Segmentation Process Research Articles

Classifying congenital brain anomalies using deep learning enabled Hunter-Squirrel Search Optimization

ABSTRACT Fetal brain anomalies are probably the most well-known inborn deformities that might be related to syndromic and chromosomal contortion. Early pre-birth location of cerebrum irregularities is fundamental for enhancing clinical management pathways and counselling for parents. To address this issue, Hunter Squirrel Search Optimization (HSSO)_LeNet enabled congenital brain anomaly classification is devised in this work. Commonly, an acquired input image is allowed to the preprocessing stage, which is accomplished by the Weiner filter. The preprocessed ultrasound image is allowed for the segmentation process, where image segmentation is done through 3D U-Net. Thereafter, the segmented image is allowed into the feature extraction process. Then, the brain anomaly classification is carried out using Deep Convolutional Neural Network (DCNN), where the hyperparameters are optimally tuned using the proposed HSSO. Consequently, the proposed HSSO algorithm is devised by incorporating the Hunter – Prey Optimizer (HPO) algorithm and the Squirrel Search Algorithm (SSA). Finally, the classification of congenital brain anomalies is carried out by LeNet, which is tuned by the proposed HSSO. The proposed technique has attained an accuracy of 93.79%, a True positive rate (TPR) of 94.67%, and a True Negative Rate (TNR) of 92.15%.

Automating Prostate Cancer Grading: A Novel Deep Learning Framework for Automatic Prostate Cancer Grade Assessment using Classification and Segmentation.

Prostate Cancer (PCa) is the second most common cancer in men and affects more than a million people each year. Grading prostate cancer is based on the Gleason grading system, a subjective and labor-intensive method for evaluating prostate tissue samples. The variability in diagnostic approaches underscores the urgent need for more reliable methods. By integrating deep learning technologies and developing automated systems, diagnostic precision can be improved, and human error minimized. The present work introduces a three-stage framework-based innovative deep-learning system for assessing PCa severity using the PANDA challenge dataset. After a meticulous selection process, 2699 usable cases were narrowed down from the initial 5160 cases after extensive data cleaning. There are three stages in the proposed framework: classification of PCa grades using deep neural networks (DNNs), segmentation of PCa grades, and computation of International Society for Urological Pathology (ISUP) grades using machine learning classifiers. Four classes of patches were classified and segmented (benign, Gleason 3, Gleason 4, and Gleason 5). Patch sampling at different sizes (500 × 500 and 1000 × 1000 pixels) was used to optimize the classification and segmentation processes. The segmentation performance of the proposed network is enhanced by a Self-organized operational neural network (Self-ONN) based DeepLabV3 architecture. Based on these predictions, the distribution percentages of each cancer grade within the whole slide images (WSI) were calculated. These features were then concatenated into machine learning classifiers to predict the final ISUP PCa grade. EfficientNet_b0 achieved the highest F1-score of 83.83% for classification, while DeepLabV3 + architecture based on self-ONN and EfficientNet encoder achieved the highest Dice Similarity Coefficient (DSC) score of 84.9% for segmentation. Using the RandomForest (RF) classifier, the proposed framework achieved a quadratic weighted kappa (QWK) score of 0.9215. Deep learning frameworks are being developed to grade PCa automatically and have shown promising results. In addition, it provides a prospective approach to a prognostic tool that can produce clinically significant results efficiently and reliably. Further investigations are needed to evaluate the framework's adaptability and effectiveness across various clinical scenarios.

Deep Learning Approaches in Medical Image Segmentation: Implications for Brain Tumor Detection and Analysis

