Vector Quantization Research Articles

Compare the Performance of Distinct Neural Networks Techniques to diagnose the kidney stone disease

Artificial Neural Networks are excellent at identifying patterns or trends in data, which makes them perfect for forecasting or prediction. Thus, neural networks have extensive application in biological systems. The application of neural networks to kidney stone diagnosis is emphasized in this article. Kidney stone issues can be diagnosed with neural networks by applying technological concepts such as MLP, SVM, RBF, and BPA. The purpose of this research is to use three different neural network algorithms—each with its own specific design and set of properties to identify kidney stone disease. The performance of the three neural networks is compared in this research with respect to training data set size, model creation time, and accuracy. Kidney stone sickness will be diagnosed using radial basis function (RBF) networks, two layers feed forward perceptrons trained with the back propagation training algorithm, and learning vector quantization (LVQ). However, determining the best approach for any particular diagnostic had never been an easy task. Like many other illnesses, kidney stones have already been diagnosed using neural network algorithms. The main objective of this work is to recommend the best medical diagnostic instrument, such as kidney stone detection, to reduce diagnosis times and improve accuracy and efficiency.

Abstract and Explore: A Novel Behavioral Metric with Cyclic Dynamics in Reinforcement Learning

Intrinsic motivation lies at the heart of the exploration of reinforcement learning, which is primarily driven by the agent's inherent satisfaction rather than external feedback from the environment. However, in recent more challenging procedurally-generated environments with high stochasticity and uninformative extrinsic rewards, we identify two significant issues of applying intrinsic motivation. (1) State representation collapse: In existing methods, the learned representations within intrinsic motivation have a high probability to neglect the distinction among different states and be distracted by the task-irrelevant information brought by the stochasticity. (2) Insufficient interrelation among dynamics: Unsuccessful guidance provided by the uninformative extrinsic reward makes the dynamics learning in intrinsic motivation less effective. In light of the above observations, a novel Behavioral metric with Cyclic Dynamics (BCD) is proposed, which considers both cumulative and immediate effects and facilitates the abstraction and exploration of the agent. For the behavioral metric, the successor feature is utilized to reveal the expected future rewards and alleviate the heavy reliance of previous methods on extrinsic rewards. Moreover, the latent variable and vector quantization techniques are employed to enable an accurate measurement of the transition function in a discrete and interpretable manner. In addition, cyclic dynamics is established to capture the interrelations between state and action, thereby providing a thorough awareness of environmental dynamics. Extensive experiments conducted on procedurally-generated environments demonstrate the state-of-the-art performance of our proposed BCD.

Prediction of Infecting Cancer based on Logistic Regression Model

Cancer is one of the most fatal contributors towards the increasing mortality rate of mankind. This represents an important topic to study for the sake of the welfare of humanity. However, the traditional manual diagnosis and prognosis procedures of this disease are quite time-consuming, even for a professional medical practitioner. Thus, a model with robust power of predictions regarding the state of the tumour (i.e., probable cancer) would benefit most patients from the toxic side effects and additional medical services fees incurred by inessential treatment. To this end, the Logistic Regression Method is applied to derive a powerful model combining an algorithm from machine learning criteria – Learning Vector Quantization. There are two phases in building this model, phase 1 is the pretreatment of our data from Kaggle, including the process of normalization, classification and feature selection. From feature selection, 14 variables are extracted based on their level of importance. Thereby, models are built on these 14 variables and one output Y, consisting of 0 or 1, derived from the classification process. These 14 variables have a huge impact towards the prediction process since they significantly reduce the work needed for the procedure. Phase 2 is applying the relevant methodology to produce our model and examine its efficiency. To test the ability of the trained logistic models to recognize cancer, we analyzed residual samples that were not previously used for the training procedure and correctly classified them in all cases. The evaluation of the model combines methods of the AUC-ROC curve as well as the confusion matrix, which are powerful statistical approaches. The AUC value after calculation is , which strengthens the validity and efficiency of the model. Besides, the confusion matrix reveals an accuracy of 0.9787 (out of 1). The repercussions of this model can be utilized in the field of forecasting the probability of cancer from concrete measurements of the tumor. This may refrain from the exorbitant expenditure on the usage of certain delicate medical machines, like X-ray. Moreover, this provides foundation statistics for the application of modern AI technology in the cancer prediction region.

