Preliminary Detection Research Articles

MicroRNA mediated gene regulatory circuits leads to machine learning based preliminary detection of acute myeloid leukemia

Acute Myeloid Leukemia (AML) can be detected based on morphology, cytochemistry, immunological markers, and cytogenetics. MicroRNAs (miRNAs) influence key biological pathways in multiple haematological malignancies including AML. In this work, we have analysed the miRNome and the transcriptome of normal and AML samples and have identified the significant set of miRNA-target mRNA pairs present within AML- Peripheral Blood and AML- Bone Marrow samples from both tissue and cell lines. The miRNA target genes are further filtered based on their functional significance in AML system. These filtered genes constitute the set of selected miRNA target features, which have been finally used for developing machine learning based prediction tool, ‘TbAMLPred’ for preliminary detection of AML.This model implements both unsupervised clustering and supervised classification algorithms that would increase the reliability of prediction. Our results show that the selected miRNA target-based features can separate the control and disease samples linearly. Overall, we put forward ‘TbAMLPred’ for a non-invasive mode of preliminary AML diagnosis in future.Github link for accessing TbAMLPred: https://github.com/zglabDIB/TbAMLPred

Radiation Dose Detection on FY-4B Satellite

The radiation damage effect is relatively serious during spacecraft operation in orbit. To know the real cumulative dose in orbit accurately, a radiation dose detector is carried on the FY-4B satellite. It comprises one electric control unit and three dose detectors, with a total of four payloads. Each dose detector includes five dose-monitoring points corresponding to different shielding thicknesses, which are mainly used for the measurement of the dose depth. Three dose detectors with the same function are installed in the X, Y and Z positions and can detect the total dose in different directions during the operation of the satellite. Each detector has the characteristics of small size, high integration and low power consumption. At present, the FY-4B satellite is in orbit. The detectors have been working normally since they were started up, and good preliminary detection results have been obtained. From the power-up of the detectors to April 2022, the maximum dose has reached 2.7 × 103 rad(Si). We conducted a preliminary analysis of the relationship between total dose and shielding thickness. In addition, the relationship between daily average dose and shielding thickness was further analyzed. These studies have application value for radiation protection design.

Global–local–global context-aware network for salient object detection in optical remote sensing images

For the salient object detection in optical remote sensing images (ORSI-SOD), many existing methods are trapped in a local–global mode, i.e., CNN-based encoder binds with a specific global context-aware module, struggling to deal with the challenging ORSIs with complex background and scale-variant objects. To solve this issue, we explore the synergy of the global-context-aware and local-context-aware modeling and construct a preferable global–local–global context-aware network (GLGCNet). In the GLGCNet, a transformer-based encoder is adopted to extract global representations, combining with local-context-aware features gathered from three saliency-up modules for comprehensive saliency modeling, and an edge assignment module is additionally employed to refine the preliminary detection. Specifically, the saliency-up module involves two components, one for global–local context-aware transfer towards pixel-wise dynamic convolution parameters prediction, the other for dynamically local-context aware modeling. The corresponding position-sensitive filter is aware of its previous global-wise focus, thus enhancing the spatial compactness of salient objects and encouraging the feature upsampling achievement for multi-scale feature combinations. The edge assignment module enhances the robustness of preliminary saliency prediction and assigns the semantic attributes of preliminary saliency cues to the shallow-level edge feature to obtain final complete salient objects in a spatially and semantically global manner. Extensive experiments demonstrate that the proposed GLGCNet surpasses 23 state-of-the-art methods on three popular datasets.

Accurate detection and identification of insects from camera trap images with deep learning