The procedure of image segmentation involves splitting images into distinct components to discern similarities or differences between regions. This facilitates the quantitative and/or qualitative analysis of lesions, thereby enhancing the reliability and accuracy of medical diagnoses. Traditionally, medical image segmentation was performed manually, slice by slice, requiring a high level of expertise to accurately define boundaries for individual areas. This manual process is time-consuming and error-prone. Currently, several deep learning methods have achieved significant advancements in image segmentation, surpassing the accuracy of traditional approaches. This study reviewed the effectiveness of deep learning models in accurately segmenting images of brain tumor patients. A search of the PubMed and Google Scholar databases, as well as the Asian Journal archives, was conducted to retrieve recent literature using the keywords: deep learning, Magnetic Resonance Imaging, image segmentation, and medical image processing. References from relevant literature were also reviewed to obtain additional sources. A critical and direct assessment of deep learning technologies on tumor MRI images was subsequently performed using these sources. The Dice scores served as metrics for evaluating the performance of the deep learning models. Based on the Dice scores, it can be inferred that deep learning models such as 3D FCNs, ResNet models, AGSE-VNet models, and encoder-decoder CNN architectures exhibit high segmentation accuracy in brain tumor images. The promising results demonstrated by deep learning-based segmentation approaches underscore their potential to enhance diagnostic capabilities in brain tumor detection and analysis.

Automated Dental Registration and TMJ Segmentation for Virtual Surgical Planning of Orthognathic Surgery via Three-Step Computer-Based Method

Objective: This study developed and evaluated a computer-based method for automating the registration of scanned dental models with 3D reconstructed skulls and segmentation of the temporomandibular joint (TMJ). Methods: A dataset comprising 1274 skull models and corresponding scanned dental models was collected. In total, 1066 cases were used for the development of the computer-based method, while 208 cases were used for validation. Performance was evaluated by comparing the automated results with manual registration and segmentation performed by clinicians, using accuracy and completeness metrics (e.g. intersection of union [IoU] and Dice similarity coefficient [DSC]). Results: The automated registration achieved a mean absolute error of 0.35 mm for the maxilla and 0.38 mm for the mandible, and a root mean squared error of 0.46 mm and 0.39 mm, respectively. The automatic TMJ segmentation exhibited an accuracy of 97.48%, a precision of 97.06%, a IoU of 95.72%, DSC of 97.3%, and a Hausdorff value of 1.87 mm, which were sufficient for clinical application. Conclusion: The proposed method significantly improved the efficiency of orthognathic surgical planning by automating the registration and segmentation processes. The accuracy and precision of the automated results were sufficient for clinical use, reducing the workload on clinicians and facilitating faster and more reliable surgical planning. Clinical significance: The computer-based method streamlines orthognathic surgical planning, enhancing precision and efficiency without compromising clinical accuracy, ultimately improving patient outcomes and reducing the workload of surgeons.

Age estimation by radiomics analysis of mandibular condylar cone beam computed tomography images.

The aim of this study was to estimate the legal age using the parameters obtained from radiomic analysis of the mandibular condyle in cone beam computed tomography (CBCT) images. The study group consisted of 300 mandibular condyles, which were categorized into six groups based on the age of the patients: 8-11years, 12-14years, 15-17years, 18-20years, 21-23years, and over 24years. Each patient's condyle was segmented individually using the 3D Slicer program. Radiomic features were extracted from the segmented images using the SlicerRadiomics plugin. Subsequently, three distinct models were developed with reference to three specific subgroups of the 12-14 age group, 15-17 age group, 18-20 age group and the efficacy of radiomic features in predicting the age of the patient was evaluated. The ROC analysis of the three radiomics scores (RS) yielded AUC values of 0.927, 0.860, and 0.769 for RS12-14, RS15-17, and RS18-20, respectively. The RS12-14 model exhibited the highest sensitivity and specificity values among the models, with 88% and 84.4%, respectively. Among the radiomic features extracted from the mandibular condyle in CBCT images, the most significant features, identified based on developed models and their respective coefficients, can be applied to estimate patients' ages. Future studies hold substantial potential for advancing this method, particularly in automating both the segmentation process and the derivation of formulae for age estimation. The use of radiomic features for age prediction presents a promising alternative method for developing fully automated systems in clinical practice.

Neural decoding reveals dynamic patterns of visual chunk memory processes.

