3D CNN Research Articles

ATR-FTIR spectroscopy and machine/deep learning models for detecting adulteration in coconut water with sugars, sugar alcohols, and artificial sweeteners

Packaged coconut water offers various options, from pure to those with added sugars and other additives. While the purity of coconut water is esteemed for its health benefits, its popularity also exposes it to potential adulteration and misrepresentation. To address this concern, our study combines Fourier transform infrared spectroscopy (FTIR) and machine learning techniques to detect potential adulterants in coconut water through classification models. The dataset comprises infrared spectra from coconut water samples spiked with 15 different types of potential sugar substitutes, including: sugars, artificial sweeteners, and sugar alcohols. The interaction of infrared light with molecular bonds generates unique molecular fingerprints, forming the basis of our analysis. Departing from previous research predominantly reliant on linear-based chemometrics for adulterant detection, our study explored linear, non-linear, and combined feature extraction models. By developing an interactive application utilizing principal component analysis (PCA) and t-distributed stochastic neighbor embedding (t-SNE), non-targeted sugar adulterant detection was streamlined through enhanced visualization and pattern recognition. Targeted analysis using ensemble learning random forest (RF) and deep learning 1-dimensional convolutional neural network (1D CNN) achieved higher classification accuracies (95% and 96%, respectively) compared to sparse partial least squares discriminant analysis (sPLS-DA) at 77% and support vector machine (SVM) at 88% on the same dataset. The CNN’s demonstrated classification accuracy is complemented by exceptional efficiency through its ability to train and test on raw data.

P-261 A comparative analysis of artificial intelligence models for blastulation in In vitro fertilization: single-frame vs. full-frame approach

Abstract Study question How does the performance of an blastulation prediction model using full-frame data over 3 days compare to a single-frame model using day 3 data? Summary answer The single-frame model, based on a day 3 embryo image, demonstrated comparable predictive performance to the full-frame model What is known already Pregnancy rates following blastocyst transfer have been reported to be higher than those after cleavage transfer. However, not all cleavage embryos reach the blastocyst stage, leading to the exploration of predictive models using embryo images and artificial intelligence. Clinical practice often involves the decision to culture embryos to the blastocyst stage on day 3 based on embryo quality assessments. Recently, there has been interest in using morphokinetics data for predicting blastulation and pregnancy outcomes. While the importance of morphokinetics in IVF outcomes is acknowledged, the specific time frames and features contributing significantly to accurate predictions remain unclear. Study design, size, duration This retrospective study analyzed a dataset of 15,615 timelapse images from 906 patients at a single IVF center. The Single-Frame Model used a single image collected at 66.7 hours post-ICSI, and the Full-Frame Model used 145 frames collected from fertilization to 66.7 hours post-ICSI. Blastulation criteria included reaching a blastocyst on day 5, deemed suitable for transfer or freezing by an experienced embryologist. Participants/materials, setting, methods We trained the data using ResNet for the one-frame model and 3D CNN for the full-frame model. The ResNet model used pre-trained weights, while the 3D CNN model was built from scratch with no pre-trained weights. The models were evaluated using the AUROC, accuracy, and F1 score metrics. The statistical significance of the AUC performance differences was assessed using DeLong’s test. Main results and the role of chance Our study revealed similar AUC performance between the Single-Frame and Full-Frame Models for day 3 embryos. The Single-Frame Model exhibited an AUROC of 0.76, accuracy of 0.71, and an F1 score of 0.75, while the Full-Frame Model demonstrated comparable performance with an AUROC of 0.75, accuracy of 0.70, and an F1 score of 0.72. DeLong’s test was employed to assess the statistical significance of the difference in AUROC, yielding a non-significant p-value of 0.4884. This study underscores that the Single-Frame Model provides similar predictive performance for blastulation compared to the Full-Frame Model. Limitations, reasons for caution Our analysis was limited to images taken at 66.7 hours post-ICSI to mirror clinical practice. Further investigations at different time points are necessary to determine the optimal time for blastulation prediction. Additional analysis of the Day 1 and Day 2 single frames may offer further insights. Wider implications of the findings Accurate prediction of blastulation on day 3 is pivotal for embryo survival and IVF success. Our study challenges the assumption that more data improves AI models, highlighting the importance of day 3 observations. Further research is warranted to identify key time points and features for better predictive accuracy. Trial registration number not applicable

