Convolutional Neural Network Training Research Articles

Quantum-enhanced forecasting: Leveraging quantum gramian angular field and CNNs for stock return predictions

This paper presents the Quantum Gramian Angular Field (QGAF) method, which integrates quantum computing with deep learning to enhance forecasting in time series analysis. This method effectively converts stock return time series data into a format compatible with Convolutional Neural Network (CNN) training. Our empirical tests, conducted on stock market data from China, Hong Kong, and the United States, demonstrate that QGAF significantly outperforms the traditional GAF approach in accuracy. These findings underscore the potential of combining quantum computing and deep learning in financial time series forecasting.

Gasoline Engine Misfire Fault Diagnosis Method Based on Improved YOLOv8

In order to realize the online diagnosis and prediction of gasoline engine fire faults, this paper proposes an improved misfire fault detection algorithm model based on YOLOv8 for sound signals of gasoline engines. The improvement involves substituting a C2f module in the YOLOv8 backbone network by a BiFormer attention module and another C2f module substituted by a CBAM module that combines channel and spatial attention mechanisms which enhance the neural network’s capacity to extract the complex features. The normal and misfire sound signals of a gasoline engine are processed by wavelet transformation and converted to time–frequency images for the training, verification, and testing of convolutional neural network. The experimental results show that the precision of the improved YOLOv8 algorithm model is 99.71% for gasoline engine fire fault tests, which is 2 percentage points higher than for the YOLOv8 network model. The diagnosis time of each sound is less than 100 ms, making it suitable for developing IoT devices for gasoline engine misfire fault diagnosis and driverless vehicles.

Innovative infrastructure to access Brazilian fungal diversity using deep learning.

In the present investigation, we employ a novel and meticulously structured database assembled by experts, encompassing macrofungi field-collected in Brazil, featuring upwards of 13,894 photographs representing 505 distinct species. The purpose of utilizing this database is twofold: firstly, to furnish training and validation for convolutional neural networks (CNNs) with the capacity for autonomous identification of macrofungal species; secondly, to develop a sophisticated mobile application replete with an advanced user interface. This interface is specifically crafted to acquire images, and, utilizing the image recognition capabilities afforded by the trained CNN, proffer potential identifications for the macrofungal species depicted therein. Such technological advancements democratize access to the Brazilian Funga, thereby enhancing public engagement and knowledge dissemination, and also facilitating contributions from the populace to the expanding body of knowledge concerning the conservation of macrofungal species of Brazil.

Optimized CNN and adaptive RBFNN for channel estimation and hybrid precoding approaches for multi user millimeter wave massive MIMO

ABSTRACT The millimetre-wave (mmWave) communication satisfies the demand for high data rates due to the characteristic of wide bandwidth. Using massive multiple-input multiple-output (MIMO) technology, a significant propagation loss of mmWave communication is effectively compensated. However, it is challenging to provide a specialised radio frequency chain for each antenna due to the constrained physical area with closely spaced antennas and prohibitive power consumption in mmWave massive MIMO systems. This paper presents novel approaches for effective channel estimation and hybrid precoding in mmWave communication systems. To address the challenges of channel estimation, a convolutional neural network (CNN) is utilised, and network parameters are optimised using enhanced whale optimization algorithm (EWOA). The proposed CNN-based channel estimation method aims to accurately estimate the channel in mmWave systems with enhanced efficiency and reduced complexity. By training CNN using EWOA optimisation algorithm, the network parameters are fine-tuned to improve accuracy and generalisation capability of channel estimation process. Furthermore, hybrid precoding is achieved using adaptive radial-basis function neural networks (adaptive RBFNNs) which enables efficient precoding while minimising complexity. Moreover, the adaptive RBFNN approach determines the optimal precoding weights based on channel state information, resulting in a improved performance and a reduced computational overhead. The performance analysis is validated using the MATLAB/Simulink software and offers to provide effectual and reliable mmWave communication systems, facilitating the realisation of high-speed and high-capacity wireless networks.

