiomyopathy. The objective of this paper is to propose a "deep convolution network" for segmenting the internal cavity of the left ventricle (endocardium) using MRI images. In particular, we design an improved UNET model which handles additional inception modules for efficiently segmenting the internal cavity of the left ventricle. Our approach has been validated on the Sunnybrook Cardiac Data (SCD) dataset and has showed promising results in terms of precision. More specifically, the improved UNET largely outperforms the baseline UNET model and many existing state-of-the-art methods.

Since the emergence of convolutional neural networks (CNNs), and later vision transformers (ViTs), the standard paradigm for model development has been using a set of identical block types with varying parameters/hyper-parameters. To leverage the benefits of different architectural designs (e.g., CNNs and ViTs), we propose alternating structurally different types of blocks to generate a new architecture, mimicking how Lego blocks can be assembled. Using two CNN-based and one SwinViT-based blocks, we investigate three variations to the so-called LegoNet that apply the new block alternation concept for the segmentation task in medical imaging. We also study a new clinical problem that has not been investigated before – the right internal mammary artery (RIMA) and perivascular space segmentation from computed tomography angiography (CTA). It was proven to demonstrate a prognostic value to primary cardiovascular outcomes. We compare the model performance against popular CNN and ViT architectures using two large datasets (achieving 0.749 dice similarity coefficient (DSC) on the larger dataset). We also evaluate the model’s performance on three external testing cohorts, where an expert clinician corrected model-segmented results (DSC>0.90 for the three cohorts). To assess our proposed model for suitability in clinical use, we perform intra- and inter-observer variability analysis. Finally, we investigate a joint self-supervised learning approach to determine its impact on model performance.

To identify objects in images, a complex set of skills is needed that includes understanding the context and being able to determine the borders of objects. In computer vision, this task is known as semantic segmentation and it involves categorizing each pixel in an image. It is crucial in many real-world situations: for autonomous vehicles, it enables the identification of objects in the surrounding area; in medical diagnosis, it enhances the ability to detect dangerous pathologies early, thereby reducing the risk of serious consequences. In this study, we compare the performance of various ensembles of convolutional and transformer neural networks. Ensembles can be created, e.g, by varying the loss function, data augmentation method or the learning rate strategy. Our proposed ensemble, which is based on the simple average rule, demonstrates exceptional performance on several datasets. All the resources used in this study are available online at the following GitHub repository: https://github.com/LorisNanni.

Polar Mesospheric Summer Echoes (PMSEs) are radar echoes that are observed in the mesosphere during the Arctic summer months in the polar regions. By studying PMSE, researchers can gain insights into physical and chemical processes that occur in the upper atmosphere specifically in the 80 to 90 km altitude range. In this paper, we employ fully convolutional networks such as UNET and UNET++ for the purposes of segmenting PMSE from the EISCAT VHF dataset. First, experiments are performed to find suitable weights and hyperparameters for UNET and UNET++. Second, different loss functions are tested to find one suitable for our task. Third, as the number of PMSE samples used is relatively small that can lead to poor generalization. To address this, image-level and object-level augmentation methods are employed. Four, we briefly explain our findings by employing layerwise relevance propagation.

Topographic mapping using stereo plotting is not effective because it takes much time and labor-intensive. Thus, this research was conducted to find the effective way to extract building footprint for mapping acceleration. Building extraction method in this process comprises four steps: ground / non-ground filtering, building classification, segmentation, and building extraction. Non-ground points from filtering process were classified as building with the algorithm based on multi-scale local dimensionality to separate points at the maximum separability plane. Segmentation using segment growing was used to separate each building, so edge detection could be conducted for each segment to create boundary of each building. Lastly, building extraction was conducted through three steps: edge points detection, building delineation, and building regularization. With 10 samples and step 0.5, classification resulted quality and miss factor of 0.597 and 0.524, respectively. The quality was improved by segmentation process to 0.604, while miss factor was getting worse to 0.561. Meanwhile, on average shape index value from extracted building had 0.02 difference and the number of errors was 30% for line segment comparison. Regarding positional accuracy using centroid accuracy assessment, this method could produce RMSE of 1.169 meters.

Background: White matter hyperintensities (WMH), of presumed vascular origin, are visible and quantifiable neuroradiological markers of brain parenchymal change. These changes may range from damage secondary to inflammation and other neurological conditions, through to healthy ageing. Fully automatic WMH quantification methods are promising, but still, traditional semi-automatic methods seem to be preferred in clinical research. We systematically reviewed the literature for fully automatic methods developed in the last five years, to assess what are considered state-of-the-art techniques, as well as trends in the analysis of WMH of presumed vascular origin. Method: We registered the systematic review protocol with the International Prospective Register of Systematic Reviews (PROSPERO), registration number - CRD42019132200. We conducted the search for fully automatic methods developed from 2015 to July 2020 on Medline, Science direct, IEE Explore, and Web of Science. We assessed risk of bias and applicability of the studies using QUADAS 2. Results: The search yielded 2327 papers after removing 104 duplicates. After screening titles, abstracts and full text, 37 were selected for detailed analysis. Of these, 16 proposed a supervised segmentation method, 10 proposed an unsupervised segmentation method, and 11 proposed a deep learning segmentation method. Average DSC values ranged from 0.538 to 0.91, being the highest value obtained from an unsupervised segmentation method. Only four studies validated their method in longitudinal samples, and eight performed an additional validation using clinical parameters. Only 8/37 studies made available their method in public repositories. Conclusions: We found no evidence that favours deep learning methods over the more established k-NN, linear regression and unsupervised methods in this task. Data and code availability, bias in study design and ground truth generation influence the wider validation and applicability of these methods in clinical research.

This study focuses on understanding how global auto parts companies manage innovation by analyzing keywords in CEO messages from their reports. The study involved three key phases: (1) extraction of innovation-related keywords emphasized in CEO messages, (2) comparison of innovation-related keyword usage between high-performing (upper group) and low-performing (lower group) companies, and (3) analysis of the characteristics of innovation management via internal meaning and the structural interpretation of keywords. A comparison between the upper and lower groups revealed distinct differences in the emphasized keywords. The mapping of open innovation success factors, based on keywords extracted according to eigenvector centrality, identified Provision of Resources and Governance as central to innovation management in the upper group. These findings serve as a benchmark for establishing the direction, vision, and strategy of innovation management in the lower group.

Tuning tensor program generation involves navigating a vast search space to find optimal program transformations and measurements for a program on target hardware. The complexity of this process is further amplified by the exponential combinations of transformations, especially in heterogeneous environments. This research addresses these challenges by introducing a novel approach that learns the joint neural network and hardware features space, facilitating knowledge transfer to new, unseen target hardware. A comprehensive analysis is conducted on the existing state-of-the-art dataset, TenSet, including a thorough examination of test split strategies and the proposal of methodologies for dataset pruning. Leveraging an attention-inspired technique, we tailor the tuning of tensor programs to embed both neural network and hardware-specific features. Notably, our approach substantially reduces the dataset size by up to 53% compared to the baseline without compromising Pairwise Comparison Accuracy (PCA). Furthermore, our proposed methodology demonstrates competitive or improved mean inference times with only 25%40% of the baseline tuning time across various networks and target hardware. The attention-based tuner can effectively utilize schedules learned from previous hardware program measurements to optimize tensor program tuning on previously unseen hardware, achieving a top-5 accuracy exceeding 90%. This research introduces a significant advancement in auto-tuning tensor program generation, addressing the complexities associated with heterogeneous environments and showcasing promising results regarding efficiency and accuracy.

