Parameters Of Convolutional Neural Network Research Articles

Oral cancer detection using convolutional neural network optimized by combined seagull optimization algorithm

Early diagnosis of oral cancer is crucial for improving patient outcomes and saving lives. However, inaccurate and improper diagnosis can hinder effective treatment. This paper presents a novel method for detecting oral cancer using an optimized version of Convolutional Neural Network (CNN). While basic CNNs have been widely used for image classification tasks, the incorporation of the Seagull Optimization Algorithm and Particle Swarm Optimization Algorithm in optimizing the CNN architecture specifically for oral cancer detection is a unique approach that is provided in this study. By combining these algorithms, the proposed method optimizes the CNN's architecture, parameters, and training process specifically for oral cancer detection. This optimization enhances the performance and accuracy of the CNN in identifying cancerous regions in oral images. Unlike previous approaches, our method incorporates advanced image processing techniques, including noise reduction, contrast enhancement, and data augmentation, to enhance the quality of input data extracted from the Oral Cancer (Lips and Tongue) images (OCI) dataset. The optimized CNN architecture uses its ability to learn intricate patterns and features from the enhanced images, enabling more accurate identification of cancerous regions. To evaluate the effectiveness of our approach, we compare it against Textural analysis, FCM, CNN, R-CNN, and ResNet-101 using four measurement indices. Results demonstrate that our proposed CSOA-based CNN system achieves the highest accuracy rate (96.94%) compared to other methods, indicating its superior performance in oral cancer detection. Furthermore, our precision rate of 94.65% and recall rate of 91.60% highlight the model's high correctness and positive classification ability. Finally, our proposed method achieves the highest F1-score (88.55%), emphasizing its superiority over other comparative methods. Through our innovative integration of the Seagull Optimization Algorithm and Particle Swarm Optimization Algorithm with CNN, coupled with advanced image processing techniques, we provide a reliable and effective solution for early detection of oral cancer.

Convolutional neural network-multi-kernel radial basis function neural network-salp swarm algorithm: a new machine learning model for predicting effluent quality parameters.

A wastewater treatment plant (WWTP) is an essential part of the urban water cycle, which reduces concentration of pollutants in the river. For monitoring and control of WWTPs, researchers develop different models and systems. This study introduces a new deep learning model for predicting effluent quality parameters (EQPs) of a WWTP. A method that couples a convolutional neural network (CNN) with a novel version of radial basis function neural network (RBFNN) is proposed to simultaneously predict and estimate uncertainty of data. The multi-kernel RBFNN (MKRBFNN) uses two activation functions to improve the efficiency of the RBFNN model. The salp swarm algorithm is utilized to set the MKRBFNN and CNN parameters. The main advantage of the CNN-MKRBFNN-salp swarm algorithm (SSA) is to automatically extract features from data points. In this study, influent parameters (if) are used as inputs. Biological oxygen demand (BODif), chemical oxygen demand (CODif), total suspended solids (TSSif), volatile suspended solids (VSSif), and sediment (SEDef) are used to predict EQPs, including CODef, BODef, and TSSef. At the testing level, the Nash-Sutcliffe efficiencies of CNN-MKRBFNN-SSA are 0.98, 0.97, and 0.98 for predicting CODef, BODef, and TSSef. Results indicate that the CNN-MKRBFNN-SSA is a robust model for simulating complex phenomena.

Expression-Guided Deep Joint Learning for Facial Expression Recognition.

In recent years, convolutional neural networks (CNNs) have played a dominant role in facial expression recognition. While CNN-based methods have achieved remarkable success, they are notorious for having an excessive number of parameters, and they rely on a large amount of manually annotated data. To address this challenge, we expand the number of training samples by learning expressions from a face recognition dataset to reduce the impact of a small number of samples on the network training. In the proposed deep joint learning framework, the deep features of the face recognition dataset are clustered, and simultaneously, the parameters of an efficient CNN are learned, thereby marking the data for network training automatically and efficiently. Specifically, first, we develop a new efficient CNN based on the proposed affinity convolution module with much lower computational overhead for deep feature learning and expression classification. Then, we develop an expression-guided deep facial clustering approach to cluster the deep features and generate abundant expression labels from the face recognition dataset. Finally, the AC-based CNN is fine-tuned using an updated training set and a combined loss function. Our framework is evaluated on several challenging facial expression recognition datasets as well as a self-collected dataset. In the context of facial expression recognition applied to the field of education, our proposed method achieved an impressive accuracy of 95.87% on the self-collected dataset, surpassing other existing methods.