G2P-DDM: Generating Sign Pose Sequence from Gloss Sequence with Discrete Diffusion Model

The Sign Language Production (SLP) project aims to automatically translate spoken languages into sign sequences. Our approach focuses on the transformation of sign gloss sequences into their corresponding sign pose sequences (G2P). In this paper, we present a novel solution for this task by converting the continuous pose space generation problem into a discrete sequence generation problem. We introduce the Pose-VQVAE framework, which combines Variational Autoencoders (VAEs) with vector quantization to produce a discrete latent representation for continuous pose sequences. Additionally, we propose the G2P-DDM model, a discrete denoising diffusion architecture for length-varied discrete sequence data, to model the latent prior. To further enhance the quality of pose sequence generation in the discrete space, we present the CodeUnet model to leverage spatial-temporal information. Lastly, we develop a heuristic sequential clustering method to predict variable lengths of pose sequences for corresponding gloss sequences. Our results show that our model outperforms state-of-the-art G2P models on the public SLP evaluation benchmark. For more generated results, please visit our project page: https://slpdiffusier.github.io/g2p-ddm.

Quantized information-theoretic learning based Laguerre functional linked neural networks for nonlinear active noise control

Traditional functional linked neural networks (FLNNs) impose a significant computational burden due to their input expansion, primarily stemming from the utilization of digital filters. This paper presents a Laguerre FLNNs filter for nonlinear active noise control (NANC) systems. By employing the truncated Laguerre series, the presented filter achieves effective approximation of long primary paths with a reduced filter length. Moreover, we develop adaptive algorithms rooted in information-theoretic learning (ITL) within the framework of the Laguerre-FLNNs NANC model. Using the ITL criterions, a Laguerre filtered-s maximum correntropy criterion (LFsMCC) algorithm is derived and a Laguerre filtered-s quantized minimum error entropy criterion (LFsQMEE) algorithm is proposed by minimizing Renyi’s quadratic entropy. To reduce the computation cost, an online vector quantization method is utilized to improve the LFsQMEE. This technique selectively quantizes the error vectors, reducing them to a smaller subset of samples within the codebook. Moreover, an enhanced LFsQMEE with a fiducial point is introduced. The steady-state performance and the computational complexity are analyzed. Theoretical analysis is validated through simulations and the control performance of the proposed model and algorithms is tested in experiments with both simulated and real paths.

Domain generalization of chemical process fault diagnosis by maximizing domain feature distribution alignment

Fault detection and diagnosis (FDD) is crucial for ensuring safety and quality control in chemical industry. But data-driven FDD methods are usually trained with samples under certain operating conditions or data domains. This leads to their performance degradation caused by domain shifts in practice. To address this, a new FDD network, termed the DFDA model, has been designed to achieve domain generalization. Distribution of features extracted from fault samples is progressively aligned by supervised contrastive learning, learning vector quantization and gradient reversal adversarial learning in the DFDA model. So that FDD using such aligned features can potentially offer enhanced domain generalization capabilities. The performance of the DFDA model is benchmarked against other state-of-the-art FDD frameworks using data from various domains/modes of the Tennessee Eastman Process and an actual industrial process. The experimental outcomes indicate that the DFDA model consistently outperforms others in five distinct tasks, achieving an average Fault Detection Rate (FDR) that is 23% higher than that of ViT and 16% higher than CausalViT.