This study compares the efficacy of the two most commonly used surgical methods for pterygium in the Polish population, conjunctival autograft versus amniotic membrane transplantation, and to evaluate the postopera-tive recurrence rate. We retrospectively analysed the medical records of 65 patients who underwent surgery for primary or recurrent pterygium at an ophthalmology clinic in Bialystok, Poland between 2016 and 2020. Surgical success (no regrowth) occurred in almost half of the amniotic membrane patients (44%) and in most of the conjunctival autograft patients (79%); this was a significant relationship. The odds of successful surgery were 79% lower for subjects with amniotic membranes than for those with conjunc-tival autografts (OR with 95% CI = 0.21 (0.05; 0.94]; p = 0.045). Our study confirms that in Polish Caucasian population the success rate of the pro-cedure using conjunctival autograft versus the use of amniotic membrane, is in favoured for the procedure with conjunctival graft.

The constant news about the corona virus is scary. It is not possible to separate treatment for Cancer due to COVID-19. An effective treatment comparison strategy is needed. We need to have a handy tool to understand cancer progression in this unprecedented scenario. Linking different events of cancer progression is the need of the hour. It is a methodological challenge. We provide the solutions to overcome the issue with interval between two consecutive events in motivating head and neck cancer (HNC) data.

A statistical analysis of semantic memory should reflect the complex, multifactorial structure of the relations among its items. Still, a dominant paradigm in the study of semantic memory has been the idea that the mental representation of concepts is structured along a simple branching tree spanned by superordinate and subordinate categories. We propose a generative model of item representation with correlations that overcomes the limitations of a tree structure. The items are generated through "factors" that represent semantic features or real-world attributes. The correlation between items has its source in the extent to which items share such factors and the strength of such factors: if many factors are balanced, correlations are overall low; whereas if a few factors dominate, they become strong. Our model allows for correlations that are neither trivial nor hierarchical, but may reproduce the general spectrum of correlations present in a data-set of nouns. We provide an estimate of the number of concepts that can be stored and retrieved by a large-scale cortical network, the Potts network, which is perhaps approximately 10⁷ with human cortical parameters. When this storage capacity is exceeded, however, retrieval fails completely only for balanced factors; above a critical degree of imbalance, a phase transition leads to a regime where the network still extracts considerable information about the cued item, even if not recovering its detailed representation: partial categorization seems to emerge spontaneously as a consequence of the dominance of particular factors, rather than being imposed ad hoc. We argue this to be a relevant model of semantic memory resilience in Tulving’s remember/know paradigms.

For automobile insurance, it has long been implied that when a policyholder made at least one claim in the prior year, the subsequent premium is likely to increase. When this happens, the policyholder may seek to switch to another insurance company to possibly avoid paying for a higher premium. In such situations, insurers may be faced with the challenges of policyholder retention by keeping premiums low in the face of competition. In this paper, we seek to find empirical evidence of possible association between policyholder switching after a claim and the associated change in premium. In accomplishing this goal, we employ the method of association rule learning, a data mining technique that has its origins in marketing for analyzing and understanding consumer purchase behavior. We apply this unique technique in two stages. In the first stage, we identify policyholder and vehicle characteristics that affect the size of the claim and resulting change in premium regardless of policy switch. In the second stage, together with policyholder and vehicle characteristics, we identify the association among the size of the claim, the level of premium increase and policy switch. This empirical process is often challenging to insurers because they are unable to observe the new premium for those policyholders who switched. However, we used a 9-year claims data for the entire Singapore automobile insurance market that allowed us to track information before and after the switch. Our results provide evidence of a strong association among the size of the claim, the level of premium increase and policy switch. We attribute this to the possible inefficiency of the insurance market because of the lack of sharing and exchange of claims history among the companies.

In this work we introduce an end-to-end multi-modal neural network to segment the Gross Tumor Volume (GTV) from 3D-CBCT’s during radiotherapy. We improve the tumor segmentation by using a U-net which takes additional information such as the tumor mask generated at the planning phase along with the CBCT volume. The mask contains relevant information about the tumor’s location and can guide the model to use this knowledge appropriately to give a better prediction. This technique could become an alternative to produce segmentation masks of GTV in CBCT automatically during radiotherapy as in the traditional RT-pipeline, they are not segmented. We have evaluated our model on a dataset of 82 patients who have undergone radiotherapy. We compare the results of registered target volumes from planning CT as mask seed with 2 different types of multi-modal architectures. Our model shows a DSC of 0.706±0.002 with Late Fusion and 0.702±0.015 with Early Fusion using the GTV Mask. The performance of the two models on this mask is similar, so we perform further experiments with different types of masks which suggest that Late Fusion model produces a better segmentation of the tumor than the Early Fusion model. We also provide an ablation study consisting of a single modality U-net and a metric based on the Planning CT mask registration. It indicates a clear advantage of using our model to produce segmentation for this type of imaging.

Introduction: Dental segmentation in panoramic radiograph has become very relevant in dentistry, since it allows health professionals to carry out their assessments more clearly and helps them to define the best possible treatment plan for their patients. Objectives: In this work, a comparative study is carried out with four segmentation algorithms (U-Net, DCU-Net, DoubleU-Net and Nano-Net) that are prominent in the medical literature on segmentation and we evaluate their results with the current state of the art of dental segmentation in panoramic radiograph. Methods: These algorithms were tested with a dataset consisting of 1,500 images, considering experiment scenarios with and without augmentation data. Results: DoubleU-Net was the model that presented the best results among the analyzed models, reaching 96.591% accuracy and 92.886% Dice using the dataset with data augmentation. Another model that stood out was Nano-Net using the dataset without data augmentation; this model achieved results close to that of the literature with only 235 thousand trainable parameters, while the literature model (TSASNet) contains 78 million. Conclusions: The results obtained in this work are satisfactory and present paths for a better and more effective dental segmentation process.

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

Semantic segmentation is a very popular topic in modern computer vision and it has applications to many fields. Researchers proposed a variety of architectures over time, but the most common ones exploit an encoder-decoder structure that aims to capture the semantics of the image and it low level features. The encoder uses convolutional layers, in general with a stride larger than one, to extract the features, while the decoder recreates the image by upsampling an using skip connections with the first layers. In this work, we use DeepLab as architecture to test the effectiveness of creating an ensemble of networks by randomly changing the activation functions inside the network multiple times. We also use different backbone networks in our DeepLab to validate our findings. We manage to reach a dice coefficient of 0.888, and a mean Intersection over Union (mIoU) of 0.825, in the competitive Kvasir-SEG dataset. Results in skin detection also confirm the performance of the proposed ensemble, which is ranked first with respect to other state-of-the-art approaches (including HardNet) in a large set of testing datasets. The developed code will be available at https://github.com/LorisNanni.

Image segmentation and classification still represent an active area of research since no universal solution can be identified. Established segmentation algorithms like thresholding are problem specific, treat well the easy cases and mostly relied on single parameter i.e intensity. Machine learning approaches offer alternatives where predefined features are combined into different classifiers. On the other hand, the outcome of machine learning is only as good as the underlying feature space. Differential geometry can substantially improve the outcome of machine learning since it can enrich the underlying feature space with new geometrical objects, called invariants. In this way, the geometrical features form a high-dimensional feature space for each pixel, where original objects can be resolved. Alternatives based on the geometry of the image scale-invariant interest points have been exploited successfully in the field of computer vision. Here, we integrate geometrical feature extraction based on signal processing, machine learning, and input relying on domain knowledge. The approach is exemplified on the ISBI 2012 image segmentation challenge data set. As a second application, we demonstrate powerful image classification functionality based on the same principles, which was applied to the HeLa and HEp-2 data sets. Obtained results demonstrate that feature space enrichment properly balanced with feature selection functionality can achieve performance comparable to deep learning approaches.