Chunk memory constitutes the basic unit that manages long-term memory and converts it into immediate decision-making processes, it remains unclear how to interpret and organize incoming information to form effective chunk memory. This paper investigates electroencephalography (EEG) patterns from the perspective of time-domain feature extraction using chunk memory in visual statistical learning and combines time-resolved multivariate pattern analysis (MVPA). The GFP and MVPA results revealed that chunk memory processes occurred during specific time windows in the learning phase. These processes included attention modulation (P1), recognition and feature extraction (P2), and segmentation for long-term memory conversion (P6). In the decision-making stage, chunk memory processes were encoded by four ERP components. Scene processing correlated with P1, followed by feature extraction facilitated by P2, encoding process (P4), and segmentation process (P6). This paper identifies the early process of chunk memory through implicit learning and applies univariate and multivariate approaches to establish the neural activity patterns of the early chunk memory process, which provides ideas for subsequent related studies.

A Comprehensive Review on Biomedical Image Classification using Deep Learning Models

Medical imaging is one of the most efficient tools for visualizing the interior organs of the body and its associated diseases. Medical imaging is used to diagnose diseases and offer treatment. Since the manual examination of a massive number of Medical Images (MI) is a laborious and erroneous task, automated MI analysis approaches have been developed for computer-aided diagnostic solutions to reduce time and enhance diagnostic quality. Deep Learning (DL) models have exhibited excellent performance in the MI segmentation, classification, and detection process. This article presents a comprehensive review of the recently developed DL-based MIK classification models for various diseases. The current review aims to assist researchers and physicians of biomedical imaging in understanding the basic concepts and recent DL models. It explores recent MI classification techniques developed for various diseases. A thorough discussion on Computer Vision (CV) and DL models is also carried out.

Optimizing Skin Cancer Diagnosis: A Modified Ensemble Convolutional Neural Network for Classification.

Skin cancer is recognized as one of the most harmful cancers worldwide. Early detection of this cancer is an effective measure for treating the disease efficiently. Traditional skin cancer detection methods face scalability challenges and overfitting issues. To address these complexities, this study proposes a random cat swarm optimization (CSO)with an ensemble convolutional neural network (RCS-ECNN) method to categorize the different stages of skin cancer. In this study, two deep learning classifiers, deep neural network (DNN) and Keras DNN (KDNN), are utilized to identify the stages of skin cancer. In this method, an effective preprocessing phase is presented to simplify the classification process. The optimal features are selected using the feature extraction phase. Then, the GrabCut algorithm is employed to carry out the segmentation process. Also, the CSO is employed to enhance the effectiveness of the method. The HAM10000 and ISIC datasets are utilized to evaluate the RCS-ECNN method. The RCS-ECNN method achieved an accuracy of 99.56%, a recall of 99.66%, a specificity value of 99.254%, a precision value of 99.18%, and an F1-score value of 98.545%, respectively. The experimental results demonstrated that the RCS-ECNN method outperforms the existing techniques.

Transformer-Based Explainable Model for Breast Cancer Lesion Segmentation

Breast cancer is one of the most prevalent cancers among women, with early detection playing a critical role in improving survival rates. This study introduces a novel transformer-based explainable model for breast cancer lesion segmentation (TEBLS), aimed at enhancing the accuracy and interpretability of breast cancer lesion segmentation in medical imaging. TEBLS integrates a multi-scale information fusion approach with a hierarchical vision transformer, capturing both local and global features by leveraging the self-attention mechanism. This model addresses the limitations of existing segmentation methods, such as the inability to effectively capture long-range dependencies and fine-grained semantic information. Additionally, TEBLS incorporates visualization techniques to provide insights into the segmentation process, enhancing the model’s interpretability for clinical use. Experiments demonstrate that TEBLS outperforms traditional and existing deep learning-based methods in segmenting complex breast cancer lesions with variations in size, shape, and texture, achieving a mean DSC of 81.86% and a mean AUC of 97.72% on the CBIS-DDSM test set. Our model not only improves segmentation accuracy but also offers a more explainable framework, which has the potential to be used in clinical settings.