Identification of clinical characteristics biomarkers for rheumatoid arthritis through targeted DNA methylation sequencing

ObjectivesRheumatoid arthritis (RA) is a complex disease with a challenging diagnosis, especially in seronegative patients. The aim of this study is to investigate whether the methylation sites associated with the overall immune response in RA can assist in clinical diagnosis, using targeted methylation sequencing technology on peripheral venous blood samples. MethodsThe study enrolled 241 RA patients, 30 osteoarthritis patients (OA), and 30 healthy volunteers control (HC). Fifty significant cytosine guanine (CG) sites between undifferentiated arthritis and RA were selected and analyzed using targeted DNA methylation sequencing. Logistic regression models were used to establish diagnostic models for different clinical features of RA, and six machine learning methods (logit model, random forest, support vector machine, adaboost, naive bayes, and learning vector quantization) were used to construct clinical diagnostic models for different subtypes of RA. Least absolute shrinkage and selection operator regression and detrended correspondence analysis were utilized to screen for important CGs. Spearman correlation was used to calculate the correlation coefficient. ResultsThe study identified 16 important CG sites, including tumor necrosis factort receptor associated factor 5 (TRAF5) (chr1:211500151), mothers against decapentaplegic homolog 3 (SMAD3) (chr15:67357339), tumor endothelial marker 1 (CD248) (chr11:66083766), lysosomal trafficking regulator (LYST) (chr1:235998714), PR domain zinc finger protein 16 (PRDM16) (chr1:3307069), A-kinase anchoring protein 10 (AKAP10) (chr17:19850460), G protein subunit gamma 7 (GNG7) (chr19:2546620), yes1 associated transcriptional regulator (YAP1) (chr11:101980632), PRDM16 (chr1:3163969), histone deacetylase complex subunit sin3a (SIN3A) (chr15:75747445), prenylated rab acceptor protein 2 (ARL6IP5) (chr3:69134502), mitogen-activated protein kinase kinase kinase 4 (MAP3K4) (chr6:161412392), wnt family member 7A (WNT7A) (chr3:13895991), inhibin subunit beta B (INHBB) (chr2:121107018), deoxyribonucleic acid replication helicase/nuclease 2 (DNA2) (chr10:70231628) and chromosome 14 open reading frame 180 (C14orf180) (chr14:105055171). Seven CG sites showed abnormal changes between the three groups (P < 0.05), and 16 CG sites were significantly correlated with common clinical indicators (P < 0.05). Diagnostic models constructed using different CG sites had an area under the receiver operating characteristic curve (AUC) range of 0.64–0.78 for high-level clinical indicators of high clinical value, with specificity ranging from 0.42 to 0.77 and sensitivity ranging from 0.57 to 0.88. The AUC range for low-level clinical indicators of high clinical value was 0.63–0.72, with specificity ranging from 0.48 to 0.74 and sensitivity ranging from 0.72 to 0.88. Diagnostic models constructed using different CG sites showed good overall diagnostic accuracy for the four subtypes of RA, with an accuracy range of 0.61–0.96, a balanced accuracy range of 0.46–0.94, and an AUC range of 0.46–0.94. ConclusionsThis study identified potential clinical diagnostic biomarkers for RA and provided novel insights into the diagnosis and subtyping of RA. The use of targeted deoxyribonucleic acid (DNA) methylation sequencing and machine learning methods for establishing diagnostic models for different clinical features and subtypes of RA is innovative and can improve the accuracy and efficiency of RA diagnosis.

Quantitative evaluation model of variable diagnosis for chest X-ray images using deep learning.

The purpose of this study is to demonstrate the use of a deep learning model in quantitatively evaluating clinical findings typically subject to uncertain evaluations by physicians, using binary test results based on routine protocols. A chest X-ray is the most commonly used diagnostic tool for the detection of a wide range of diseases and is generally performed as a part of regular medical checkups. However, when it comes to findings that can be classified as within the normal range but are not considered disease-related, the thresholds of physicians' findings can vary to some extent, therefore it is necessary to define a new evaluation method and quantify it. The implementation of such methods is difficult and expensive in terms of time and labor. In this study, a total of 83,005 chest X-ray images were used to diagnose the common findings of pleural thickening and scoliosis. A novel method for quantitatively evaluating the probability that a physician would judge the images to have these findings was established. The proposed method successfully quantified the variation in physicians' findings using a deep learning model trained only on binary annotation data. It was also demonstrated that the developed method could be applied to both transfer learning using convolutional neural networks for general image analysis and a newly learned deep learning model based on vector quantization variational autoencoders with high correlations ranging from 0.89 to 0.97.