The segmentation of urban scene mobile laser scanning (MLS) data into meaningful street objects is a great challenge due to the scene complexity of street environments, especially in the vicinity of street objects such as poles and trees. This paper proposes a three-stage method for the segmentation of urban MLS data at the object level. The original unorganized point cloud is first voxelized, and all information needed is stored in the voxels. These voxels are then classified as ground and non-ground voxels. In the second stage, the whole scene is segmented into clusters by applying a density-based clustering method based on two key parameters: local density and minimum distance. In the third stage, a merging step and a re-assignment processing step are applied to address the over-segmentation problem and noise points, respectively. We tested the effectiveness of the proposed methods on two urban MLS datasets. The overall accuracies of the segmentation results for the two test sites are 98.3% and 97%, thereby validating the effectiveness of the proposed method.

Ship pilots and maritime safety administration have an urgent need for more accurate and earlier warnings on strong wind gusts. This study firstly investigates the “Oriental Star” cruise ship cap-sizing event in 2015, one of the deadliest shipwreck events in recent years, and explores all related hydro-meteorological components in a global mesoscale model. It is found that, rather than the missing signal in raw surface wind prediction, the cumulus precipitation variable (CP) increases dramatically during the accident occurrence, which significantly corresponds to the sub-grid strong wind gust. The effective lead-time can be extended from 24hr (deterministic model) to 48hr (en-semble model). This finding is then verified in another two recent deadly cruise boat accidents. The introduction of the new variable is bearing the hope of improvement to the current maritime safeguard system, on predicting sub-grid strong wind gusts for small-size cruise boats in offshore and inland rivers. Finally, an automatic-response system is developed to provide economical con-vection prediction via Inmarsat email communication, aiming to explore operational severe con-vective gust early-warning and appropriate numerical mesoscale model application.

Mechanochemical technology is developing rapidly, judging by the scientific information in both basic and applied studies. However, many issues and points of view remain to be discussed. This review presents some new key issues for the optimization of mechanochemical processes in theoretical and practical aspects. Emphasis is placed on powder technology aspects, which are not always discussed compared to functional or microscopic viewpoints. The transfer of chemical species across the interparticle interface between organic and inorganic species during the mechanosynthesis of nanocomposite oxides offers many new possibilities, which are discussed here in detail. Since all material transport is preceded by charge transfer, its driving force has been searched for using terminology beyond the well-established electrochemical ones. The role of organic compounds during the whole process is emphasized, regardless of their survival in the final product. The similarity with the pharmaceutical phenomena is pointed out, although its mentality is very different from that of the synthesis of nanocomposites. Not only for the rational amorphization of the active pharmaceutical ingredient, but also for the stabilization of molecular dispersion states with the participation of excipients are discussed. The effects of liquids, either added or formed by mechanochemical auto-liquefaction, are presented with reference to the comparison between wet and dry grinding. Finally, mechanisms of apparent stabilization of mechanically activated states of products are elucidated to investigate the practical applicability of mechanochemically synthesized products

The spatial distribution of elements can be regarded as a numerical field of concentration values with a continuous spatial coverage. An active area of research is to discover geologically meaningful relationships among elements from their spatial distribution. To solve this problem, we propose an association rule mining method based on clustered events of spatial auto-correlation and applied it to the polymetallic deposits of the Chahanwusu River area, Qinghai Province, China. The elemental data for stream sediments were first clustered into HH (high-high), LL (low-low), HL (high-low), and LH (low-high) groups by using local Moran’s I clustering map (LMIC). Then the Apriori algorithm was used to mine the association rules among different elements in these clusters. More than 86% of the mined rule points are located within 1000 m of faults and near known ore occurrences, and occur in the upper reaches of the stream and catchment areas. In addition, we found that the Indosinian granodiorite is enriched in sulfophile elements, e.g., Zn, Ag and Cd, and the Variscan granite quartz diorite (P1γδο) coexists with Cu and associated elements. Therefore, the proposed algorithm is an effective method for mining co-existence patterns of elements and provides an insight into their enrichment mechanisms.

This paper describes the use of the Chinese Gaofen-1 (GF-1) satellite imagery to automatically extract tertiary Linear Archaeological Traces of Tuntian Irrigation Canals (LATTICs) located in the Miran site. The site is adjacent to the ancient Loulan Kingdom at the eastern margin of the Taklimakan Desert in western China. GF-1 data was processed following atmospheric and geometric correction, and spectral analyses were carried out for multispectral data. The low values produced by SSI indicate that it is difficult to distinguish buried tertiary LATTICs from similar backgrounds using spectral signatures. Thus, based on the textual characteristics of high-resolutionGF-1 panchromatic data, this paper proposes an automatic approach that combines joint morphological bottom and hat transformation with a Canny edge operator. The operator was improved by adding stages of geometric filtering and gradient vector direction analysis. Finally, the detected edges of tertiary LATTICs were extracted using the GIS-based draw tool and converted into shapefiles for archaeological mapping within a GIS environment. The proposed automatic approach was verified with an average accuracy of 95.76% for 754 tertiary LATTICs in the entire Miran site and compared with previous manual interpretation results. The results indicate that GF-1 VHR PAN imagery can successfully uncover the ancient tuntian agricultural landscape. Moreover, the proposed method can be generalized and applied to extract linear archaeological traces such as soil and crop marks in other geographic locations.

Due to the health crisis caused by SARS-CoV-2, the creation of a new vaccine platform based on mRNA was implemented. Globally, around 13.32 billion COVID-19 vaccine doses of diverse platforms have been given, and up to this date, 69.7% of the total population received at least one injection of a COVID-19 vaccine. Although these vaccines prevent hospitalization and severe forms of the disease, increasing evidence has shown they do not produce sterilizing immunity, allowing people to suffer frequent re-infections. Recent research has also raised concerns that mRNA vaccines could induce immune tolerance, which, added to that caused by the virus itself, could complicate the clinical course of a COVID-19 infection. Furthermore, recent investigations have found high IgG4 levels in people who were administered two or more injections of mRNA vaccines. It has been suggested that an increase in IgG4 levels could have a protecting role by preventing immune over-activation, similar to that occurring during successful allergen-specific immunotherapy by inhibiting IgE-induced effects. Altogether, evidence suggests that the reported increase in the IgG4 levels detected after repeated vaccination with the mRNA vaccines is not a protective mechanism; rather, it may be a part of the immune tolerance mechanism to the spike protein that could promote unopposed SARS-CoV2 infection and replication by suppressing natural antiviral responses. IgG4-induced suppression of the immune system due to repeated vaccination can also cause autoimmune diseases, promotes cancer growth, and autoimmune myocarditis in susceptible individuals.