Development of an Optimized YOLO-PP-Based Cherry Tomato Detection System for Autonomous Precision Harvesting

An accurate and efficient detection method for harvesting is crucial for the development of automated harvesting robots in short-cycle, high-yield facility tomato cultivation environments. This study focuses on cherry tomatoes, which grow in clusters, and addresses the complexity and reduced detection speed associated with the current multi-step processes that combine target detection with segmentation and traditional image processing for clustered fruits. We propose YOLO-Picking Point (YOLO-PP), an improved cherry tomato picking point detection network designed to efficiently and accurately identify stem keypoints on embedded devices. YOLO-PP employs a C2FET module with an EfficientViT branch, utilizing parallel dual-path feature extraction to enhance detection performance in dense scenes. Additionally, we designed and implemented a Spatial Pyramid Squeeze Pooling (SPSP) module to extract fine features and capture multi-scale spatial information. Furthermore, a new loss function based on Inner-CIoU was developed specifically for keypoint tasks to further improve detection efficiency.The model was tested on a real greenhouse cherry tomato dataset, achieving an accuracy of 95.81%, a recall rate of 98.86%, and mean Average Precision (mAP) scores of 99.18% and 98.87% for mAP50 and mAP50-95, respectively. Compared to the DEKR, YOLO-Pose, and YOLOv8-Pose models, the mAP value of the YOLO-PP model improved by 16.94%, 10.83%, and 0.81%, respectively. The proposed algorithm has been implemented on NVIDIA Jetson edge computing devices, equipped with a human–computer interaction interface. The results demonstrate that the proposed Improved Picking Point Detection Network exhibits excellent performance and achieves real-time accurate detection of cherry tomato harvesting tasks in facility agriculture.

Research on Negative Road Obstacle Detection Based on Multimodal Feature Enhancement and Fusion

To address the issues of low recognition rates and poor detection accuracy for road negative obstacles caused by insufficient feature representation, we propose a novel detection framework: the Negative Road Obstacles Segmentation Network (NROSegNet). The detection performance of the algorithm is improved through a data enhancement strategy based on feature splicing and an adaptive feature enhancement module. Specifically, the data augmentation strategy introduces negative obstacle features into other datasets through geometric transformations and random splicing, effectively increasing the diversity of training data. This can solve the problem of an uneven distribution of data features while improving the performance of the model in capturing illumination changes and local details. The framework further adopts a dynamic multi-scale feature enhancement module to improve the perception of local details and global semantics. A robust multimodal data fusion mechanism and edge-aware optimization strategy are designed to effectively alleviate the problems of noise interference and boundary blur. The experimental results show that the NROSegNet proposed in this paper achieves 70.6 and 83.0 in mIoU and mF1, respectively, which is 2.8 percentage points and 2.9 percentage points higher than other methods. The results fully demonstrate its excellent performance in precise segmentation and boundary detail processing.

Preparation of Silicon Nanopillar Arrays Using Reactive Ion Etching with a Faraday Cage.

Faraday cages are extensively utilized in plasma-based etching and deposition processes to regulate ion behavior due to their shielding effect on electromagnetic fields. Herein, vertical silicon nanopillar arrays are fabricated through SF6 and O2 reactive ion etching. By incorporation of a Faraday cage in the plasma equipment, the impact of the Faraday cage on the morphology of the silicon nanopillars is analyzed; the Faraday cage blocks out the sputtered particles and eradicates the formation of silicon nanograss. Specifically, it regulates the value and dispersion of the etching rate by varying the mesh number and the distance from the grid wires to the sample surface. A "flattening belly" phenomenon of silicon nanopillars associated with the temperature is resolved using segmented multiple etching processes. This research contributes to an in-depth analysis of plasma etching using a Faraday cage as well as potential applications for silicon nanopillars.

Accurate LAI estimation of soybean plants in the field using deep learning and clustering algorithms.