Footbridge damage detection using smartphone-recorded responses of micromobility and convolutional neural networks

This paper presents a footbridge damage detection and classification framework using smartphone-recorded responses of micromobility and deep learning techniques. Time–frequency representations (TFRs) of scooter vibrations are employed to detect and classify footbridge damage severities using a Two-Dimensional Convolutional Neural Network (2D CNN). A One-Dimensional (1D) CNN using scooter frequency spectra was also investigated for comparison. The effectiveness of the method was verified using a numerical model of scooter-footbridge interactions and field tests on a real footbridge. The results indicated that both CNNs were sensitive to footbridge frequency alterations caused by damage in the numerical simulations. Nevertheless, the performance of the 1D CNN experienced a substantial decline in field tests involving stochastic influencing factors, whereas the accuracy of damage classification using the 2D CNN remained high. Finally, reasonable interpretations for the superior performance of the 2D CNN are provided using Shapley Additive Explanations (SHAP) values.

Enhancing Spatial Resolution in Tandem Mass Spectrometry Ion/Ion Reaction Imaging Experiments through Image Fusion.

We have recently developed a charge inversion ion/ion reaction to selectively derivatize phosphatidylserine lipids via gas-phase Schiff base formation. This tandem mass spectrometry (MS/MS) workflow enables the separation and detection of isobaric lipids in imaging mass spectrometry, but the images acquired using this workflow are limited to relatively poor spatial resolutions due to the current time and limit of detection requirements for these ion/ion reaction imaging mass spectrometry experiments. This trade-off between chemical specificity and spatial resolution can be overcome by using computational image fusion, which combines complementary information from multiple images. Herein, we demonstrate a proof-of-concept workflow that fuses a low spatial resolution (i.e., 125 μm) ion/ion reaction product ion image with higher spatial resolution (i.e., 25 μm) ion images from a full scan experiment performed using the same tissue section, which results in a predicted ion/ion reaction product ion image with a 5-fold improvement in spatial resolution. Linear regression, random forest regression, and two-dimensional convolutional neural network (2-D CNN) predictive models were tested for this workflow. Linear regression and 2D CNN models proved optimal for predicted ion/ion images of PS 40:6 and SHexCer d38:1, respectively.

Bidirectional Hybrid LSTM Based Recurrent Neural Network for Multi-View Stereo.

Recently, deep learning based multi-view stereo (MVS) networks have demonstrated their excellent performance on various benchmarks. In this paper, we present an effective and efficient recurrent neural network (RNN) for accurate and complete dense point cloud reconstruction. Instead of regularizing the cost volume via conventional 3D CNN or unidirectional RNN like previous attempts, we adopt a bidirectional hybrid Long Short-Term Memory (LSTM) based structure for cost volume regularization. The proposed bidirectional recurrent regularization is able to perceive full-space context information comparable to 3D CNNs while saving runtime memory. For post-processing, we introduce a visibility based approach for depth map refinement to obtain more accurate dense point clouds. Extensive experiments on DTU, Tanks and Temples and ETH3D datasets demonstrate that our method outperforms previous state-of-the-art MVS methods and exhibits high memory efficiency at runtime.

Fdstnet & TransCAM: A 1D CNN temperature interpretation model for temperature indication paint and model interpretability method

The color of temperature indicating paint (TIP) is commonly used in temperature measurement testing of aircraft engine hot end components. In this paper, an end-to-end convolutional neural network utilizing DSTNet, is proposed for accurate temperature interpretation of TIP. Furthermore, the DSTNet is optimized by fusion of reflectance spectrum and sub-band statistical features, resulting in the creation of FDSTNet. The FDSTNet achieves highly accurate temperature interpretation. When the temperature error is 0℃, the interpretation accuracy on KN3A, KN6 and KN8 samples is 98 %, 97 % and 94 %, respectively. When the temperature error is ±10℃, the accuracy on the engine blade is 88 %. In addition, a 1D convolutional neural network interpretability method based on TransCAM, is proposed. This approach analyzes the process of learning the reflectance spectrum of DSTNet, and localizes the characteristic wavelength by visualizing the class activation mapping curves of each convolutional layer of DSTNet.