This paper presents the design and implementation of a multichannel bio-impedance spectroscopy system on field programmable gate arrays (FPGA). The proposed system is capable of acquiring multiple signals from multiple bio-impedance sensors, process the data on the FPGA and store the final data in the on-board Memory. The system employs the Digital Automatic Balance Bridge (DABB) method to acquire data from biosensors. The DABB measures initial data of a known impedance to extrapolate the value of the impedance for the device under test. This method offers a simpler design because the balancing of the circuit is done digitally in the FPGA rather than using an external circuit. Calculations of the impedance values for the device under test were done in the processor. The final data is sent to an onboard Flash Memory to be stored for later access. The control unit handles the interfacing and the scheduling between these different modules (Processor, Flash Memory) as well as interfacing to multiple Balance Bridge and multiple biosensors. The system has been simulated successfully and has comparable performance to other FPGA based solutions. The system has a robust design that is capable of handling and interfacing input from multiple biosensors. Data processing and storage is also performed with minimal resources on the FPGA.

We introduce a novel microscopic image dataset augmented with segmentation and detection labels specifically designed for microplastic analysis in sewage environments. Recognizing the increasing concern over microplastics — particles of synthetic polymers smaller than 5mm — and their detrimental effects on marine ecosystems and human health, our research focuses on enhancing detection and analytical methodologies through advanced computer vision and deep learning techniques. The dataset comprises high-resolution microscopic images of microplastics collected from sewage, meticulously labeled for both segmentation and detection tasks, aiming to facilitate accurate and efficient identification and quantification of microplastic pollution. In addition to dataset development, we present example deep learning models optimized for segmentation and detection of microplastics within complex sewage samples. The models demonstrate significant potential in automating the analysis of microplastic contamination, offering a scalable solution to environmental monitoring challenges. Furthermore, we ensure the accessibility and reproducibility of our research by making the dataset and model codes publicly available, accompanied by detailed documentation on GitHub and LabelBox. The dataset and example deep learning models are publicly available at the following GitHub link. https://anonymous.4open.science/r/Microplastics-in-Sewage-1BEF

Semantic segmentation of remote sensing urban scene imagery is a pixel-wise prediction, which is applied to identify the land-cover or land-use category. However, semantic segmentation demands huge computation cost. In order to reduce the huge computation cost, a common method is to introduce transformer and CNN hybrid method to have a good trade-off between accuracy and computation cost. However, recent CNN-transformer hybrid methods often capture local-global context and cross-window interaction information simultaneously. Then they introduce the local-global context to fuse the local feature, which repeat fuse the local and global feature and result in the additional computation cost. And previous methods often ignore to filter the local and global feature. To fix the problem, we design a lightweight decoder-EDDformer, which is Efficient Global Value Transformer with Dynamic Gatefusion module. Efficient global value transformer only response for extracting global feature. Dynamic Gatefusion module filter the local and global semantic feature and fuse them to capture the local-global context in one time. Extensive experiments reveal that our method not only runs faster but also achieves higher accuracy compared with other state-of-the-art lightweight models.

This article presents a method that uses a semi-automatic algorithm for the detection and analysis of microcracks in steel test specimens using binarized image analysis. It obtains the length along the crack path in contrast to previous methods that have obtained linear length, thereby achieving a closer approximation to its actual value. Additionally, this method automatically calculates the COD and COA parameters with measurement deviations in micrometres, thus providing greater precision than previous methods proposed to date.

Accurate pose estimation is a fundamental ability that all mobile robots must posses in order to navigate a given environment. Much like a human, this ability is dependent on the robot's understanding of a given scene. For Autonomous Vehicles (AV's), detailed 3D maps created beforehand are widely used to augment the perceptive abilities and estimate pose based on current sensor measurements. This approach however is less suited for rural communities that are sparsely connected and cover large areas. Topological maps such as OpenStreetMaps have proven to be a useful alternative in these situations. However, vehicle localization using these maps is non-trivial, particularly for the global localization task, where the map spans large areas. To deal with this challenge, we propose road descriptors along with an initialization technique for localization that allows for fast global pose estimation. We test our algorithms on (real world) maps and benchmark them against other map based localization as well as SLAM algorithms. Our results show that the proposed method can narrow down the pose to within 50 centimeters of the ground truth significantly faster than the state of the art methods.

Foraminifera are single-celled marine organisms that construct shells that remain as fossils in the marine sediments. Classifying and counting these fossils are important in e.g. paleo-oceanographic and -climatological research. However, the identification and counting process has been performed manually since the 1800s and is laborious and time-consuming. In this work, we present a deep learning-based instance segmentation model for classifying, detecting, and segmenting microscopic foraminifera. Our model is based on the Mask R-CNN architecture, using model weight parameters that have learned on the COCO detection dataset. We use a fine-tuning approach to adapt the parameters on a novel object detection dataset of more than 7000 microscopic foraminifera and sediment grains. The model achieves a (COCO-style) average precision of 0.78±0.00 on the classification and detection task, and 0.80±0.00 on the segmentation task. When the model is evaluated without challenging sediment grain images, the average precision for both tasks increases to 0.84±0.00 and 0.86±0.00, respectively. Prediction results are analyzed both quantitatively and qualitatively and discussed. Based on our findings we propose several directions for future work, and conclude that our proposed model is an important step towards automating the identification and counting of microscopic foraminifera.

Active contour models present a robust segmentation approach which make efficient use of specific information about objects in the input data rather than processing all the data. They have been widely used in many applications including image segmentation, object boundary localisation, motion tracking, shape modelling, stereo matching and object reconstruction. In this paper, we investigate the potential of active contour models in extracting roads from Mobile Laser Scanning (MLS) data. The categorisation of active contours based on their mathematical representation and implementation are discussed in detail. We discuss an integrated version in which active contour models are combined to overcome their limitations. We review various active contour based methodologies which have been developed to extract roads and other features from LiDAR and digital imaging datasets. We present a small case study in which an integrated version of active contour models is applied to automatically extract road edges from MLS dataset. An accurate extraction of left and right edges from the tested road section validates the use of active contour models. The present study provides a valuable insight on the potential of active contours for extracting roads and other infrastructures from 3D LiDAR point cloud data.

1) Introduction: Brain parcellation is an important processing step in the analysis of structural brain MRI. Existing software implementations are optimized for fully developed adult brains, and provide inadequate results when applied to neonatal brain imaging. 2) Methods: We developed a semi-automated pipeline, NeBSS, for extracting 50 discrete brain structures from neonatal brain MRI, using an atlas registration method that leverages the existing ALBERT neonatal atlas 3) Results: We demonstrate a simple linear workflow for neonatal brain parcellation. NeBSS is robust to variation in imaging acquisition protocol and magnet field strength. 4) Conclusion: NeBSS is a robust pipeline capable of parcellating neonatal brain MRIs using a simple processing workflow. NeBSS fills a need in clinical translational research in neonatal imaging, where existing automated or semi-automated implementations are too rigid to be successfully applied to multi-center neuroprotection studies and clinically heterogeneous cohorts. The software is open source and freely available.

Digital twins are gaining in popularity for simulating complex natural and urban environments. In this context, accurate segmentation of objects within 3D urban environments is of crucial importance. The aim of this project is to develop a methodology for extracting buildings from textured 3D meshes. To this end, PicassoNet-II, a semantic segmentation architecture is employed. The methodology also incorporates Markov field-based contextual analysis to assess post-segmentation features. In addition, building instantiation is performed using cluster analysis algorithms. Training this model to fit various datasets requires a large amount of annotated data, both from Quebec City, Canada, and from simulated data. Experimental results show that the use of simulated data improves segmentation accuracy, and the DBScan algorithm proves effective in extracting isolated buildings. This project paves the way for improved applications in 3D urban modeling, offering opportunities in fields ranging from urban planning to resource management. The positive results with simulated data reinforce the impact of this research on improving digital models of our ever-changing urban environments.