Reported insect declines have dramatically increased the global demand for standardized insect monitoring data. Image-based monitoring can generate such data cost-efficiently and non-invasively. However, extracting ecological data from images is more challenging for insects than for vertebrates because of their small size and great diversity. Deep learning facilitates fast and accurate insect detection and identification, but the lack of training data for coveted deep learning models is a major obstacle for their application. We present a large annotated image dataset of functionally important insect taxa. The primary dataset consists of 29,960 annotated insects representing nine taxa including bees, hoverflies, butterflies and beetles across more than two million images recorded with ten time-lapse cameras mounted over flowers during the summer of 2019. The insect image dataset was extracted using an iterative approach: First, a preliminary detection model identified candidate insects. Second, candidate insects were manually screened by users of an online citizen science platform. Finally, all annotations were quality checked by experts. We used the dataset to train and compare the performance of selected You Only Look Once (YOLO) deep learning algorithms. We show that these models detect and classify small insects in complex scenes with unprecedented accuracy. The best performing YOLOv5 model consistently identifies nine dominant insect species that play important roles in pollination and pest control across Europe. The model reached an average precision of 92.7% and recall of 93.8% in detection and classification across species. Importantly, when presented with uncommon or unclear insects not seen during training, our model detects 80% of individuals and usually interprets them as closely related species. This is a useful property to (1) detect rare insects for which training data are absent, and (2) generate new training data to correctly identify those insects in future. Our camera system, dataset and deep learning framework show promising results in non-destructive monitoring of insects. Furthermore, resulting data are useful to quantify phenology, abundance, and foraging behaviour of flower-visiting insects. Above all, this dataset represents a critical first benchmark for future development and evaluation of deep learning models for insect detection and identification.

Fault diagnosis for rotor based on multi-sensor information and progressive strategies

Fault diagnosis is an effective tool to ensure safe operation of machinery and avoid serious accidents. As most currently used fault diagnosis methods usually employ mapping relationship established by training samples and their labels to achieve classification of testing samples, it is difficult for them to achieve fault diagnosis under the condition of incomplete training sample types. In addition, previous studies usually focus on feature extraction of single-channel vibration signal, which cannot get complete fault feature information. To solve the above problems, a progressive fault diagnosis method is investigated in this paper. First, the preliminary fault detection for the rotor is performed by studying reconstruction error of a sparse auto-encoder. Second, if a fault exists in the rotor, the outlier detection is implemented by the support vector data description method. Finally, if there are no outlier samples, the well -trained support vector machine is used to confirm the type of fault samples and complete the diagnosis. The performance of the proposed method was verified using the data obtained from a rotor laboratory bench. The types of rotor states investigated include normal, contact-rubbing, unbalance and misalignment. The experimental results verify the effectiveness and superiority of the proposed method in reducing the incidents of fault omission and fault misunderstanding.

A Performance Study of CNN Architectures for the Autonomous Detection of COVID-19 Symptoms Using Cough and Breathing

Deep learning (DL) methods have the potential to be used for detecting COVID-19 symptoms. However, the rationale for which DL method to use and which symptoms to detect has not yet been explored. In this paper, we present the first performance study which compares various convolutional neural network (CNN) architectures for the autonomous preliminary COVID-19 detection of cough and/or breathing symptoms. We compare and analyze residual networks (ResNets), visual geometry Groups (VGGs), Alex neural networks (AlexNet), densely connected networks (DenseNet), squeeze neural networks (SqueezeNet), and COVID-19 identification ResNet (CIdeR) architectures to investigate their classification performance. We uniquely train and validate both unimodal and multimodal CNN architectures using the EPFL and Cambridge datasets. Performance comparison across all modes and datasets showed that the VGG19 and DenseNet-201 achieved the highest unimodal and multimodal classification performance. VGG19 and DensNet-201 had high F1 scores (0.94 and 0.92) for unimodal cough classification on the Cambridge dataset, compared to the next highest F1 score for ResNet (0.79), with comparable F1 scores to ResNet for the larger EPFL cough dataset. They also had consistently high accuracy, recall, and precision. For multimodal detection, VGG19 and DenseNet-201 had the highest F1 scores (0.91) compared to the other CNN structures (≤0.90), with VGG19 also having the highest accuracy and recall. Our investigation provides the foundation needed to select the appropriate deep CNN method to utilize for non-contact early COVID-19 detection.

Ultra-low-dose CT lung screening with artificial intelligence iterative reconstruction: evaluation via automatic nodule-detection software