Early gesture detection in untrimmed streams: A controlled CTC approach for reliable decision-making

This paper focuses on the problem of online action detection for interactive systems, with a special emphasis on earliness. Online Action Detection (OAD) refers to the challenging task of recognizing gestures in untrimmed, streaming videos where the actions occur in unpredictable orders and durations. To address these challenges, we present a skeleton-based system for OAD incorporating a decision mechanism to accurately detect ongoing gestures. This allows us to provide instance-level output, achieving a high level of stream understanding. This mechanism relies on a novel Connectionist Temporal Classification (CTC) loss design that restricts the path possibilities according to the action boundaries. We also present a mechanism to tune the trade-off between accuracy and earliness according to the needs of the interactive system using a weighted label prior. This system includes a 3D CNN network, referred to as DOLT-C3D, exploiting the spatial–temporal information provided by the euclidean skeleton representation. We extensively evaluate our approach on eight publicly available datasets, demonstrating its superior performance compared to state-of-the-art methods in terms of both accuracy and earliness. We also successfully applied our approach to early 2D gestures detection. Furthermore, our system shows real-time performance, making it a suitable choice for interactive systems.

Application of 3D fluorescence spectroscopy and a convolutional neural network for oil emulsion species identification

Increased pollution from oil emulsions may cause serious ecological damage. The development of a fast and effective emulsified oil species identification method plays a crucial role in dealing with oil spills on the sea surface. Because of this, this paper proposes an emulsified oil species category identification method based on 3D fluorescence spectroscopy and CNN. First, the 3D fluorescence spectra of emulsified oil were measured by an FLS1000 steady-state fluorescence spectrometer, and their fluorescence characteristics were analyzed in depth. Second, the 3D fluorescence spectral data of emulsified oil was extended using a conditional variational autoencoder (CVAE), and the spectral features were extracted using a pre-trained ResNet50. Finally, the spectral features extracted by ResNet50 were used as inputs to the hunter-prey optimized support vector machine (HPO-SVM), and the results show that the recognition accuracy of this method is 97 %, which is better than other classification models.

Deep learning based 3D multimodal CNN for brain tumor segmentation and detection

Deep learning based 3D multimodal CNN for brain tumor segmentation and detection

FF3D: A Rapid and Accurate 3D Fruit Detector for Robotic Harvesting.

This study presents the Fast Fruit 3D Detector (FF3D), a novel framework that contains a 3D neural network for fruit detection and an anisotropic Gaussian-based next-best view estimator. The proposed one-stage 3D detector, which utilizes an end-to-end 3D detection network, shows superior accuracy and robustness compared to traditional 2D methods. The core of the FF3D is a 3D object detection network based on a 3D convolutional neural network (3D CNN) followed by an anisotropic Gaussian-based next-best view estimation module. The innovative architecture combines point cloud feature extraction and object detection tasks, achieving accurate real-time fruit localization. The model is trained on a large-scale 3D fruit dataset and contains data collected from an apple orchard. Additionally, the proposed next-best view estimator improves accuracy and lowers the collision risk for grasping. Thorough assessments on the test set and in a simulated environment validate the efficacy of our FF3D. The experimental results show an AP of 76.3%, an AR of 92.3%, and an average Euclidean distance error of less than 6.2 mm, highlighting the framework's potential to overcome challenges in orchard environments.

Rapid identification and quantitative analysis of malachite green in fish via SERS and 1D convolutional neural network

Rapid and quantitative detection of malachite green (MG) in aquaculture products is very important for safety assurance in food supply. Here, we develop a point-of-care testing (POCT) platform that combines a flexible and transparent surface-enhanced Raman scattering (SERS) substrate with deep learning network for achieving rapid and quantitative detection of MG in fish. The flexible and transparent SERS substrate was prepared by depositing silver (Ag) film on the polydimethylsiloxane (PDMS) film using laser molecular beam epitaxy (LMBE) technique. The wrinkled Ag NPs@PDMS film exhibits high SERS activity, excellent reproducibility and good mechanical stability. Additionally, the fast in situ detection of MG residues onfishscales was achieved by using the wrinkled Ag NPs/PDMS film and a portable Raman spectrometer, with a minimum detectable concentration of 10-6 M. Subsequently, a one-dimensional convolutional neural network (1D CNN) model was constructed for rapid quantification of MG concentration. The results demonstrated that the 1D CNN quantitative analysis model possessed superior predictive performance, with a coefficient of determination (R2) of 0.9947 and a mean squared error (MSE) of 0.0104. The proposed POCT platform, integrating a transparent flexible SERS substrate, a portable Raman spectrometer and a 1D CNN model, provides an efficient strategy for rapid identification and quantitative analysis of MG in fish.