378 Workload Assessment of Suturing Tasks and AI-Task Classification Using Electromyography

Abstract Aim It is well established that excess surgeon workload results in poorer performance. Workload can be divided into physical workload (PWL) and cognitive workload (CWL). The study aims are twofold: 1. Assess how the subjective PWL of suturing is affected by varying PWL and CWL 2. Develop an AI-classification algorithm for task detection using electromyography (EMG). Method Novices were trained in interrupted suturing and asked to suture under four conditions of varied workload. Tasks included were: 1. Control, 2. Different suture material (Silk), 3. Simultaneously undertaking a neurocognitive task and 4. Suturing at depth. Subjective workload was recorded using a validated workload questionnaire (SURG-TLX). EMG sensors recorded physiological data from the biceps brachii and extensor ulnar carpi. A convolutional neural network (CNN) was created for AI-task classification using EMG data. Results The depth task had the highest subjective workload. Subjective depth raw workload was significantly higher than Control (p=<0.01) and Silk (p=<0.001) but comparable to the neurocognitive task. Subjective depth weighted workload was significantly higher than the neurocognitive task (p=<0.05). Subjective depth adjusted workload was significantly higher than the neurocognitive and silk tasks (both p=<0.05). The CNN training accuracy was 76.4% (95%CI 75.5-77.4) and had a classification accuracy of 76.5% (95%CI 75.7-77.2). Conclusions The relationship between PWL and CWL on subjective PWL is complex. Despite this, the CNN was able to differentiate between tasks using objective EMG data with good accuracy. This CNN has potential to characterise CWL which can be further developed to detect excess workload to improve surgical training through objective benchmarks.

O-260 Identifying seminiferous tubules for sperm retrieval during microdissection testicular sperm extraction (M-TESE) using deep learning

Abstract Study question Is it possible to utilize artificial intelligence (AI) in the selection of seminiferous tubules for sperm retrieval during microdissection testicular sperm extraction (M-TESE)? Summary answer AI algorithm was able to segment seminiferous tubules deemed to be good candidates for sperm retrieval with IoU of 0.746 and F1 score of 72.5%. What is known already M-TESE is an advanced surgical procedure reserved for sperm retrieval in men with non-obstructive azoospermia (NOA). Meta-analysis have shown M-TESE might be superior in relation to sperm retrieval rates and postsurgical complications when compared to conventional techniques. Limitations of the technique are the relatively long learning curve for the surgeons and the longer intraoperative time required to identify the tubules with active spermatogenesis. Convolutional neural networks (CNNs) have been shown to successfully identify areas of interest in medical images such as CT and MRI scans. The possibility of utilizing trained CNNs in M-TESE procedures has so far not been studied. Study design, size, duration This is a cross sectional study analyzing image data gathered during M-TESE procedures including the first five men enrolled in a prospective study designed specifically to test the utilization of AI in the treatment of NOA. All participants signed written informed consent. Images were collected intraoperatively with low and high resolution cameras according to predefined protocol. Participants/materials, setting, methods CNN model with down and upsampling architecture was trained using patch-based technique with corresponding labelled truth image pairs based on combination of semi-automated hue saturation value thresholding and manual segmentation of seminiferous tubules. Tubules were allocated into two different classes by the operating surgeon according to the visual perception of their morphology as type 1 (i.e. larger, opaque, good candidates for micro dissection) and type 2 (i.e. sclerotic or atrophic; unlikely to harbor active spermatogenesis). Main results and the role of chance CNN models were trained on 1809 patches with corresponding ground truth segmented images. Two algorithms were tested: the first was trained solely to detect and semantically distinguish type 1 seminiferous tubules. The second was trained to semantically segment the major anatomical structures: tunica albuginea, testicular parenchyma, blood vessels; lobules and the two types of seminiferous tubules describe above. Validation was performed on 988 image patches not previously shown to the algorithm. After grid search for optimal learning rate and augmentation the first algorithm was able to segment type 1 tubules with F1 score of 72.5% and Jaccard Index (IoU) of 0.746. Training took 856 minutes on 48 core high performance computer (HPC) equipped with single graphics processing unit (GPU). Same computational environment was used in the training of the second algorithm. This model was able to segment anatomical structures such as parenchyma (IoU=0.732) and testicular lobules (IoU=0.683) but performed sub optimally on the clinically relevant type 1 tubules (IoU=0.432). The first trained algorithm was able to segment a single high resolution surgical image in 3.4 seconds on an HPC. However, the same procedure took 5.5 minutes on standard desktop computer with 8 core Intel processor without GPU. Limitations, reasons for caution The number of patients is relatively small and therefore more training data would be needed to achieve robust performance. Training data were labelled by single surgeon limiting the generalizability and possibly biasing the selection process. The need of HPC environment for real time segmentation can limit the clinical use. Wider implications of the findings This pilot study shows the potential of AI to help in choosing suitable tubules for micro dissection, shortening the learning curve for young andrological surgeons. The access to cluster based computation is getting easier by the day and can soon allow instant intraoperative AI segmentation, thus shortening the surgical procedure. Trial registration number NA