Intelligent passive infrared sensor based on learning vector quantization for human detection

Passive Infrared (PIR) Sensors have been used widely in human detection indoors nowadays due to their low cost and range. However, traditional PIR sensors may get fault detection, especially when the human is in a static pose. To overcome this limitation, a Machine Learning (ML)-based PIR sensor is proposed in this work for detection accuracy enhancement. The Learning Vector Quantization (LVQ) approach is used to be easily implemented in the embedded device (which requires a low computational complexity) to provide a real-time response. The experimental scenarios to create the datasets are conducted in two distinct locations for training and testing purposes. In each location, participants performed a series of different activities and left the room unoccupied. Data is collected via a PIR sensor and then wireless transmitted to a computer for training and testing. In the test set, the presence of humans with an accuracy of 89.25 % is obtained using the proposed LVQ algorithm prediction. Finally, the LVQ is implemented on an embedded device based on Xtensa Dual-Core 32-bit LX6 CPU to form an intelligent PIR (iPIR)-based LVQ sensor, this novel iPIR sensor then is evaluated and tested with a remarkable result.

Semisupervised Vector Quantization in Visual SLAM Using HGCN

We present a novel vector quantization (VQ) module for the two state-of-the-art long-range simultaneous localization and mapping (SLAM) algorithms. The VQ task in SLAM is generally performed using unsupervised methods. We provide an alternative approach trough embedding a semisupervised hyperbolic graph convolutional neural network (HGCN) in the VQ step of the SLAM processes. The SLAM platforms we have utilized for this purpose are fast appearance-based mapping (FABMAP) and oriented fast and rotated short (ORB), both of which rely on extracting the features of the captured images in their loop closure detection (LCD) module. For the first time, we have considered the space formed by these SURF features, robust image descriptors, as a graph, enabling us to apply an HGCN in the VQ section which results in an improved LCD performance. The HGCN vector quantizes the SURF feature space, leading to a bag-of-word (BoW) representation construction of the images. This representation is subsequently used to determine LCD accuracy and recall. Our approaches in this study are referred to as HGCN-FABMAP and HGCN-ORB. The main advantage of using HGCN in the LCD section is that it scales linearly when the features are accumulated. The benchmarking experiments show the superiority of our methods in terms of both trajectory generation accuracy in small-scale paths and LCD accuracy and recall for large-scale problems.

A Codebook Compression Method for Vector Quantization Algorithm

This study introduces a novel approach to enhance the compression ratio of the vector quantization (VQ) algorithm by specifically targeting the compression of its codebook. The VQ algorithm typically generates an index matrix and a codebook to represent compressed images. The proposed method focuses on reducing the size of the codebook, which comprises N codewords, each with elements quantized into four levels. Each 8-bit element in a codeword is compressed to 2-bits, and the encoded codeword is accompanied by the minimum value and a threshold value in the codebook. Experimental results on benchmark color images, such as baboon, airplane, Lena, and others, demonstrate a significant reduction of 62.50% in the size of the VQ codebook.