To test the feasibility of ultra-low-dose (ULD) computed tomography (CT) combined with an artificial intelligence iterative reconstruction (AIIR) algorithm for screening pulmonary nodules using computer-assisted diagnosis (CAD). A chest phantom with artificial pulmonary nodules was first scanned using the routine protocol and the ULD protocol (3.28 versus 0.18 mSv) to compare the image quality and to test the acceptability of the ULD CT protocol. Next, 147 lung-screening patients were enrolled prospectively, undergoing an additional ULD CT immediately after their routine CT examination for clinical validation. Images were reconstructed with filtered back-projection (FBP), hybrid iterative reconstruction (HIR), the AIIR, and were imported to the CAD software for preliminary nodule detection. Subjective image quality on the phantom was scored using a five-point scale and compared using the Mann-Whitney U-test. Nodule detection using CAD was evaluated for ULD HIR and AIIR images using the routine dose image as reference. Higher image quality was scored for AIIR than for FBP and HIR at ULD (p<0.001). As reported by CAD, 107 patients were presented with more than five nodules on routine dose images and were chosen to represent the challenging cases at an early stage of pulmonary disease. Among such, the performance of nodule detection by CAD on ULD HIR and AIIR images was 75.2% and 92.2% of the routine dose image, respectively. Combined with AIIR, it was feasible to use an ULD CT protocol with 95% dose reduction for CAD-based screening of pulmonary nodules.

Machine-learning-based simultaneous detection and ranging of impulsive baleen whale vocalizations using a single hydrophone.

The low-frequency impulsive gunshot vocalizations of baleen whales exhibit dispersive propagation in shallow-water channels which is well-modeled by normal mode theory. Typically, underwater acoustic source range estimation requires multiple time-synchronized hydrophone arrays which can be difficult and expensive to achieve. However, single-hydrophone modal dispersion has been used to range baleen whale vocalizations and estimate shallow-water geoacoustic properties. Although convenient when compared to sensor arrays, these algorithms require preliminary signal detection and human labor to estimate the modal dispersion. In this paper, we apply a temporal convolutional network (TCN) to spectrograms from single-hydrophone acoustic data for simultaneous gunshot detection and ranging. The TCN learns ranging and detection jointly using gunshots simulated across multiple environments and ranges along with experimental noise. The synthetic data are informed by only the water column depth, sound speed, and density of the experimental environment, while other parameters span empirically observed bounds. The method is experimentally verified on North Pacific right whale gunshot data collected in the Bering Sea. To do so, 50 dispersive gunshots were manually ranged using the state-of-the-art time-warping inversion method. The TCN detected these gunshots among 50 noise-only examples with high precision and estimated ranges which closely matched those of the physics-based approach.

MODELLING OF GROUP DECISION SUPPORT SYSTEMS FOR FLOOD ALERT WITH NAKAYASU SYNTHETIC UNIT HYDROGRAPH IN GADANG WATERSHED

Natural disasters still occur regularly and continuously in Indonesia and in the world, such as floods, earthquakes, tsunamis, and landslides. The impact of natural disasters such as floods can be reduced through flood hazard mitigation activities. Flood hazard mitigation can be done by knowing early rainfall in history and today and river water levels river flow to a region upstream of the history and current. This study aims to make a group decision support system modeling for early detection of candidate flooding caused by the condition of the watershed, in this case is Gadang Watershed. The system is designed as a tool to detect candidate field hydrometric flood early. Modelling Group Decision Support System (GDSS) was developed based on the analysis of flood design represented in a Nakayasu Synthetic Unit Hydrograph. A group of Decision Support Systems is a type of computer-based interactive system that is designed for a group of decision-making. The users of the decision support system are a group that consists of some people. Hydrograph is in accordance with the conditions of the watershed, especially in tropical Indonesia. The results of the design flood serve as a reference to the operational unit, the data management unit, and the planning unit of the institution of the watershed maintenance such as Perum Jasa Tirta I. A suitability test is intended to determine whether the distribution of the selected distributions may be used or not, in a series of data available. Analysis of the suitability test using the Chi Square distribution. From the results of the distribution test that the distribution can be accepted and the system can support for analysing flood hazards as preliminary information early detection of flooding. Keywords: Group Decision Support System, Flood Hazard, Nakayasu Synthetic Unit Hydrograph, Water Level DOI： https://doi.org/10.35741/issn.0258-2724.58.1.13

Possible Evidence for Lorentz Invariance Violation in Gamma-Ray Burst 221009A

The preliminary detections of the gamma-ray burst 221009A up to 18 TeV by LHAASO and up to 251 TeV by Carpet 2 have been reported through Astronomer’s Telegrams and Gamma-ray Coordination Network circulars. Since this burst is at redshift z = 0.1505, these photons may at first seem to have a low probability to avoid pair production off of background radiation fields and survive to reach detectors on Earth. By extrapolating the reported 0.1–1.0 GeV Fermi Large Area Telescope spectrum from this burst to higher energies and using this to limit the intrinsic spectrum of the burst, we show that the survival of the 18 TeV photon detected by LHAASO is not unlikely with many recent extragalactic background light models, although the detection of a 251 TeV event is still very unlikely. This can be resolved if Lorentz invariance is violated at an energy scale E QG ≲ 49E Planck in the linear (n = 1) case, and E QG ≲ 10−6 E Planck in the quadratic (n = 2) case (95% confidence limits), where E Planck is the Planck energy. This could potentially be the first evidence for subluminal Lorentz invariance violation.