Smart agriculture: An intelligent approach for apple leaf disease identification based on convolutional neural network

AbstractPlant diseases pose a significant threat to global agricultural productivity and food safety. Early detection and accurate identification of these diseases are essential for effective disease management strategies. Traditional plant disease identification mainly relies on manual observation and experienced expert judgement, which has the disadvantages of being time‐consuming, labour‐intensive and low efficiency. Given the above problems, this study proposes a method for identifying apple leaf diseases based on a convolutional neural network combining hybrid attention and bidirectional long short‐term memory (BiLSTM). Appropriate apple leaf disease samples were selected from multiple public data sets to form an experimental data set. Then, the data set is imported into the improved convolutional neural network for training. Based on the original ResNet18 model, a new convolutional neural network, AppleNet, is constructed by adding a hybrid attention module and modifying the classifier structure. The experimental results show that the average recognition accuracy of AppleNet is 94.66%, which is 2.47% higher than that of the ResNet18 network. In addition, the training time of the model is only slightly increased. The ablation experiment further verified the effectiveness of the model modification. Compared with other advanced models in recognition accuracy and model training time, the superiority of AppleNet is confirmed. This study verifies that deep learning has great potential and application prospects in plant disease identification and provides a new technical solution for intelligent and convenient plant disease identification.

Wheat Leaf Disease Detection: A Lightweight Approach with Shallow CNN Based Feature Refinement

Improving agricultural productivity is essential due to rapid population growth, making early detection of crop diseases crucial. Although deep learning shows promise in smart agriculture, practical applications for identifying wheat diseases in complex backgrounds are limited. In this paper, we propose CropNet, a hybrid method that utilizes Red, Green, and Blue (RGB) imaging and a transfer learning approach combined with shallow convolutional neural networks (CNN) for further feature refinement. To develop our customized model, we conducted an extensive search for the optimal deep learning architecture. Our approach involves freezing the pre-trained model for feature extraction and adding a custom trainable CNN layer. Unlike traditional transfer learning, which typically uses trainable dense layers, our method integrates a trainable CNN, deepening the architecture. We argue that pre-trained features in transfer learning are better suited for a custom shallow CNN followed by a fully connected layer, rather than being fed directly into fully connected layers. We tested various architectures for pre-trained models including EfficientNetB0 and B2, DenseNet, ResNet50, MobileNetV2, MobileNetV3-Small, and Inceptionv3. Our approach combines the strengths of pre-trained models with the flexibility of custom architecture design, offering efficiency, effective feature extraction, customization options, reduced overfitting, and differential learning rates. It distinguishes itself from classical transfer learning techniques, which typically fine-tune the entire pre-trained network. Our aim is to provide a lightweight model suitable for resource-constrained environments, capable of delivering outstanding results. CropNet achieved 99.80% accuracy in wheat disease detection with reduced training time and computational cost. This efficient performance makes CropNet promising for practical implementation in resource-constrained agricultural settings, benefiting farmers and enhancing production.