The vehicles number continuously growing lead to increasingly intense and congested traffic and it will additionally demand the braking system, and drivers behave more aggressively and as result is required that the braking system to be durable and efficient. For this is necessary the study the braking system behavior in conditions of intense and moderate traffic to increase the safety of traffic participants, respectively to demonstrate the need for more frequent replacement of some braking system elements. Thus, on a vehicle were performed a series of successive tests, through which the degree of wear of the brake pads and discs was monitored periodically and as a result the efficiency evolution of the braking system. The tests were carried out both in laboratory (on dynamometer) and in traffic to establish the efficiency of the braking system according to some parameters considered essential. The experimental tests showed that the recommendations regarding the frequency of replacement of brake pads and disks are inconsistent with their actual wear. Therefore, the aim of this paper is the establishment of the braking system efficiency of an auto-vehicle, subject to testing depending on the auto-vehicle mass, travel speed, distance driven, and braking time, based on experimental on stand and in-traffic tests, according the road safety regulations.

The question of the relevance of human and natural capital, as well as the potential adverse effect of natural capital on economic growth, has gained increased attention in development economics. The aim of this paper is to theoretically and empirically assess the relevance of several forms of capital on economic growth in small economies that are dependent upon tourism or natural resources. The empirical framework is based on Impulse Response Functions obtained from Vector Autoregressive models in which we focus on the model where economic growth is the dependent variable for ten small economies that are dependent upon either tourism or natural resources. We find that there is evidence of the ‘’natural resource curse’’, especially in the economies that have a strong dependence on resources that are easily substitutable and whose prices constantly fluctuate. We further find that in the majority of observed cases the type of capital these small economies are most dependent on for their economic growth causes negative impulses in the majority of the observed periods. The main policy recommendation should be to assure that even these small economies should strive towards further diversification and avoid dependence on only one segment of their economy.

Open-vocabulary learning has recently gained prominence as a means to enable image segmentation for arbitrary categories based on textual descriptions. This advancement has extended the applicability of segmentation systems to a broader range of generally purpose scenarios. However, current methods often revolve around specialized architectures and parameters tailored to specific segmentation tasks, resulting in a fragmented landscape of segmentation models. In response to these challenges, we introduce OVAMTSeg, a versatile framework designed for Open-Vocabulary and Multitask Image Segmentation. OVAMTSeg harnesses adaptive prompt learning to empower the model to capture category-sensitive concepts, enhancing its robustness across diverse multi-task and scenario contexts. Text prompts are employed to effectively capture semantic and contextual features of the text, while cross-attention and cross-modal interactions enable the fusion of image and text features. Furthermore, a transformer-based decoder is incorporated for dense prediction. Extensive experimental results underscore the effectiveness of OVAMTSeg, showcasing its state-of-the-art performance and superior generalization capabilities across three segmentation tasks. Notable achievements include a 47.5 mIoU in referring expression segmentation, 51.6 mIoU on Pascal-VOC with four unseen classes, 46.6 mIoU on Pascal-Context in zero-shot segmentation, 65.9 mIoU on Pascal-5i, and 35.7 mIoU on COCO-20i datasets for one-shot segmentation.

Large datasets play a crucial role in the progression of surgical robotics, facilitating advancements in the fields of surgical task recognition and automation. Moreover, public datasets enable the comparative analysis of various algorithms and methodologies, thereby assessing their effectiveness and performance. The ROSMA (Robotics Surgical Maneuvers) dataset provides 206 trials of common surgical training tasks performed with the da Vinci Research Kit (dVRK). In this work, we extend ROSMA dataset with two annotated subsets: ROSMAT24, which contains bounding box annotations for instrument detection, and ROSMAG40, which contains high and low level gesture annotations. We propose an annotation method that provides independent labels for the right-handed tool and the left-handed tool. For instrument identification, we validate our proposal with a YOLOv4 model in two experimental scenarios. We demonstrate the generalization capabilities of the network to detect instruments in unseen scenarios. For gesture segmentation, we propose two label categories: high-level annotations that describe gestures at a maneuvers level, and low-level annotations that describe gestures at a fine-grain level. To validate this proposal, we have designed a recurrent neural network based on a bidirectional long-short term memory layer. We present results for four cross-validation experimental setups, reaching up to a 77.35% mAP.

Oncology has emerged as a crucial field of study and treatment in the domain of medicine. Computed tomography has gained widespread adoption as a radiological modality for the identification and characterisation of pathologies, particularly in oncology, enabling precise identification of affected organs and tissues. However, achieving accurate liver segmentation in computed tomography scans remains a challenge due to the presence of artefacts and the varying densities of soft tissues and adjacent organs. This paper compares artificial intelligence algorithms and traditional medical image processing techniques to assist radiologists in liver segmentation on computed tomography scans, and evaluates their accuracy and efficiency. It is noteworthy that although studies have been conducted on liver segmentation in computed tomography scans, they often lack an intuitive and visual component that allows healthcare professionals to manipulate and observe the results obtained, thereby limiting interaction with the outcomes. From the literature review, challenges such as under-segmentation, over-segmentation, and poor boundary detection, as well as the selection of methods to improve the accuracy and efficiency of liver segmentation in computed tomography scanners, are highlighted as needs to be addressed. The importance of future research in understanding the essential features for the study, generating more datasets, improving segmentation efficiency, and developing lightweight artificial intelligence frameworks for liver segmentation is outlined.

Iberian ham, a traditional Spanish meat product, is renowned for its unique nutritional and sensory attributes, garnering widespread appreciation both domestically and internationally [1]. It is one of the most outstanding Spanish gastronomic treasures, with very special nutritional and sensory properties that make it highly appreciated throughout the world [2]. Recent trends indicate a notable surge in its consumption, a pattern projected to persist [3]. For an enhanced online shopping experience, understanding the specific characteristics and requirements of various consumer segments is crucial. This study aims to scrutinize national Iberian ham consumption patterns and, through survey methodologies, discern the preferences and needs of online consumers purchasing whole Iberian hams. The subsequent cluster analysis will empower suppliers with insights to pinpoint business prospects and craft segment-specific online marketing strategies.

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

The integration of robotics and image processing has led to the realization of robot autonomy in dynamic environments through the provision of visual feedback. This paper presents the application of parallel and open-link robots in palletizing and shape drawing tasks as enhanced by visual feedback from image processing. In determining the set of joint angles that could be used to reach the desired position and orientation of the end effector, the geometric approach in which the spatial geometry of the robotic arms was decomposed into several plane geometry problems was employed. Image processing techniques were used to enhance the performance of the robotic manipulators. In one approach, Color-based segmentation was used to distinguish between different objects in the workspace by using predefined color markers as references in the L*a*b color space. Classification of each pixel in the workspace image was then done by calculating the Euclidean distance between that pixel and a predefined color marker. A second approach employed Edge detection to identify the boundaries of objects within the workspace image by employing the Hough Transform mathematical model to detect the abrupt changes in the image brightness pixel-wise. The pixel locations from Hough were then sorted sequentially to outline the detected object. The integration of image processing with the robotic tasks was expected to improve the precise detection of the position of objects as well as the outline of geometric shapes. The incorporation of visual feedback allowed for dynamic robot manipulation in which prior knowledge of the workspace was not requisite. This led to improved pick and place as well as shape detection as applied in palletizing and shape drawing tasks actuated by the parallel and serial link manipulators, respectively.