Lightweight Violence Detection Model Based on 2D CNN with Bi-Directional Motion Attention

With the widespread deployment of surveillance cameras, automatic violence detection has attracted extensive attention from industry and academia. Though researchers have made great progress in video-based violence detection, it is still a challenging task to realize accurate violence detection in real time, especially with limited computing resources. In this paper, we propose a lightweight 2D CNN-based violence detection scheme, which takes advantage of frame-grouping to reduce data redundancy greatly and, meanwhile, enable short-term temporal modeling. In particular, a lightweight 2D CNN, named improved EfficientNet-B0, is constructed by integrating our proposed bi-directional long-term motion attention (Bi-LTMA) module and a temporal shift module (TSM) into the original EfficientNet-B0. The Bi-LTMA takes both spatial and channel dimensions into consideration and captures motion features in both forward and backward directions. The TSM is adopted to realize temporal feature interaction. Moreover, an auxiliary classifier is designed and employed to improve the classification capability and generalization performance of the proposed model. Experiment results demonstrate that the computational cost of the proposed model is 1.21 GFLOPS. Moreover, the proposed scheme achieves accuracies of 100%, 98.5%, 91.67%, and 90.25% on the Movie Fight dataset, the Hockey Fight dataset, the Surveillance Camera dataset, and the RWF-2000 dataset, respectively.

Leveraging 3D convolutional neural network and 3D visible-near-infrared multimodal imaging for enhanced contactless oximetry.

Monitoring oxygen saturation ( ) is important in healthcare, especially for diagnosing and managing pulmonary diseases. Non-contact approaches broaden the potential applications of measurement by better hygiene, comfort, and capability for long-term monitoring. However, existing studies often encounter challenges such as lower signal-to-noise ratios and stringent environmental conditions. We aim to develop and validate a contactless measurement approach using 3D convolutional neural networks (3D CNN) and 3D visible-near-infrared (VIS-NIR) multimodal imaging, to offer a convenient, accurate, and robust alternative for monitoring. We propose an approach that utilizes a 3D VIS-NIR multimodal camera system to capture facial videos, in which is estimated through 3D CNN by simultaneously extracting spatial and temporal features. Our approach includes registration of multimodal images, tracking of the 3D region of interest, spatial and temporal preprocessing, and 3D CNN-based feature extraction and regression. In a breath-holding experiment involving 23 healthy participants, we obtained multimodal video data with reference values ranging from 80% to 99% measured by pulse oximeter on the fingertip. The approach achieved a mean absolute error (MAE) of 2.31% and a Pearson correlation coefficient of 0.64 in the experiment, demonstrating good agreement with traditional pulse oximetry. The discrepancy of estimated values was within 3% of the reference for of all 1-s time points. Besides, in clinical trials involving patients with sleep apnea syndrome, our approach demonstrated robust performance, with an MAE of less than 2% in estimations compared to gold-standard polysomnography. The proposed approach offers a promising alternative for non-contact oxygen saturation measurement with good sensitivity to desaturation, showing potential for applications in clinical settings.

ECG Signal Denoising Using 1D Convolutional Neural Network

Electrocardiogram (ECG) signals are crucial for monitoring cardiac activity and diagnosing various cardiovascular conditions. However, these signals are often contaminated by different types of noise, such as baseline wander, muscle artifacts, and power line interference, which can obscure critical information and hinder accurate diagnosis. This study used a 1-Dimensional Convolutional Neural Network (1D CNN) architecture with seven convolutional layers for denoising ECG signals. The model utilizes a fully convolutional autoencoder approach, comprising an encoder that transforms noisy input signals into compact feature representations and a decoder that reconstructs the cleaned signals. The proposed architecture was tested using the MIT-BIH Noise Stress Test Database, which includes ECG recordings with simulated noise conditions. Performance evaluation metrics such as Mean Squared Error (MSE), Signal-to-Noise Ratio (SNR), and Mean Absolute Deviation (MAD) were used to assess the model's effectiveness. Results showed a low MSE of 0.034, a high SNR of 15.8 dB, and a MAD of 0.754, indicating significant noise reduction and high-quality signal reconstruction. These findings demonstrate that the 1D CNN architecture effectively reduces various types of noise in ECG signals, thereby enhancing signal quality and facilitating more accurate analysis and diagnosis. The model's ability to maintain the integrity of crucial ECG features while removing noise suggests its potential utility in clinical applications for improving cardiovascular disease diagnosis