A Digital Approach to via Edge Roughness Characterization and Quantification

This paper introduces a new digital integration that combines edge diffractometry with convolutional neural networks (CNN) for via metrology and inspection. The beam propagation method (BMP) was used to simulate the interferogram generated by edge diffractometry to characterize via edge roughness (VER). A comprehensive database was established to link different fringe patterns to VER for CNN training. The well-trained CNN-based methodology provided a fast and accurate assessment of VER, with a root mean squared error (RMSE) of 0.073 and an average mean absolute deviation ratio (MADR) of 2.274%. In addition, the proposed digital approach was compared to the multilayer perceptron machine (MLP) in terms of computational efficiency and predictive accuracy. The proposed digital integration greatly improved the accuracy and speed of VER measurement, characterization, and quantification, potentially enhancing device yield and reliability. The successful application of this digital approach could open up possibilities for various types of via or pattern metrology.

Unveiling Anomalies in Surveillance Videos

Abstract: The implementation of Convolutional Neural Network (CNN) algorithm for the detection of anomalies like fire and potholes in images or videos. Leveraging deep learning technique, the model aims to accurately identify fire, potholes, etc. within various contexts. The CNN architecture is trained on a dataset comprising diverse images to enhance its ability to generalize. This proposed project not only addresses safety concerns by promoting helmet usage and proper maintenance of roads but also contributes to the broader field of computer vision and object detection. This implementation involves training the CNN on annotated datasets, fine-tuning the model for optimal performance, and integrating it into a practical application for efficient anomaly identification. With a focus on real-time detection, the system utilizes image processing techniques and a trained CNN model to analyze visual data from cameras or video feeds. The system's versatility allows integration into surveillance systems, industrial sites, or any environment where fire detection is crucial for safety. By automating the detection process, the project contributes to minimizing human error and ensuring consistent monitoring. The proposed solution holds the potential to significantly impact safety protocols, particularly in industries where protective headgear is paramount. Potholes pose a significant threat to both drivers and pedestrians, leading to accidents and infrastructure damage. The proposed solution leverages CNN's ability to effectively process visual data, making it well-suited for image recognition tasks. Our approach involves training the CNN on a diverse dataset of road images to enable it to accurately identify potholes. The model will learn distinctive features and patterns associated with potholes, allowing for robust detection under various environmental conditions. Real-time implementation on embedded systems or cameras along roadways will enable instantaneous identification and alerting.

Audio Classification on the FSDKaggle2018 Dataset using Tensorflow, Keras

This project explores audio classification leveraging representation learning within the TensorFlow framework. The methodology focuses on the initial engineering of wave features derived from raw audio data, which are subsequently used to train convolutional neural networks (CNNs) for effective representation learning. By transforming the audio signals into a structured format amenable to convolutional processing, our system is designed to capture the intrinsic properties and patterns embedded in the sound waves. The feature engineering process is detailed where various envelope features such as the homomorphic envelogram, hilbert envelogram and wavelet decompositions help in extracting meaningful information from the raw audio signals. These engineered features provide a robust foundation for the subsequent layers of convolutional networks. The CNNs are meticulously architected to learn hierarchical representations, effectively capturing both low-level and high-level audio characteristics.This study attempts to reinforces the significance of tailored feature engineering in deep learning and demonstrate an effective audio classification pipeline using representation learning and open up new avenues for research in audio signal processing and machine learning.

Deepfake Detection using Integrate-backward-integrate Logic Optimization Algorithm with CNN