Procena prakse medicinskih sestara u skriningu poremećaja zdravlja

Introduction: Screening represents the preliminary detection of persons with unrecognized forms of health disorders with the help of easily and quickly applicable procedures with the aim of early detection. Although organized screening is carried out in our country, which is a mass invitation of the target population for examination, breast cancer has been the leading location in the incidence and death of malignant tumors in women in Serbia for years. The aim of the work was to determine the practice of nurses in the screening of leading health disorders. Method and subjects: The research was designed as a cross-sectional study that was carried out in the Obstetrics and Gynecology Clinic "Narodni Front" in Belgrade. The research included 59 nurses. As a monitoring instrument, a questionnaire for nurses specially designed for this research was used. Research result: Breast self-examination and clinical breast examination were performed by only slightly more than 1/3 of nurses who participated in the research, while mammography was performed by 70% of nurses who are older than 50 years. Almost all nurses performed a pap smear. The largest percentage of nurses (57.6%) measures blood pressure only when they do not feel well, and even 15.3% never measure it. As many as 74.6% of nurses never performed an examination of moles and skin. Conclusion: Bearing in mind that almost all nurses employed in the Gynecology and Obstetrics Clinic regularly go for Pap smears, while a small percentage go to other screenings for health disorders or ignore them, indicates the necessity of additional education about the importance of screening

Design of Hexagonal Ring Wearable Textile Antenna using Polyester for Early Bone Health Detection

In this research manuscript, the author proposes an innovative solution for monitoring and preliminary detection of bone health with the use of a newly designed Hexagonal Ring Wearable Textile Antenna (HRWTA) using polyester material. The HRWTA is designed and fabricated using polyester conductive electro-textile as radiating fabric and polyester fabric as substrate having dielectric constant of 1.44 with loss tangent of 0.01. The motivation behind this work stems from the increasing number of osteoporosis cases around the world has led to a greater need for new, non-invasive ways to keep track of bone health. Leveraging advancements in microwave technology and antenna design, this study introduces a novel approach by drawing parallels between hexagonal ring and annular ring microstrip antennas, resulting in a precise empirical formula for resonance frequency calculation [9]. Rigorous validation through simulations and experiments showcases the antenna's accuracy in assessing bone health parameters. HRWTA, born from this formula, offers a discreet and affordable means for continuous bone health monitoring, holding significant promise for early intervention and improved healthcare outcomes in the face of the growing osteoporosis challenge. The return loss bandwidth of HRWTA is 350 MHz (3.39 GHz-3.74 GHz, 10%). Also, it has a peak gain of 2.5 dB at 3.5 GHz. Hence, HRWTA is suitable for wireless body area network (WBAN) as it has good radiation characteristics.

Preliminary study of colorimetric detection for potential medicinal compounds of Kaempferia parviflorausing phytochemical determination

Medicinal plants are used in traditional medicine to treat various diseases. They have been utilized to prevent and cure numerous diseases, the treatment of which is established in conventional knowledge practices. K. parviflora is a perennial plant with numerous medicinal properties. This study seeks to conduct a preliminary investigation of traditional medical treatment using K. parviflora, which has been employed for treating hypertension and promoting longevity through overall good health. In its results, this study shows that K. parviflora contains potential medicinal compounds such as flavonoids, phenolics, tannins, and terpenoids. The preliminary colorimetric detection of the K. parviflora extracts provides high confidence in the positive assessment of traditional medical practice. The present investigation suggests that using colorimetric detection for initial screening is acceptable. However, it is strongly recommended that chromatography be used in chemical concentration analysis for further study.