Dual-stream spectral-spatial convolutional neural network for hyperspectral image classification and optimal band selection

Along with the high spectral rich information it provides, one of the difficulties in processing a hyperspectral image is the need for expert knowledge and high-spec hardware to process very high-dimensional data. 3D convolutional neural network(3D CNN), which uses spectral and spatial features together, enables a powerful solution for HSI classification. This study proposes an efficient dual-stream 3D CNN for accurate HSI classification.The proposed method offers effective classification using spectral-spatial features without relying on pre-processing or post-processing. A comparative study of how CNN classification performance is affected by hyperspectral band selection based on deep reinforcement learning (DRL) is presented. Using the most relevant bands in the hyperspectral image is decisive in deep CNN networks without losing information and accuracy. The proposed method was compared with 3D CNN, 3D + 1D CNN, Multiscale 3D deep convolutional neural network (M3D-DCNN), and InceptionV3 algorithms using Indian Pines (IP), Salinas, Pavia Center (PaviaC), Houston 2013 and QUH-Tangdaowan datasets. It achieved 92.43 % overall accuracy (OA) in IP, 95.06 % OA in Salinas dataset, 99.00 % OA in PaviaC dataset, 91.25 % OA in Houston 2013 and 94.87 % OA in QUH-Tangdaowan. Codes are released at: https://github.com/lapistlazuli/DS-3DCNN.

A novel approach for estimating initial sound level for speech reception threshold test.

The speech reception threshold (SRT), synonymous with the speech recognition threshold, denotes the minimum hearing level required for an individual to discern 50% of presented speech material. This threshold is measured independently in each ear with a repetitive up-down adjustment of stimulus level starting from the initial SRT value derived from pure tone thresholds (PTTs), measured via pure-tone audiometry (PTA). However, repetitive adjustments in the test contributes to increased fatigue for both patients and audiologists, compromising the reliability of the hearing tests. Determining the first (initial) sound level closer to the finally determined SRT value, is important to reduce the number of repetitions. The existing method to determine the initial sound level is to average the PTTs called pure tone average (PTAv). We propose a novel method using a machine learning approach to estimate a more optimal initial sound level for the SRT test. Specifically, a convolutional neural network with 1-dimensional filters (1D CNN) was implemented to predict a superior initial level than the conventional methods. Our approach produced a reduction of 37.92% in the difference between the initial stimulus level and the final SRT value. This outcome substantiates that our approach can reduce the repetitions for finding the final SRT, and, as the result, the hearing test time can be reduced.

Point Cloud Quality Assessment Using a One-Dimensional Model Based on the Convolutional Neural Network.

Recent advancements in 3D modeling have revolutionized various fields, including virtual reality, computer-aided diagnosis, and architectural design, emphasizing the importance of accurate quality assessment for 3D point clouds. As these models undergo operations such as simplification and compression, introducing distortions can significantly impact their visual quality. There is a growing need for reliable and efficient objective quality evaluation methods to address this challenge. In this context, this paper introduces a novel methodology to assess the quality of 3D point clouds using a deep learning-based no-reference (NR) method. First, it extracts geometric and perceptual attributes from distorted point clouds and represent them as a set of 1D vectors. Then, transfer learning is applied to obtain high-level features using a 1D convolutional neural network (1D CNN) adapted from 2D CNN models through weight conversion from ImageNet. Finally, quality scores are predicted through regression utilizing fully connected layers. The effectiveness of the proposed approach is evaluated across diverse datasets, including the Colored Point Cloud Quality Assessment Database (SJTU_PCQA), the Waterloo Point Cloud Assessment Database (WPC), and the Colored Point Cloud Quality Assessment Database featured at ICIP2020. The outcomes reveal superior performance compared to several competing methodologies, as evidenced by enhanced correlation with average opinion scores.