Recently, Artificial Intelligence (AI)-based algorithms have revolutionized the medical image segmentation processes. Thus, the precise segmentation of organs and their lesions may contribute to an efficient diagnostics process and a more effective selection of targeted therapies as well as increasing the effectiveness of the training process. Thus, AI may contribute to the automatization of the image scan segmentation process and increase the quality of the resulting 3D objects, which may lead to the generation of more realistic virtual objects. In this paper, we focus on the AI-based solutions applied in the medical image scan segmentation, and intelligent visual-content generation, i.e. computer-generated three-dimensional (3D) images in the context of Extended Reality (XR). We consider different types of neural networks used with a special emphasis on the learning rules applied, taking into account algorithm accuracy and performance, as well as open data availability. This paper also attempts to summarize the current development of AI-based segmentation methods in medical imaging and intelligent visual content generation that are applied in XR. Finally, this paper concludes with possible developments and open challenges in AI application in Extended Reality-based solutions. Finally, the future lines of research and development directions of Artificial Intelligence applications both in medical image segmentation and Extended reality-based medical solutions are discussed.

One of the most leading causes of death worldwide is Colorectal cancer(CRC). Polyp segmentation is the most important detected measure for preventing CRC. However, there is still a missing rate for diminutive polyps and multiple ones. In order to solve the phenomenon, we propose to introduce auxiliary attention module(AAM) that can enhance the learning of features related to multiple and diminutive polyps by focusing more on the located and detailed information. Meanwhile, we design to decrease missed rate of multiple and diminutive polyps by implementing an area adaptive loss(AAL) which adapts the weight according to the area and the number of polyps. Our proposed novel AAM and AAL concentrates on training with hard examples and localized information. To evaluate the effectiveness and generalization ability of our proposed model, We utilize three different datasets of variable sizes and a cross dataset. Our proposed method achieves the best results on the Kvasir-SEG dataset, the CVC-ClinicDB dataset and the cross dataset, particularly for the Kvasir-Sessile dataset consisting of small,flat and diminutive polyps. Extensive experimental results show that our proposed DoubleAANet surpass the performance of all existing state-of-the-art segmentation methods.

While there are several ways to identify customer behaviors, few extract this value from information already in a database, much less extract relevant characteristics. This paper presents the development of a prototype using the recency, frequency, and monetary attributes for customer segmentation of a retail database. For this purpose, the standard K-means, K-medoids, and MiniBatch K-means were evaluated. The standard K-means clustering algorithm was more appropriate for data clustering than other algorithms as it remained stable until solutions with 6 clusters. The evaluation of the clusters’ quality was obtained through the internal validation indexes: Silhouette, Calinski Harabasz, and Davies Bouldin. Once consensus was not obtained, three external validation indexes were applied: global stability, stability per cluster, and segment-level stability across solutions. Six customer segments were obtained, identified by their unique behavior: Lost customers, disinterested customers, recent customers, less recent customers, loyal customers, and best customers. Their behavior was evidenced and analyzed, indicating trends and preferences.

This paper explores the potential of using the SAM segmentator to enhance the segmentation capability of known methods. SAM is a promptable segmentation system that offers zero-shot generalization to unfamiliar objects and images, eliminating the need for additional training. The open-source nature of SAM on GitHub allows for easy access and implementation. In our experiments, we aim to improve the segmentation performance by providing SAM with checkpoints extracted from the masks produced by DeepLabv3+, then merging the segmentation masks provided by these two networks. Additionally, we examine the \enquote{oracle} method (as upper bound baseline performance), where segmentation masks are inferred only by SAM with checkpoints extracted from ground truth. In addition, we tested in the CAMO datasets an ensemble of PVTv2 transformers; combining the ensemble and SAM yields state-of-the-art performance in that dataset. The results of our study provide valuable insights into the potential of incorporating the SAM segmentator into existing segmentation techniques. We release with this paper the open-source implementation of our method.

Plant phenotype plays an important role in crop breeding and planting. Leaf phenotype is an important part of plant phenotype. In order to analyze the leaf phenotype, the target leaf is required to be segmented from the complex background image. In this paper, an automatic soybean leaf segmentation method based on object detection and interactive segmentation models is proposed. Firstly, the Libra R-CNN object detection algorithm is used to detect all soybean leaves in the image. Then, based on the idea that the target soybean leaf is located in the center of the image and the area is large, the detection bounding box of the target leaf is selected. In order not to destroy the segmentation result, the bounding box is optimized to completely enclose the whole leaf. Finally, according to the optimized bounding box, the prior channels of foreground and background are constructed using Gaussian model. The two channels together with the original image are as the input of the interactive object segmentation with inside-outside guidance model to segment the target soybean leaf. A large number of qualitative and quantitative experimental results show that the method has high segmentation accuracy and strong generalization capacity.

Sea ice extraction and segmentation of remote sensing images is the basis for sea ice monitoring. Machine learning-based image segmentation methods rely on manual sampling and require complex feature extraction. Deep-learning semantic segmentation methods have the advantages of high efficiency, intelligence, and automation. Sea ice segmentation using deep learning methods faces the following problems: in terms of datasets, the high cost of sea ice image label production leads to fewer datasets for sea ice segmentation; in terms of image quality, remote sensing image noise and Severe weather conditions affects image quality, which affects the ac-curacy of sea ice extraction. To address the quantity and quality of the dataset, this study used multiple data augmentation methods for data expansion. To improve the semantic segmentation accuracy, the SC-U2-Net network was constructed using multi-scale inflation convolution and a multi-layer Convolutional Block Attention Module (CBAM) attention mechanism for the U2-Net network. The experiments showed that (1) data augmentation solved the problem of an insuffi-cient number of training samples to a certain extent and improved the accuracy of image seg-mentation. (2) This study designed a multilevel Gaussian noise data augmentation scheme to improve the network's ability to resist noise interference and achieve a more accurate segmenta-tion of images with different degrees of noise pollution. (3) The inclusion of a multi-scale inflation perceptron and multi-layer CBAM attention mechanism improved the ability of U2-Net network feature extraction and enhanced the model accuracy and generalization ability.

Fractures of the talar neck and body are associated with spine fractures and scoliosis deformity, which affect cosmetic appearance and cause difficulty in ambulation. The implant design for talus surgery is thriving as a functional alternative in case of severe talar destruction, focusing on segmentation and reconstruction of the talus’s shape. However, manual segmentation of the talus is time-consuming and subjective. In this study we exploited the automatic segmentation framework to efficiently train a deep learning-based model to accurately segment the talus based on computed tomography imaging. We developed three model configurations with nnU-Net and investigated their Dice similarity coefficients (DSC) and 95% Hausdorff distances (HD95) for talus segmentation on a CT image dataset. The three configurations performed well (DSC > 0.95, HD95 < 0.6). When tested on the same samples, one of the configurations was more efficient while ensuring higher accuracy. We propose to focus on talus anatomic variations with increasing age based on this framework and apply it to clinical trials at the next stage.

Convolutional neural network architectures have become increasingly complex, which has improved the performance slowly on well-known benchmark datasets in the recent years. In this research, we have analyzed the true need for such complexity. We have introduced G-Net light, a lightweight modified GoogleNet with improved filter count per layer to reduce feature overlaps and complexity. Additionally, by limiting the amount of pooling layers in the proposed architecture, we have exploited the skip connections to minimize the spatial information loss. The investigations on the proposed architecture are evaluated on three retinal vessel segmentation publicly available datasets. The proposed G-Net light outperforms other vessel segmentation architectures by reducing the number of trainable parameters..