The emergence of deepfake technology has spurred the need for robust and adaptive methods to detect manipulated media content. This study explores the integration of the Integrate-backward-integrate (IbI) Logic Optimization Algorithm with Convolutional Neural Networks (CNNs) for enhanced deepfake detection. The proposed approach involves a multi-phase iterative process: the CNN initially trained on a diverse dataset encompassing both real and deepfake images. The CNN serves as the foundation for the IbI-driven optimization. The integration phase employs the trained CNN to forward-integrate images, classifying them as real or deepfake. Subsequently, the IbI Logic Optimization Algorithm engages in the backward phase, utilizing feedback from the CNN's performance to iteratively refine the network's parameters, architecture, and feature extraction capabilities. This iterative optimization process aims to adaptively enhance the CNN's ability to discern subtle nuances between authentic and manipulated visuals. The re-integration phase evaluates the refined CNN's performance through multiple iterations, seeking to iteratively improve deepfake detection accuracy. Validation occurs using separate datasets to prevent overfitting and ensure the model's generalizability. The proposed method aims to enhance the CNN's adaptability to evolving deepfake techniques, addressing the dynamic nature of manipulative media creation. This fusion of IbI Logic Optimization with CNNs presents a promising avenue for bolstering deepfake detection capabilities. However, the effectiveness of this approach relies on dataset quality, network architecture, and the dynamic nature of deepfake generation techniques. Continuous refinement and validation are essential to adapt the model to new challenges posed by advancing deepfake technologies.

Two-stage deep learning classification for diabetic retinopathy using gradient weighted class activation mapping

The fundus images of patients with Diabetic Retinopathy (DR) often display numerous lesions scattered across the retina. Current methods typically utilize the entire image for network learning, which has limitations since DR abnormalities are usually localized. Training Convolutional Neural Networks (CNNs) on global images can be challenging due to excessive noise. Therefore, it's crucial to enhance the visibility of important regions and focus the recognition system on them to improve accuracy. This study investigates the task of classifying the severity of diabetic retinopathy in eye fundus images by employing appropriate preprocessing techniques to enhance image quality. We propose a novel two-branch attention-guided convolutional neural network (AG-CNN) with initial image preprocessing to address these issues. The AG-CNN initially establishes overall attention to the entire image with the global branch and then incorporates a local branch to compensate for any lost discriminative cues. We conduct extensive experiments using the APTOS 2019 DR dataset. Our baseline model, DenseNet-121, achieves average accuracy/AUC values of 0.9746/0.995, respectively. Upon integrating the local branch, the AG-CNN improves the average accuracy/AUC to 0.9848/0.998, representing a significant advancement in state-of-the-art performance within the field.

Deep learning models and methods for solving the problems of remote monitoring of forest resources

Relevance. The need for precise data analysis in remote monitoring of Earth's forest resources through satellites and unmanned aerial vehicles. Aim. Analysis of the current research status in forest remote monitoring via satellites and unmanned aerial vehicles, formulation of directions for the prospective development of this area; implementation and investigation of new deep learning models for analyzing high and very high-resolution images of coniferous forests. Objects. Hardware, models, methods, information systems, and technologies for real-time analysis of remote monitoring data of forest resources, obtained in the form of high and very high-resolution images. Methods. Deep learning models and methods for classifying trees in images; methodology for conducting real-time remote forest monitoring; methods for training, validation, and research of convolutional neural networks. Results and conclusions. Analytical review of models, methods, and information technologies for real-time analysis of remote forest monitoring data; list of formulated directions for prospective development of methodology and tools for efficient remote forest monitoring; development of two models, Mo-U-Net and Mo-Res-U-Net, based on the classical U-Net model. Two datasets based on imagery from an unmanned aerial vehicle were created for training, validation, and research of these models. The research results were obtained for solving multiclass classification tasks of Siberian fir (A. sibirica) and Siberian pine (P. sibirica) trees infested by insect pests. The studies showed that unlike the classical U-Net model, these models provide a higher classification accuracy for all classes of A. sibirica and P. sibirica trees, including intermediate classes, with IoU and mIoU metrics above the threshold value of 0.5, indicating the practical value of such models for the forestry industry.