The leaf area index (LAI) is a critical parameter for characterizing plant foliage abundance, canopy structure changes, and vegetation productivity in ecosystems. Traditional phenological measurements are often destructive, time-consuming, and labor-intensive. This paper proposes a high-throughput 3D point cloud data processing pipeline to segment field soybean plants and estimate their LAI. The 3D point cloud data is obtained from a UAV equipped with a LiDAR camera. First, The PointNet++ model was applied to simplify the segmentation process by isolating field soybean plants from their surroundings and eliminating environmental complexities. Subsequently, individual segmentation was achieved using the Watershed approach and k-means clustering algorithms, segmenting the field soybeans into individual plants. Finally, the LAI of soybean plant was estimated using a machine learning method and validated against measured values. The PointNet++ model improved segmentation accuracy by 6.73%, and the watershed algorithm achieved F1 scores of 0.89-0.90, outperforming k-means in complex adhesion cases. For LAI estimation, the SVM model showed the highest accuracy (R² = 0.79, RMSE = 0.47), with RF and XGBoost also performing well (R² > 0.69, RMSE< 0.65). This indicates that the individual segmentation algorithm, Watershed-based approach combined with PointNet++, can serve as a crucial foundation for extracting high-throughput plant phenotypic data. The experimental results confirm that the proposed method can rapidly calculate the morphological parameters of each soybean plant, making it suitable for high-throughput soybean phenotyping.

A Comprehensive Review on Brain Tumor Detection Using Advanced Learning Algorithms

Early detection of brain tumor is of critical importance in medical imagery. It reviews the application of advanced learning algorithms to increase the accuracy and efficiency of brain tumor detection using noninvasive imaging (in particular MRI). In the last couple of years, recent machine learning and deep learning approaches like Convolutional Neural Networks (CNNs), Support Vector Machines (SVMs), and hybrid models have shown an overnight progress by automating the process of extraction, segmentation, and classification of brain tumors. Tumor sub-region identification and feature selection has been improved by using techniques such as Random Forest classifiers, unsupervised clustering, and ensemble methods. Secondly, detection performance has been improved by the integration of handcrafted and automatic features, including texture, shape, and intensity. Further feature selection process is dimensionality reduction based techniques like Principal Component Analysis (PCA) and Information Gain (IG). The focus of this review is on the increasing usefulness of these algorithms to achieve adequate diagnosis and discuss future trends in personalized diagnostics and treatment planning.

A Cross-scale Attention-Based U-Net for Breast Ultrasound Image Segmentation.

Breast cancer remains a significant global health concern and is a leading cause of mortality among women. The accuracy of breast cancer diagnosis can be greatly improved with the assistance of automatic segmentation of breast ultrasound images. Research has demonstrated the effectiveness of convolutional neural networks (CNNs) and transformers in segmenting these images. Some studies combine transformers and CNNs, using the transformer's ability to exploit long-distance dependencies to address the limitations inherent in convolutional neural networks. Many of these studies face limitations due to the forced integration of transformer blocks into CNN architectures. This approach often leads to inconsistencies in the feature extraction process, ultimately resulting in suboptimal performance for the complex task of medical image segmentation. This paper presents CSAU-Net, a cross-scale attention-guided U-Net, which is a combined CNN-transformer structure that leverages the local detail depiction of CNNs and the ability of transformers to handle long-distance dependencies. To integrate global context data, we propose a cross-scale cross-attention transformer block that is embedded within the skip connections of the U-shaped architectural network. To further enhance the effectiveness of the segmentation process, we incorporated a gated dilated convolution (GDC) module and a lightweight channel self-attention transformer (LCAT) on the encoder side. Extensive experiments conducted on three open-source datasets demonstrate that our CSAU-Net surpasses state-of-the-art techniques in segmenting ultrasound breast lesions.

Tourist Market Segmentation Strategies

Traveler is consumers who do purchasing and fulfillment need related with product tourism. And individuals who do purchase a product or can it is said as request individual. While more from One individual who does request to a product so it is said as market demand for products So market demand is​ gathering more from One individual who does request products . Specifically the tourist market is gathering from consumer product tourism. Size the size of the market indicates how much Lots amount consumers. For marketers will try For get a number of consumer as its target market. Such as outlined Kotler relatedness between behavior consumer with analysis marketing. In the analysis marketing there is marketing strategy relationship with the market as the target. After then determine the target market marketing strategy is carried out For influence behavior consumer as part from the market. While the target market can known after market division process is carried out. Market division can be done based on criteria certain from Consumers. Activities dividing the market is called activity market segmentation (market segmentation). So market segmentation is activity segmenting the market consisting of from various criteria behavior buyers. While the existence of a market is necessary done activity market segmentation. Because the market is gathering or a group of people who will buy product. So the market does not must identical with location certain but more is a process of interaction between consumer as buyers and marketers as party seller product. In chapter This discuss definition and concept segmentation consumer as part from the market. Among them are the segmentation process, as well as procedure in do activity market segmentation. Understanding the need done segmentation For products and approaches in segmentation . The basis in do segmentation as well as stages in do segmentation.