Extensive growth in the volume of irregular brain cells is known as brain tumor. Human brain is surrounded by stiff skull. There are various issues that occur due to the growth of any tumor inside this restricted space. The malignant and benign are two main categories of the brain tumor. The skull is pressurized to enlarge from inside in case of growth of any benign or malignant tumor. This tumor leads to harm in brain and it may be dangerous to life also. The brain tumor is divided into two kinds - primary or secondary. The brain tumor detection techniques have various phases. In this paper, comparative study of CNN with GLCM approach and superpixel based spectral clustering is done tumor. This work takes into account metrics like accuracy, sensitivity and specificity for drawing the comparison between both the techniques.

Segmentation of brain tumor images is a major research topic in medical imaging to have a refined detection and understanding of abnormal masses in the brain. This paper proposes a new segmentation method, consisting of three main steps, to detect brain lesions using magnetic resonance imaging (MRI). In the first step, the parts of the image delineating the skull bone are removed to exclude insignificant data. In the second step, which is the main contribution of this study, the particle swarm optimization (PSO) technique is applied to detect the block that contains the brain lesions. The fitness function, used to determine the best block among all candidate blocks, is based on a two-way fixed-effects analysis of variance (ANOVA). In the last step of the algorithm, the K-means segmentation method is used in the lesion block to classify it as tumor or not. A thorough evaluation of the proposed algorithm is performed using the MRI database provided by the Kouba imaging center in Algiers, Algeria. Estimates of the selected fitness function are first compared to those based on the sum-of-absolute-differences (SAD) dissimilarity criterion and demonstrate the efficiency and robustness of the ANOVA. The performance of the optimized brain tumor segmentation algorithm is then compared to the results of several state-of-the-art techniques, including fuzzy C-means, K-means, Otsu thresholding, local thresholding, and watershed segmentation. The results obtained using Dice coefficient, Jaccard distance, correlation coefficient, and root mean square error (RMSE) measurements demonstrate the superiority of the proposed optimized segmentation algorithm over equivalent techniques.

Orbital fractures are a common finding in facial trauma and serious complications may arise when orbital reconstruction is not done properly. The virtual planning can be used to manufacture patient-specific titanium orbital implants (PSI) through the process of selective laser melting. This method is currently considered the most accurate technique for orbital reconstruction. Even with the most accurate tehniques of bone reconstruction, there are still situations where enophthalmos is present after reconstruction which may be produced by intraorbital soft tissue atrophy. The aim of this paper was to evaluate the orbital soft tissue after postraumatic reconstruction of the orbital walls fractures. 10 patients diagnosed with unilateral orbital fractures were included in this study. A CT scan of the head region with thin slices (0.6mm) and soft and bone tissue windows was done. After data processing, the STL files were exported and the intraorbital fat tissue volume and the muscular tissue volume were masured. The volumes of affected orbit tissues were compared with the volumes of the healthy orbit tissues for each patient. Our findings conclude that a higher or a lower grade of fat and muscular tissue loss is present in all cases of reconstructed orbital fractures.

Anomaly detection and segmentation aim at distinguishing abnormal images from normal images and further localizing the anomalous regions. Feature reconstruction based method has become one of the mainstream methods for this task. This kind of method has two assumptions: (1) The features extracted by neural network is a good representation of the image. (2) The autoencoder solely trained on the features of normal images cannot reconstruct the features of anomalous regions well. But these two assumptions are hard to meet. In this paper, we propose a new anomaly segmentation method based on feature reconstruction. Our approach mainly consists of two parts: (1) We use a pretrained vision transformer (ViT) to extract the features of the input image. (2) We design a self-attention autoencoder to reconstruct the features. We regard that the self-attention operation which has a global receptive field is beneficial to the methods based on feature reconstruction both in feature extraction and reconstruction. The experiments show that our method outperforms the state-of-the-art approaches for anomaly segmentation on the MVTec dataset. It is both effective and time-efficient.

Human beatboxing is a vocal art making use of speech organs to produce vocal drum sounds and imitate musical instruments. Beatbox sound classification is a current challenge that can be used for automatic database annotation and music-information retrieval. In this study, a large-vocabulary humanbeatbox sound recognition system was developed with an adaptation of Kaldi toolbox, a widely-used tool for automatic speech recognition. The corpus consisted of eighty boxemes, which were recorded repeatedly by two beatboxers. The sounds were annotated and transcribed to the system by means of a beatbox specific morphographic writing system (Vocal Grammatics). The image processing techniques plays vital role on image Acquisition, image pre-processing, Clustering, Segmentation and Classification techniques with different kind of images such as Fruits, Medical, Vehicle and Digital text images etc. In this study the various images to remove unwanted noise and performs enhancement techniques such as contrast limited adaptive histogram equalization, Laplacian and Harr filtering, unsharp masking, sharpening, high boost filtering and color models then the Clustering algorithms are useful for data logically and extract pattern analysis, grouping, decision-making, and machine-learning techniques and Segment the regions using binary, K-means and OTSU segmentation algorithm. It Classifying the images with the help of SVM and K-Nearest Neighbour(KNN) Classifier to produce good results for those images.

Automatic Number Plate Recognition is a computer vision technology that provides a way to recognize the vehicles number plates without direct human intervention. Developing Automatic Number Plate Recognition methodologies is a widely studied topic among the computer vision community to increase the accuracy rates. Although there are many studies, the research in character segmentation and improving the recognition accuracy remains limited. In this study, a new methodology is proposed to reduce the character recognition errors of Automatic Number Plate Recognition systems. To achieve this, it will be determined whether the characters are letters or numbers, and the number plates will be expressed in the form of letters - digit. The method suggested for segmenting blobs correctly worked with an accuracy of 96.12% on the test dataset. The method suggested for generating letter-digit expression for the number plates correctly worked with an accuracy of 99.28% on the test dataset. The proposed methodology can work only on Turkish number plates. In the future studies, the proposed methodology can be expanded by using the number plate dataset of a different country.

White matter hyperintensity (WMH) has been considered the primary biomarker from small-vessel cerebrovascular disease to Alzheimer’s disease (AD) and has been reported for its correlation of brain structural changes. To perform WMH related analysis with brain structure, both T1-weighted (T1w) and (Fluid Attenuated Inversion Recovery(FLAIR) are required. However, in a clinical situation, it is limited to obtain 3D T1w and FLAIR images simultaneously. Also, the most of brain segmentation technique supports 3D T1w only. Therefore, we introduced the semi-supervised learning method that can perform brain segmentation using FLAIR image only. Our method achieved a dice overlap score of 0.86 for brain tissue segmentation on FLAIR, with the relative volume difference between T1w and FLAIR segmentation under 4.8%, which is just as reliable as the segmentation done by its paired T1w image. We believe our semi-supervised learning method has a great potential to be used to other MRI sequences and provide encouragement to people who seek brain tissue segmentation from a non-T1w image.

Automated weeding is an important research area in agrorobotics. Weeds can be removed mechanically or with the precise usage of herbicides. Deep Learning techniques achieved state of the art results in many computer vision tasks, however their deployment on low-cost mobile computers is still challenging. These paper present an advanced version of the system presented in [1]. The described system contains several novelties, compared both with its previous version and related work. It is a part of a project of the automatic weeding machine, developed by Warsaw University of Technology and MCMS Warka Ltd. The obtained model reaches satisfying accuracy at over 10~FPS on the Raspberry Pi 3B+ computer. It was tested for four different plant species at different growth stadiums and lighting conditions. The system performing semantic segmentation is based on Convolutional Neural Networks. Its custom architecture mixes U-Net, MobileNets, DenseNet and ResNet concepts. Amount of needed manual ground truth labels was significantly decreased by the usage of knowledge distillation process, learning final model to mimic an ensemble of complex models on the large database of unlabeled data. Further decrease of the inference time was obtained by two custom modifications: in the usage of separable convolutions in DenseNet block and in the number of channels in each layer. In the authors’ opinion, described novelties can be easily transferred to other agrorobotics tasks.