Hybrid Architecture Model of Genetic Algorithm and Learning Vector Quantization Neural Network for Early Identification of Ear, Nose, and Throat Diseases

Background: In 2020, the World Health Organization (WHO) estimated that 466 million people worldwide are affected by hearing loss, with 34 million of them being children. Indonesia is identified as one of the four Asian countries with a high prevalence of hearing loss, specifically at 4.6%. Previous research was conducted to identify diseases related to the Ear, Nose, and Throat, utilizing the certainty factor method with a test accuracy rate of 46.54%. The novelty of this research lies in the combination of two methods, the use of genetic algorithms for optimization and learning vector quantization to improve the level of accuracy for early identification of Ear, Nose, and Throat diseases. Objective: This research aims to produce a hybrid model between the genetic algorithm and the learning vector quantization neural network to be able to identify Ear, Nose, and Throat diseases with mild symptoms to improve accuracy. Methods: Implementing a 90:10 ratio means that 90% (186 data) of the data from the initial sequence is assigned for training purposes, while the remaining 10% (21 data) is allocated for testing. The procedural stages of genetic algorithm-learning vector quantization are population initialization, crossover, mutation, evaluation, selection elitism, and learning vector quantization training. Results The optimum hybrid genetic algorithm-learning vector quantization model for early identification of Ear, Nose, and Throat diseases was obtained with an accuracy of 82.12%. The parameter values with the population size 10, cr 0.9, mr 0.1, maximum epoch of 5000, error goal of 0.01, and learning rate (alpha) of 0.5. Better accuracy was obtained compared to backpropagation (64%), certainty factor 46.54%), and radial basic function (72%). Conclusion: Experiments in this research, successed identifying models by combining genetic algorithm-learning vector quantization to perform the early identification of Ear, Nose, and Throat diseases. For further research, it's very challenging to develop a model that automatically adapts the bandwidth parameters of the weighting functions during trainin Keywords: Early Identification, Ear-Nose-Throat Diseases, Genetic Algorithm, Learning Vector Quantization

Efficient high-resolution template matching with vector quantized nearest neighbour fields

Template matching is a fundamental problem in computer vision with applications in fields including object detection, image registration, and object tracking. Current methods rely on nearest-neighbour (NN) matching, where the query feature space is converted to NN space by representing each query pixel with its NN in the template. NN-based methods have been shown to perform better in occlusions, appearance changes, and non-rigid transformations; however, they scale poorly with high-resolution data and high feature dimensions. We present an NN-based method that efficiently reduces the NN computations and introduces filtering in the NN fields (NNFs). A vector quantization step is introduced before the NN calculation to represent the template with k features, and the filter response over the NNFs is used to compare the template and query distributions over the features. We show that state-of-the-art performance is achieved in low-resolution data, and our method outperforms previous methods at higher resolution.

Addressing Concerns about Single Path Analysis in Business Cycle Turning Points: The Case of Learning Vector Quantization

Data-driven approaches in machine learning are increasingly applied in economic analysis, particularly for identifying business cycle (BC) turning points. However, temporal dependence in BCs is often overlooked, leading to what we term single path analysis (SPA). SPA neglects the diverse potential routes of a temporal data structure. It hinders the evaluation and calibration of algorithms. This study emphasizes the significance of acknowledging temporal dependence in BC analysis and illustrates the problem of SPA using learning vector quantization (LVQ) as a case study. LVQ was previously adapted to use economic indicators to determine the current BC phase, exhibiting flexibility in adapting to evolving patterns. To address temporal complexities, we employed a multivariate Monte Carlo simulation incorporating a specified number of change-points, autocorrelation, and cross-correlations, from a second-order vector autoregressive model. Calibrated with varying levels of observed economic leading indicators, our approach offers a deeper understanding of LVQ’s uncertainties. Our results demonstrate the inadequacy of SPA, unveiling diverse risks and worst-case protection strategies. By encouraging researchers to consider temporal dependence, this study contributes to enhancing the robustness of data-driven approaches in financial and economic analyses, offering a comprehensive framework for addressing SPA concerns.

Improving the second-tier classification of methylmalonic acidemia patients using a machinelearning ensemble method.