Measuring the substructure mass power spectrum of 23 SLACS strong galaxy–galaxy lenses with convolutional neural networks

ABSTRACT Strong gravitational lensing can be used as a tool for constraining the substructure in the mass distribution of galaxies. In this study we investigate the power spectrum of dark matter perturbations in a population of 23 Hubble Space Telescope images of strong galaxy–galaxy lenses selected from The Sloan Lens ACS (SLACS) survey. We model the dark matter substructure as a Gaussian random field perturbation on a smooth lens mass potential, characterized by power-law statistics. We expand upon the previously developed machine learning framework to predict the power-law statistics by using a convolutional neural network (CNN) that accounts for both epistemic and aleatoric uncertainties. For the training sets, we use the smooth lens mass potentials and reconstructed source galaxies that have been previously modelled through traditional fits of analytical and shapelet profiles as a starting point. We train three CNNs with different training set: the first using standard data augmentation on the best-fitting reconstructed sources, the second using different reconstructed sources spaced throughout the posterior distribution, and the third using a combination of the two data sets. We apply the trained CNNs to the SLACS data and find agreement in their predictions. Our results suggest a significant substructure perturbation favouring a high frequency power spectrum across our lens population.

Efficient Guided Grad-CAM Tuned Patch Neural Network for Accurate Anomaly Detection in Full Images

Deep learning-based anomaly detection in images has recently gained popularity as an investigative field with many global submissions. To simplify complex data analysis, researchers in the deep learning subfield of machine learning employ Artificial Neural Networks (ANNs) with many hidden layers. Finding data occurrences that significantly differ from generalizable to most data sets is the primary goal of anomaly detection. Many medical imaging applications use convolutional neural networks (CNNs) to examine anomalies automatically. While CNN structures are reliable feature extractors, they encounter challenges when simultaneously classifying and segmenting spots that need removal from scans. We suggest a separate and integration system to solve these issues, separated into two distinct departments: classification and segmentation. Initially, many network architecturesare taught independently for each abnormality, and these networks’ main components are combined. A sharedcomponent of the branched structure functions for all abnormalities. The final structure has two branches: onehas distinct sub-networks, each intended to classify a particular abnormality, and the other for segmenting various abnormalities. Deep CNNs training directly on high-resolution images necessitate input layer image compression, which results in the loss of information necessary for detecting medical abnormalities. A guided GradCAM (GCAM) tuned patch neural network is applied to full-size images for anomaly localization. Therefore, the suggested approach merges the pre-trained deep CNNs with class activation mappings and area suggestion systems to construct abnormality sensors and then fine-tunes the CNNs on picture patches, focusing on medical abnormalities instead of training on whole images. A mammogram data set was used to test the deep patch classifier, which had a 99% overall classification accuracy. A Brain tumor image data set was used to test the integrateddetector’s ability to detect abnormalities, and it did so with an average precision of 0.99.

Artificial intelligence for nonmelanoma skin cancer

Nonmelanoma skin cancers (NMSCs) are among the top five most common cancers globally. NMSC is an area with great potential for novel application of diagnostic tools including artificial intelligence (AI). In this scoping review, we aimed to describe the applications of AI in the diagnosis and treatment of NMSC. Twenty-nine publications described AI applications to dermatopathology including lesion classification and margin assessment. Twenty-five publications discussed AI use in clinical image analysis, showing that algorithms are not superior to dermatologists and may rely on unbalanced, nonrepresentative, and nontransparent training data sets. Sixteen publications described the use of AI in cutaneous surgery for NMSC including use in margin assessment during excisions and Mohs surgery, as well as predicting procedural complexity. Eleven publications discussed spectroscopy, confocal microscopy, thermography, and the AI algorithms that analyze and interpret their data. Ten publications pertained to AI applications for the discovery and use of NMSC biomarkers. Eight publications discussed the use of smartphones and AI, specifically how they enable clinicians and patients to have increased access to instant dermatologic assessments but with varying accuracies. Five publications discussed large language models and NMSC, including how they may facilitate or hinder patient education and medical decision-making. Three publications pertaining to the skin of color and AI for NMSC discussed concerns regarding limited diverse data sets for the training of convolutional neural networks. AI demonstrates tremendous potential to improve diagnosis, patient and clinician education, and management of NMSC. Despite excitement regarding AI, data sets are often not transparently reported, may include low-quality images, and may not include diverse skin types, limiting generalizability. AI may serve as a tool to increase access to dermatology services for patients in rural areas and save health care dollars. These benefits can only be achieved, however, with consideration of potential ethical costs.