Forest certification is considered a viable market-based policy instrument to promote forest sustainability. It has an important role of play in meeting the objective of modern forestry development in China, which is to sustain ecological and environmental benefits of forests. To understand differences in attitudes, opinions, and interests in forest certification, this study segmented respondents of a landowner’s survey in Shandong, China based on their level of interest in participating in forest certification under different program requirements. Multivariate cluster analysis revealed three distinct groups: likely-, potential-, and unlikely-landowners. We further examined the heterogeneity of these groups in terms of their demographics, ownership characteristics, management objectives, and perceived benefits and challenges with adopting forest certification. The results suggested the necessity of differentiating landowners in formulating and designing specific motivation-based incentives and tailor outreach efforts and communication strategies to improve their interests in forest certification. Findings are useful and interesting to forest policymakers interested in promoting forest certification among landowners in China and other countries facing similar circumstances.

Identifying the total number of fruits on trees has long been of interest in agricultural crop estimation work. Yield prediction of fruits in practical environment is one of the hard and significant tasks to obtain better results in crop management system to achieve more productivity with regard to moderate cost. Utilized color vision in machine vision system to identify citrus fruits, and estimated yield information of the citrus grove in-real time. Fruit recognition algorithms based on color features to estimate the number of fruit. In the current research work, some low complexity and efficient image analysis approach was proposed to count yield fruits image in the natural scene. Semi automatic segmentation and yield calculation of fruit based on shape analysis is presented. Color and shape analysis was utilized to segment the images of different fruits like apple, pomegranate obtained under different lighting conditions. First the input sectional tree image was converted from RGB colour space into the colour space transform (i.e., YUV, YIQ, or YCbCr). The resultant image was then applied to the algorithm for fruit segmentation. After it is applied Morphological Operations which is enhanced image then execute Blob counting method which identify the object and count the number of it. Accuracy of this algorithm used in this thesis is 82.21% for images that have been scanned.

With the development of sensor and communication technologies, Internet of Things (IoT) subsystem is gradually becoming a crucial part in vehicles. It can effectively enhance functionalities of vehicles. However, new attack types are also emerged. For example, a driver with the smart key in the pocket can push the start button to start a car when. At the same time, security issues in the push-to-start scenario are alerted, such as smart key forgery. In this paper, we propose a vehicle Passive Entry Passive Start (PEPS) system that uses deep learning algorithms to recognize the driver by the Electrocardiogram (ECG) signals measured by his or her smart watch. ECG signals are used for verification. Smart watches, as a new smart key of PEPS system, can replace traditional smart keys to improve security. Experiment results show that Long Short-Term Memory (LSTM) models have achieved the best accuracy score for identity recognition (91%) when single ECG cycle is used. However, it takes at least 30 minutes for training. The training time of Auto Encoder successfully reduces to 5 minutes. When 15 continuous ECG cycles are used, it can achieve 100% identity accuracy.

In order to realize the performance degradation trend prediction accurately, a prediction method based on multi-domain features and temporal convolutional network (TCN) is proposed. Firstly, construct a high-dimensional feature set in the multi-domain of vibration signals, and use comprehensive evaluation indicators to preliminarily screen performance degradation indexes with good sensitivity and strong trend. Secondly, the kernel principal component analysis (KPCA) method is adopted to eliminate redundant information between multi-domain features, and construct a health index (HI) based on convolutional auto-encoder (CAE) network. Thirdly, a TCN-based performance degradation trend prediction model is constructed, and direct multi-step prediction is used to predict the performance degradation trend of the monitored object. On this basis, the validity of the proposed method is verified using the bearing public data, and it is successfully applied to performance degradation trend prediction of rolling contact fatigue specimen. The results show that the feature set can be reduced from 14 dimensions to 4 dimensions by using KPCA, while 98.33% of the information of the original feature set is retained. Furthermore, the method of constructing HI based on CAE network is effective. The change process of the HI constructed truly reflects the performance degradation process of the rolling contact fatigue specimen. Compared with the two commonly used HI construction methods, auto-encoding (AE) network and gaussian mixture model (GMM), this method has obvious advantages. At the same time, the prediction model based on TCN can accurately predict the performance degradation of the rolling contact fatigue specimen with the root mean square error 0.0146 and the mean absolute error 0.0105, which has better performance and higher prediction accuracy than the prediction model based on the long short-term memory (LSTM) network and the gated recurrent unit (GRU). This method has general significance and may be extended to the performance degradation prediction of other mechanical equipment/parts.

Variations in groundwater levels that are noticed in different parts of the world are typically the primary focus of research carried out in hydrology. The fluctuating levels of groundwater can be ascribed to several different factors, some of which include an increase in the demand for water, inappropriate irrigation practices, improper management of soil, and unregulated extraction from aquifers. It is necessary to effectively manage groundwater resources to have a trustworthy method of measuring and forecasting groundwater levels. The dynamics of groundwater are inherently uneven and difficult to understand. As a result, applying methods driven by data could potentially yield significant gains in hydrology. In this study, two data-driven models were utilized to estimate groundwater levels at a total of 4 monitoring wells located in Colorado state, USA. These models included ARIMA and ANN. The comparative analysis of the algorithms made use of a data set that had one month's worth of information from each of the years 1980 to 2019. The models were put through their paces, and the results of those tests were statistically and visually assessed. To evaluate the relative accuracy and precision of the models, the mean absolute error (MAE), mean square error (MSE), and root-mean-square error (RMSE) were used. When compared to ARIMA, the analysis demonstrates that ANN can produce the most accurate forecasts of groundwater levels in Colorado state USA.

In the context of developing machine learning models, until and unless we have the required data engineering and machine learning development competencies as well as the time to train and test different machine learning models and tune their hyperparameters, it is worth trying out the automatic machine learning features provided by several cloud-based and cloud-agnostic platforms. This paper explores the possibility of generating automatic machine learning models with low-code experience. We have developed criteria to compare different machine learning platforms for generating automatic machine learning models and presenting their results. Thereafter, lessons learned by developing automatic machine learning models from a sample dataset across four different machine learning platforms were elucidated. We have also interviewed machine learning experts to conceptualize their domain-specific problems that automatic machine learning platforms could address. Results showed that automatic machine learning platforms could provide a fast track for organizations seeking digitalization of their businesses. Automatic machine learning platforms help produce results, especially for time-constrained projects where resources are lacking. The contribution of this paper is in the form of a lab experiment in which we demonstrate how low-code platforms could provide a viable option to many business cases and henceforth provide a lane that is faster than the usual hiring and training of already scarce data scientists and to analytics projects that suffer from overruns.

The purpose of this study is to propose a consecutive manufacturing process system to secure the productivity of excellent STKN540B steel tube in the respect of economy and safety as the supporting material for mega structures such as building, bridge and ship. The components of consecutive manufacturing are press-bending, orbital auto welding and steel tube correction. By using STKN540B a high-strength steel material with low yield point that requires a special manufacturing process unlike other steel materials, an actual tube manufacturing is carried out at each stage in this experimental study. With this, the quality of steel tube and the efficiency of the manufacturing process are analyzed to draw out some points to improve in the future.

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.