Assessment of the correlation between the volume of tongue, oral cavity, tongue/oral cavity volume ratio and the upper airway in unilateral cleft subjects: A CBCT study.

The current study was conducted to assess the volume of the tongue, oral cavity, and tongue/oral cavity and their correlation with the volume of the upper airway in cleft subjects compared with the control group. The study population included 60 CBCT images from dental school. The sample comprised 30 unilateral cleft patients and 30 sex and age-matched healthy subjects. The CBCT images were imported to the Mimics software in DICOM format. Then, the segmentation process was done in order to create distinct masks for the upper airway, oral cavity, and tongue. The software calculated the volume of the created masks. The volume of tongue, oral and upper airway were significantly lower in cleft patients than in the control group (P value < 0.05 taken as statistically significant). There was a weak but statistically significant correlation between the U.A.W.V and T.V in both cleft and non-cleft subjects. Additionally, there was a statistically significant correlation between the O.C.V and the U.A.W.V in cleft subjects. Except than the proportion of tongue/oral cavity volume, other volumetric measurements were significantly lower in cleft subjects than control group. This reveals that clefts are not necessarily more susceptible to obstructive sleep apnea. Also, the positive correlation between the volume of the tongue and oral cavity with the upper airway confirms that early expansion of the maxillary region in clefts helps significantly in increasing their upper airway volume.

A Heuristic Strategy Assisted Deep Learning Models for Brain Tumor Classification and Abnormality Segmentation

ABSTRACTBrain tumors are prevalent forms of malignant neoplasms that, depending on their type, location, and grade, can significantly reduce life expectancy due to their invasive nature and potential for rapid progression. Accordingly, brain tumors classification is an essential step that allows doctors to perform appropriate treatment. Many studies have been done in the sector of medical image processing by employing computational methods to effectively segment and classify tumors. However, the larger amount of information collected by healthcare images prohibits the manual segmentation process in a reasonable time frame, reducing error measures in healthcare settings. Therefore, automated and efficient techniques for segmentation are crucial. In addition, various visual information, noisy images, occlusion, uneven image textures, confused objects, and other features may impact the process. Therefore, the implementation of deep learning provides remarkable results in medicinal image processing, particularly in the segmentation and classification process. However, conventional deep learning‐assisted methods struggle with complex structures and dimensional issues. Thus, this paper develops an effective technique for diagnosing brain tumors. The main aspect of the proposed system is to classify the brain tumor types by segmenting the affected regions of the raw images. This novel approach can be applied for various applications like diagnostic centers, decision‐making tools, clinical trials, medical research institutes, disease prognosis, and so on. Initially, the requisite images are collected from standard datasets and further, it is subjected to the segmentation period. In this stage, the Multi‐scale and Dilated TransUNet++ (MDTUNet++) model is employed to segment the abnormalities. Further, the segmented images are given into an Adaptive Dilated Dense Residual Attention Network (ADDRAN) to classify the brain tumor types. Here, to optimize the ADDRAN technique's parameters, an Improved Hermit Crab Optimizer (IHCO) is supported, which increases the accuracy rates of the overall network. Finally, the numerical examination is conducted to guarantee the robustness and usefulness of the designed model by contrasting it with other related techniques. For Dataset 1, the accuracy value attains 93.71 for the proposed work compared to 87.86 for CNN, 90.18 for DenseNet, and 89.56 and 90.96 for RAN and DRAN, respectively. Thus, supremacy has been achieved for the recommended system while detecting the brain tumor types.