ELECTROCHEMICAL BIOSENSORS FOR CONT­ROL OF LEAD CONTENT IN THE ENVIRONMENT. A REVIEW

The review presents different types of biosensors and their principles of operation that are currently used to detect heavy metals and lead. Biosensors are considered highly sensitive, specific, accurate, inexpensive and effective tools for the preliminary detection of one or more metals in sources of mixed pollution, especially in wastewater. The use of functional nanomaterials based on metal-organic frameworks and layered hydroxides allowed to miniaturize the design of biosensors and significantly improve their applicability for on-site analysis of target samples, which reduces the probability of any changes in the samples during transport to the laboratory. Also, these materials have long-term stability, improve the signal and response speed of electrochemical biosensors, and also increase their sensitivity and selectivity. An overview of the methods of manufacturing the active component of multilayer electrochemical sensors was conducted. The main methods of obtaining stable and sensitive to lead ions electrochemical systems are noted.Sensors and biosensors are powerful tools for accurate qualitative and quantitative analysis of a specific analyte and integration of biotechnology, microelectronics, and nanotechnology to fabricate miniaturized devices without loss of sensitivity, specificity, and cont­rol accuracy. The characteristic properties of biomolecule carriers significantly affect the sensitivity and selectivity of the device. The impact of carriers based on metal-organic frameworks and layered hydroxides on increasing the efficiency of modern lead biosensors due to the implementation of the enzyme inhibition mechanism was considered, and the me­thods of manufacturing the active component of multilayer electrochemical sensors were also reviewed. The perspective of using the coprecipitation method and the ion exchange method to obtain stable and sensitive lead ion electrochemical systems was noted. Thus, electrochemical biosensors can be considered as one of the most widely developed biosensors for the detection of lead ions, in which the presence of direct electron transfer from the recognition center to the electrode reduces the probability of unnecessary interference, which significantly increases their sensitivity and selectivity and enables the development of devices for in-mode monitoring real-time.

A Preliminary Fault Detection Methodology for Abnormal Distillation Column Operations Using Acoustic Signals

The fault detection of the chemical equipment operation process is an effective means to ensure safe production. In this study, an acoustic signal processing technique and a k-nearest neighbor (k-NN) classification algorithm were combined to identify the running states of the distillation columns. This method can accurately identify various fluid flow states in distillation columns, including normal and flooding states. First, the acoustic signals were collected under normal and abnormal states in an experimental distillation column. Then, the method of dual-domain feature extraction was used to extract the features such as the energy ratio and linear prediction coefficient (LPC). Moreover, the extracted feature parameters were analyzed and compared in a general way. Finally, the k-NN model was used to classify the acoustic signals. The results show that this method had high identification accuracy and provided an important reference for further research.

An Internal Waves Data Set From Sentinel‐1 Synthetic Aperture Radar Imagery and Preliminary Detection

AbstractInternal waves (IWs) are a widely occurring phenomenon in the global oceans. They have significant impacts on marine environments through their propagation mechanisms. In this study, we collect 390 satellite images with 775 labels from Sentinel‐1 Synthetic Aperture Radar (SAR) from 2014 to 2021 to construct a data set containing IW packets in Andaman Sea, South China Sea, Sulu Sea, and Celebes Sea, respectively. All the SAR images acquired are pre‐processed to provide clear IW packets for better visualization. To better detect IWs in global oceans automatically, a machine‐learning based model is proposed to focus on different channels and the spatial information. The precision, recall, and mean average precision of our improved model applied on the IW data set is up to 98.7%, 96.9%, and 98.9%, respectively. Various cases of IWs images are analyzed to illustrate detection quality in different stripes, scales, and propagation directions of IWs. The experimental results indicate that our data set is helpful to better detect IWs, and proposed network can accurately detect IWs in SAR images under various conditions.

Object defect detection based on data fusion of a 3D point cloud and 2D image

In the process of defect detection, there can be interference factors such as poor image quality and missing point cloud data as a result of the complexity of the acquisition environment. Certain limitations can be found relying solely on point cloud data processing or image feature detection. Therefore, this paper tries a more intuitive and effective exploration. Firstly, an algorithm named hole boundary points detection of point cloud, based on multi-scale principal component analysis, is proposed, which can achieve the preliminary detection of hole boundary points while calculating the normal vector of each point in the point cloud. Then the boundary contour of each hole is constructed by a polygon growth algorithm. Finally, we use the complementary information of the 3D point cloud and 2D image to explore the origin of holes and realize the ‘true’ and ‘false’ classification of holes. The experimental results show that our algorithm can successfully detect point cloud holes and can also distinguish them from object defects, providing data support for subsequent hole filling and defect measurement.