Methylmalonic acidemia (MMA) is a disorder of autosomal recessive inheritance, with an estimated prevalence of 1:50,000. First-tier clinical diagnostic tests often return many false positives [five false positive (FP): one true positive (TP)]. In this work, our goal was to refine a classification model that can minimize the number of false positives, currently an unmet need in the upstream diagnostics of MMA. We developed machinelearning multivariable screening models for MMA with utility as a secondary-tier tool for false positives reduction. We utilized mass spectrometry-based features consisting of 11 amino acids and 31 carnitines derived from dried blood samples of neonatal patients, followed by additional ratio feature construction. Feature selection strategies (selection by filter, recursive feature elimination, and learned vector quantization) were used to determine the input set for evaluating the performance of 14 classification models to identify a candidate model set for an ensemble model development. Our work identified computational models that explore metabolic analytes to reduce the number of false positives without compromising sensitivity. The best results [area under the receiver operating characteristic curve (AUROC) of 97%, sensitivity of 92%, and specificity of 95%] were obtained utilizing an ensemble of the algorithms random forest, C5.0, sparse linear discriminant analysis, and autoencoder deep neural network stacked with the algorithm stochastic gradient boosting as the supervisor. The model achieved a good performance trade-off for a screening application with 6% false-positive rate (FPR) at 95% sensitivity, 35% FPR at 99% sensitivity, and 39% FPR at 100% sensitivity. The classification results and approach of this research can be utilized by clinicians globally, to improve the overall discovery of MMA in pediatric patients. The improved method, when adjusted to 100% precision, can be used to further inform the diagnostic process journey of MMA and help reduce the burden for patients and their families.

A One-Class Classifier for the Detection of GAN Manipulated Multi-Spectral Satellite Images

The current image generative models have achieved a remarkably realistic image quality, offering numerous academic and industrial applications. However, to ensure these models are used for benign purposes, it is essential to develop tools that definitively detect whether an image has been synthetically generated. Consequently, several detectors with excellent performance in computer vision applications have been developed. However, these detectors cannot be directly applied as they areto multi-spectral satellite images, necessitating the training of new models. While two-class classifiers generally achieve high detection accuracies, they struggle to generalize to image domains and generative architectures different from those encountered during training. In this paper, we propose a one-class classifier based on Vector Quantized Variational Autoencoder 2 (VQ-VAE 2) features to overcome the limitations of two-class classifiers. We start by highlighting the generalization problem faced by binary classifiers. This was demonstrated by training and testing an EfficientNet-B4 architecture on multiple multi-spectral datasets. We then illustrate that the VQ-VAE 2-based classifier, which was trained exclusively on pristine images, could detect images from different domains and generated by architectures not encountered during training. Finally, we conducted a head-to-head comparison between the two classifiers on the same generated datasets, emphasizing the superior generalization capabilities of the VQ-VAE 2-based detector, wherewe obtained a probability of detection at a 0.05 false alarm rate of 1 for the blue and red channels when using the VQ-VAE 2-based detector, and 0.72 when we used the EfficientNet-B4 classifier.

Towards Learning Discrete Representations via Self-Supervision for Wearables-Based Human Activity Recognition.

Human activity recognition (HAR) in wearable and ubiquitous computing typically involves translating sensor readings into feature representations, either derived through dedicated pre-processing procedures or integrated into end-to-end learning approaches. Independent of their origin, for the vast majority of contemporary HAR methods and applications, those feature representations are typically continuous in nature. That has not always been the case. In the early days of HAR, discretization approaches had been explored-primarily motivated by the desire to minimize computational requirements on HAR, but also with a view on applications beyond mere activity classification, such as, for example, activity discovery, fingerprinting, or large-scale search. Those traditional discretization approaches, however, suffer from substantial loss in precision and resolution in the resulting data representations with detrimental effects on downstream analysis tasks. Times have changed, and in this paper, we propose a return to discretized representations. We adopt and apply recent advancements in vector quantization (VQ) to wearables applications, which enables us to directly learn a mapping between short spans of sensor data and a codebook of vectors, where the index comprises the discrete representation, resulting in recognition performance that is at least on par with their contemporary, continuous counterparts-often surpassing them. Therefore, this work presents a proof of concept for demonstrating how effective discrete representations can be derived, enabling applications beyond mere activity classification but also opening up the field to advanced tools for the analysis of symbolic sequences, as they are known, for example, from domains such as natural language processing. Based on an extensive experimental evaluation of a suite of wearable-based benchmark HAR tasks, we demonstrate the potential of our learned discretization scheme and discuss how discretized sensor data analysis can lead to substantial changes in HAR.