VeriCNN: Integrity verification of large-scale CNN training process based on zk-SNARK

Cloud environments are frequently employed to train Convolutional Neural Networks (CNNs). On the other hand, the training procedure is exposed to potential integrity threats due to the cloud’s lack of trustworthiness. Although there are now available methods for zero-knowledge proof-based training integrity verification for small models, the low-proof performance of large-scale CNNs like LeNet-5 and VGG16 makes this task challenging. To solve the training integrity verification of large-scale CNNs, this research suggests a technique called VeriCNN. Particularly, VeriCNN builds proof of integrity for CNN training using zk-SNARK. It adopts the Winograd algorithm to optimize convolution operations and introduces a high-probability matrix multiplication to optimize zero-knowledge proofs. Experimental results demonstrate the effectiveness and practicality of VeriCNN in verifying the training integrity of large-scale models. For instance, VeriCNN can generate a training integrity proof for the LeNet-5 model in just 25 s and for the VGG16 model in 390 s.

PATH-13. LEARNED RESIZING WITH EFFICIENT TRAINING (LRET) FACILITATES IMPROVED PERFORMANCE OF LARGE-SCALE BRAIN TUMOR HISTOLOGY IMAGE CLASSIFICATION MODELS

Abstract BACKGROUND Histologic examination is vital in oncology research and diagnostics. The adoption of digital scanning of whole slide images (WSI) has created an opportunity to leverage deep learning-based image classification methods to enhance diagnosis and risk stratification. However, technical limitations prevent training and deployment of accurate comprehensive multiclass deep convolutional neural networks (DCNN) models for histopathology image classification. The input dimensions of DCNN architectures are small compared to the typical pathologist field of view, degrading performance by excluding important architectural features. Furthermore, data requirements for comprehensive models are sufficiently large to overwhelm the system memory during training. METHODS A method termed Learned Resizing with Efficient Training (LRET) was developed to address the main limitations of traditional histopathology classification model training. The LRET method couples efficient training techniques with image resizing to facilitate seamless integration of larger histology image patches into state-of-the-art classification models while preserving important structural information. The LRET method was coupled with two distinct resizing techniques to train three diverse histology image datasets using five different DCNN architectures. Performance metrics were compared on cross validation and hold out test sets. RESULTS LRET-trained models were flexible to multiple input patch dimensions and DCNN models. We demonstrated performance improvement across all datasets while significantly reducing the training time and resources over traditional methods. Using a large-scale, multiclass brain tumor classification dataset consisting of 74 distinct histopathologic classes, LRET-trained models outperformed existing methods by 15-28% in accuracy, yielding 94% accuracy for the best model. CONCLUSION The LRET method for DCNN training significantly enhances the performance of large-scale multiclass histopathology image classification. The implications of this work extend to broader applications within medical imaging and beyond, where efficient integration of high-resolution images into deep learning pipelines is paramount for driving advancements research and clinical practice.

Prediction of photovoltaic power generation based on a hybrid model

In order to fully exploit the relationship between temporal features in photovoltaic power generation data and improve the prediction accuracy of photovoltaic power generation, a photovoltaic power generation forecasting method is proposed based on a hybrid model of the convolutional neural network (CNN) and extreme gradient boost (XGBoost). Taking the historical data of China’s photovoltaic power plants as a sample, the high-dimensional mapping relationship of photovoltaic power generation variables is extracted based on the convolutional layer and pooling layer of the CNN network to construct a high-dimensional time-series feature vector, which is an input for the XGBoost. A photovoltaic power generation prediction model is established based on CNN-XGBoost by training CNN and XGBoost parameters. Since it is difficult for a single model to achieve optimal prediction accuracy under different weather conditions, the k-means clustering algorithm is used to group the power datasets and train independent models to improve prediction accuracy. Through the actual data verification of photovoltaic power plants, the proposed photovoltaic power generation prediction model can accurately predict the power, which shows high prediction accuracy and generalization ability compared with other methods.