Reduction of Feature Extraction for COVID-19 CXR using Depthwise Separable Convolution Network

A Convolutional Neural Network (CNN) classifier is generally utilized to classify an image tensor according to the mapped labels. The simplification of the classifier causes CNN to be often used to classify images, especially in the biomedical field. Thus, CNN is widely used to classify computer tomography (CT) and chest X-ray (CXR) images against the mapped labels. Several transfer learning models were implemented to classify CXR images for preliminary detection of COVID-19 infection, e.g., ResNet, Inception, Xception, etc. However, a transfer learning model has a maximum and minimum input resolution. Thus, the computational cost tends to be huge and unable to be optimized. Therefore, A custom CNN model can be a solution to reduce computational costs by configuring the feature extraction layers. This study proposed an efficient reduction of feature extraction for COVID-19 CXR namely Depthwise Separable Convolution Network. Furthermore, numerous strategies were adopted to lower the computational cost while retaining accuracy, including customizing the Batch Normalization (BN) layer and replacing the convolution layer with a separable convolution layer. The proposed model successfully reduced the feature extraction represented by the decreases in trainable parameters from 28.640 trainable parameters to 4.640 trainable parameters. The depthwise separable convolution effectively retains the performance accuracy 72.96%, loss 12.43%, recall 74.67%, precision 77.67%, and F1-score 75.33%. The CXR augmentation is also successfully increase the performance accuracy 74.55%, loss 11.37%, recall 77.67%, precision 79.56%, and F1-score 78.33%.

Isolation and Production of Human Monoclonal Antibody Proteins against a Toxocara canis Excretory-Secretory Recombinant Antigen.

Toxocariasis is a widespread zoonotic parasitic disease with a significant socioeconomic impact, particularly on underprivileged communities. Limitations of existing diagnostic tools and vague presenting symptoms may lead to misdiagnosis, thus underestimating the actual global impact of the disease. The present study describes the isolation and production of novel recombinant monoclonal antibodies against Toxocara canis recombinant TES-26 antigen (rTES-26) utilizing a human helminth scFv phage display library. The isolated antibody clones were characterized based on their gene sequences and binding characteristics. Three clones representing unique gene families (clone 48: IgHV3-LV1; clone 49: IgHV3-LV3; clone 50: IgHV6-LV3) were isolated, but only clones 48 and 49 showed successful insertion of the full-length scFv antibody sequence after sub-cloning. Both clones produced antibody proteins of good solubility and satisfactory yield and purity. Binding assays via Western blot and ELISA using rTES-26 and Toxocara&amp;nbsp;canis native protein showed that both monoclonal antibodies were highly specific and sensitive to the target antigen. A preliminary antigen detection ELISA showed the diagnostic potential of the monoclonal antibody proteins. The proteins can also be useful in studying host-parasite interactions and therapeutic applications.

Automatic detection of fault-controlled rivers using spatial pattern matching

The river system of a region records its tectonic evolution. This study expects to infer some potential faults by effectively quantifying river morphology and identifying rivers with specific morphological and structural characteristics. Thus, this study aims to develop a novel method for automatically detecting fault-controlled rivers (FCRs) from drainage maps using spatial pattern matching and to support the scientific inference of potential faults. The method involves (1) constructing a scene model for the entire drainage basin in the study area based on the attributed relational graph (ARG) model; (2) defining spatial patterns for four types of FCRs using the ARG model, including straight river reaches, right-angle river reaches, barb rivers, and contra-aperture rivers, and storing all river patterns in a spatial pattern library; and (3) detecting the four types of FCRs with a spatial pattern-matching algorithm and the FCR pattern library. Case studies demonstrated the basic effectiveness of this method for detecting FCRs in the study areas of Bomi County (Parong Tsangpo River Valley and Yigong Zangbo River Valley) and southeast of the Qinghai Tibet Plateau. The goals of this study are to quantify river shape better, support the preliminary detection of potential faults, and provide a useful reference for structure-based spatial queries in GIS. Additionally, more river pattern types with specific morphological and structural characteristics can be automatically detected through dynamic maintenance of the spatial pattern library.