Retinal spike train decoder using vector quantization for visual scene reconstruction

AbstractThe retinal impulse signal is the basic carrier of visual information. It records the distribution of light on the retina. However, its direct conversion to a scene image is difficult due to the nonlinear characteristics of its distribution. Therefore, the use of artificial neural network to reconstruct the scene from retinal spikes has become an important research area. This paper proposes the architecture of a neural network based on vector quantization, where the feature vectors of spike trains are extracted, compressed, and stored using a feature extraction and compression network. During the decoding process, the nearest neighbour search method is used to find the nearest feature vector corresponding to each feature vector in the feature map. Finally, a reconstruction network is used to decode a new feature map composed of matching feature vectors to obtain a visual scene. This paper also verifies the impact of vector quantization on the characteristics of pulse signals by comparing experiments and visualizing the characteristics before and after vector quantization. The network delivers promising performance when evaluated on different datasets, demonstrating that this research is of great significance for improving relevant applications in the fields of retinal image processing and artificial intelligence.

Fast Real-Time Brain Tumor Detection Based on Stimulated Raman Histology and Self-Supervised Deep Learning Model.

In intraoperative brain cancer procedures, real-time diagnosis is essential for ensuring safe and effective care. The prevailing workflow, which relies on histological staining with hematoxylin and eosin (H&E) for tissue processing, is resource-intensive, time-consuming, and requires considerable labor. Recently, an innovative approach combining stimulated Raman histology (SRH) and deep convolutional neural networks (CNN) has emerged, creating a new avenue for real-time cancer diagnosis during surgery. While this approach exhibits potential, there exists an opportunity for refinement in the domain of feature extraction. In this study, we employ coherent Raman scattering imaging method and a self-supervised deep learning model (VQVAE2) to enhance the speed of SRH image acquisition and feature representation, thereby enhancing the capability of automated real-time bedside diagnosis. Specifically, we propose the VQSRS network, which integrates vector quantization with a proxy task based on patch annotation for analysis of brain tumor subtypes. Training on images collected from the SRS microscopy system, our VQSRS demonstrates a significant speed enhancement over traditional techniques (e.g., 20-30min). Comparative studies in dimensionality reduction clustering confirm the diagnostic capacity of VQSRS rivals that of CNN. By learning a hierarchical structure of recognizable histological features, VQSRS classifies major tissue pathological categories in brain tumors. Additionally, an external semantic segmentation method is applied for identifying tumor-infiltrated regions in SRH images. Collectively, these findings indicate that this automated real-time prediction technique holds the potential to streamline intraoperative cancer diagnosis, providing assistance to pathologists in simplifying the process.

Damage Detection of Gantry Crane with a Moving Mass Using Artificial Neural Network

Gantry cranes play a pivotal role in various industrial applications, and their reliable operation is paramount. While routine inspections are standard practice, certain defects, particularly in less accessible components, remain challenging to detect early. In this study, first a finite element model is presented, and the damage is introduced using random changes in the stiffness of different parts of the structure. Contrary to the assumption of inherent reliability, undetected defects in crucial structural elements can lead to catastrophic failures. Then, the vibration equations of healthy and damaged models are analyzed to find the displacement, velocity, and acceleration of the different crane parts. The learning vector quantization neural network is used to train and detect the defects. The output is the location of the damage and the damage severity. Noisy data are then used to evaluate the network performance robustness. This research also addresses the limitations of traditional inspection methods, providing early detection and classification of defects in gantry cranes. The study’s relevance lies in the need for a comprehensive and efficient damage detection method, especially for components not easily accessible during routine inspections.