A New Transformation Method of the T2 Spectrum Based on Ordered Clustering—A Case Study on the Pore-Throat Utilization Rule of Supercritical CO2 Flooding in Low Permeability Cores

Nuclear magnetic resonance (NMR) and high-pressure mercury injection (HPMI) have been widely used as common characterization methods of pore-throat. It is generally believed that there is a power function relationship between transverse relaxation time (T2) and pore-throat radius (r), but the segmentation process of the pore-throat interval is subjective, which affects the conversion accuracy. In this paper, ordered clustering is used to improve the existing segmentation method of the pore-throat interval, eliminate the subjectivity in the segmentation process, and obtain a more accurate distribution curve of the pore-throat. For the three kinds of cores with ordinary-low permeability (K &gt; 1 mD), ultra-low permeability (0.1 mD &lt; K &lt; 1 mD), and super-low permeability (K &lt; 0.1 mD), the pore-throat distribution curves of the cores were obtained by using the improved T2 conversion method. Then, the oil and gas two-phase displacement experiment was carried out to investigate the degree of recovery and cumulative gas–oil ratio changes during the displacement process. Finally, the converted T2 spectrum was used to quantify the utilization of different pore sizes. The improved T2 conversion method not only has better accuracy but also is not limited by the pore-throat distribution types (such as unimodal, bimodal, and multi-modal, etc.) and is suitable for any core with measured HPMI pore-throat distribution and an NMR T2 spectrum. Combined with the results of core displacement and the degree of pore-throat utilization, it is found that the potential of miscible flooding to improve the recovery degree is in the order of ordinary-low permeability core (18–22%), ultra-low permeability core (25–29%), and super-low permeability core (8–12%). The utilization degree of immiscible flooding to the &lt;10 nm pore-throat is low (up to 35%), while miscible flooding can effectively use the &lt;3.7 nm pore-throat (up to 73%). The development effect of supercritical CO2 flooding on K &lt; 0.1 mD reservoirs is not good, the seepage resistance of CO2 is large, the miscible flooding makes it difficult to improve the recovery degree, and the utilization effect of pore-throat is poor.

Enhancing Autonomous Vehicle Navigation in Complex Environment With Semantic Proto‐Reinforcement Learning

ABSTRACTDespite great progress in autonomous vehicle (AV) navigation, the technical challenges within this space are still considerable when it comes to successful integration of AVs into complex real‐world environments. To tackle these challenges, this paper presents a new semantic proto‐reinforcement learning (SP‐RL) method for dynamic path planning and real‐time obstacle avoidance of an autonomous car that can be adapted to various weather conditions in localization‐deficient environments, while predicting the human intentions of different shapes on road. This approach seeks to improve navigation capability of AV in dynamic and unstructured environments, as well as to address real‐time detection and avoidance response for obstacles more promptly while being able to adapt its decision‐making system based on weather condition by using the semantic graph network (SGN) within segmentation process therefore enhanced version configured with prototype‐based reinforcement learning (PRL). This innovation is new competitive edge compared previous existing approaches. Dynamic SGN is used to segment challenging 3D and free space environments, so that the AV can comprehend highly unintuitive areas like parking lots, construction site conditionals, or off‐road scenarios. At the same time, PRL is used to help real‐time decision‐making so the AV can quickly and precisely respond unexpected obstacles or changing environments. This approach is confirmed to be effective by extensive testing in the CARLA simulation environment, showing substantial improvement of AV navigation capability. This work demonstrates an exciting step towards solving the most fundamental problems faced by autonomous vehicles and could help to ensure that future AV systems are safer, more robust, and adaptable than current ones. It is appliable for urban areas which represent high volumes of pedestrians and vehicles, industrial sites with changing conditions that may be unpredictable at times or the challenging off‐road areas in rural geographies where typical terrains are rough, uneven, rugged yet not well‐structured. The model is robust to diverse weather conditions that make AV operations more reliable and safer. The model was tested on root mean square error (RMSE), computational time, no crash, obstacles avoidance, and success rate obtaining overall 98%.