Machine learning model with output correction: Towards reliable bradycardia detection in neonates

Bradycardia is a commonly occurring condition in premature infants, often causing serious consequences and cardiovascular complications. Reliable and accurate detection of bradycardia events is pivotal for timely intervention and effective treatment. Excessive false alarms pose a critical problem in bradycardia event detection, eroding trust in machine learning (ML)-based clinical decision support tools designed for such detection. This could result in disregarding the algorithm’s accurate recommendations and disrupting workflows, potentially compromising the quality of patient care. This article introduces an ML-based approach incorporating an output correction element, designed to minimise false alarms. The approach has been applied to bradycardia detection in preterm infants. We applied five ML-based autoencoder techniques, using recurrent neural network (RNN), long-short-term memory (LSTM), gated recurrent unit (GRU), 1D convolutional neural network (1D CNN), and a combination of 1D CNN and LSTM. The analysis is performed on ∼440 hours of real-time preterm infant data. The proposed approach achieved 0.978, 0.73, 0.992, 0.671 and 0.007 in AUC-ROC, AUC-PRC, recall, F1 score, and false positive rate (FPR) respectively and a false alarms reduction of 36% when compared with methods without the correction approach. This study underscores the imperative of cultivating solutions that alleviate alarm fatigue and encourage active engagement among healthcare professionals.

Zero-shot knowledge transfer for seismic damage diagnosis through multi-channel 1D CNN integrated with autoencoder-based domain adaptation

Accurate and timely structural damage diagnosis is crucial to efficient disaster response and city renovation in post-earthquake events. The scarcity of labeled data hinders the powerful deep learning techniques from in-domain damage detection on target structures. Cross-domain transfer learning has emerged as a captivating strategy through digging knowledge from the abundant source domain to detect the damage in the target domain. However, the heterogeneity among multi-domain structures poses the challenge in seismic damage diagnosis. This study proposes a novel zero-shot knowledge transfer approach for seismic damage diagnosis through multi-channel one-dimensional convolutional neural networks (1D CNN) integrated with deep autoencoder (DAE)-based domain adaptation (DA). The framework consists of three modules, namely, data preprocessor adaptive to seismic vibration signals, DAE-based DA module, and damage diagnosis via multi-channel 1D CNN. The DA module is customized to seamlessly translate the unseen target-domain data to mimic latent representation via a DAE pretrained on the source data, thus realizing rigorous zero-shot learning. Imbalanced data distribution is also considered during the network training and testing. Two representative phases of knowledge transfer are performed to substantiate the knowledge transferability of the proposed method. The first phase involves multi-class damage quantification on two ASCE benchmark models from the simplified model to the refined one, and the second phase conducts binary damage detection on a three-story reinforced frame structure from the finite element numerical model to the laboratory-tested physical model. Both examples show that the proposed method exhibits high prediction accuracy and a lower false negative rate in achieving zero-shot knowledge transfer for cross-domain structural damage diagnosis. With a delicate network design for diverse data, the proposed knowledge transfer framework can be further extended from the present zero-shot approach to the few-shot learning paradigm, thus suggesting a feasible algorithm adaptability and promising engineering applicability.

Classification of Benign-Malignant Thyroid Nodules Based on Hyperspectral Technology.

In recent years, the incidence of thyroid cancer has rapidly increased. To address the issue of the inefficient diagnosis of thyroid cancer during surgery, we propose a rapid method for the diagnosis of benign and malignant thyroid nodules based on hyperspectral technology. Firstly, using our self-developed thyroid nodule hyperspectral acquisition system, data for a large number of diverse thyroid nodule samples were obtained, providing a foundation for subsequent diagnosis. Secondly, to better meet clinical practical needs, we address the current situation of medical hyperspectral image classification research being mainly focused on pixel-based region segmentation, by proposing a method for nodule classification as benign or malignant based on thyroid nodule hyperspectral data blocks. Using 3D CNN and VGG16 networks as a basis, we designed a neural network algorithm (V3Dnet) for classification based on three-dimensional hyperspectral data blocks. In the case of a dataset with a block size of 50 × 50 × 196, the classification accuracy for benign and malignant samples reaches 84.63%. We also investigated the impact of data block size on the classification performance and constructed a classification model that includes thyroid nodule sample acquisition, hyperspectral data preprocessing, and an algorithm for thyroid nodule classification as benign and malignant based on hyperspectral data blocks. The proposed model for thyroid nodule classification is expected to be applied in thyroid surgery, thereby improving surgical accuracy and providing strong support for scientific research in related fields.