Optimizing Deep Learning Model Parameters Using Socially Implemented IoMT Systems for Diabetic Retinopathy Classification Problem

Diabetic retinopathy (DR) is on the increase nowadays due to the high sugar level in the blood, and it is the reason for blindness that mainly occurs in middle-aged people. Furthermore, the Internet of Medical Things (IoMT) enabled computer-aided diagnostic (CAD) systems record DR-related data online and give patients with reassuring information. The internet allows for the interconnection of a variety of smart devices, enabling remote healthcare systems based on the IoMT to link patients with medical professionals. The proper diagnosis of diabetic patients and detection of DR severity in earlier stages help in preventing blindness. Therefore, the basic aim of this study is to prevent the diabetic patient from losing vision by detecting and classifying the severity of DR fundus images using the IoMT-enabled CAD system. This article designed a novel diabetic retinopathy classification (DRC) system by hybridizing the DL model with optimization algorithms to classify the DR images based on severity. This system begins with preprocessing phase for removing the noise from edges. Next, the proposed K-mean cluster-based growing region segmentation is employed to extract the useful region from the images. Then, pretrained convolutional neural network (CNN) model, i.e., RESnet with the proposed hybrid genetic and ant colony optimization (HGACO) algorithm, is applied to extract the features from the region of interest (ROI) and classify them into four severity levels. Performance indices such as AUC, <inline-formula xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink"> <tex-math notation="LaTeX">$F$</tex-math> </inline-formula> -measure, accuracy, sensitivity, and specificity are analyzed to evaluate the performance on MESSIDOR dataset. The performance of the proposed DRC system is compared with state-of-the-art classification systems. The proposed HGACO algorithm is also compared with Adam and gradient descent (GD) optimizers. The system is also evaluated by employing different parameters of CNN and HGACO. Additionally, for the determination of the classification accuracy of the DRC system, the confidence interval statistical test is implemented considering various parameters and configurations of the neural network. The results revealed that the proposed DR system provides higher classification results by achieving 95.78%, 91.98%, 97.7%, and 94.56% AUC, sensitivity, accuracy, and specificity rate, respectively. CNN alleviates the difficulty of developing image features, whereas the HGACO algorithm-based technique automates CNN hyperparameter design.

A Single-Ended Fault Location Method for Transmission Line Based on Full Waveform Features Extractions of Traveling Waves

Conventional single-ended traveling wave fault location methods, which commonly depend on partial features of traveling wavefronts, may lead to fault location failure, especially for weak-signal faults such as high impedance or zero-crossing faults and close-in faults. To tackle it, this paper presents a fault location method according to the extracted panoramic features of traveling wave full waveform (TWFW) in time-frequency domains. Firstly, two rules of the TWFW features are probed, that is, the wavefront arrival sequence is varied from fault sections, as well as the frequency distribution of wavefronts is strongly related to the precise fault distance. Ergo, the mapping relationships between the TWFW and fault distance are qualitatively confirmed in order to demonstrate the uniqueness of the TWFW subsequently. Next, a LeNet-5-based convolution neural network (CNN) model is constructed to quantitatively evaluate such mapping relationships. In this model, various TWFW features will be extracted to the convolution channels when the CNN parameters are optimized adaptively, and the mapping relations can be formed in light of these sensitive features to estimate the fault distance. Finally, a Grad-CAM visualization method is deployed in the case study, and the accuracy along with the robustness of the proposed method in various fault conditions can be validated consequently.

Texture-driven super-resolution of ultrasound images using optimized deep learning model

ABSTRACT While comparing to the additional medical imaging modalities, the low resolution (LR) with poor quality images are obtained because of natural intrinsic imaging characteristics. We proposed a novel deep learning- based super-resolution of ultrasound images that are texture-driven. In this study, Convolutional Neural Networks (CNNs) are used to speed up the process to increase the image quality. Additionally, the Dwarf Mongoose Optimization (DMO) method is used to adjust the parameters of CNN thereby improving the quality of the image resolutions. The textures of the super-resolution images are examined with the Histogram of Oriented Gradients (HOG). The experimental works are handled using python software. Super-resolution per second and PSNR/dB values for the proposed model are 0.289 and 42.340, respectively. This model also offers FSO, GMSD, MAD, and MSSIM values of 0.9712, 0.013, 0.9802, and 0.9832 which is relatively higher than the existing techniques.

Learning from Projection to Reconstruction: A Deep Learning Reconstruction Framework for Sparse-View Phase Contrast Computed Tomography via Dual-Domain Enhancement

Phase contrast computed tomography (PCCT) provides an effective non-destructive testing tool for weak absorption objects. Limited by the phase stepping principle and radiation dose requirement, sparse-view sampling is usually performed in PCCT, introducing severe artifacts in reconstruction. In this paper, we report a dual-domain (i.e., the projection sinogram domain and image domain) enhancement framework based on deep learning (DL) for PCCT with sparse-view projections. It consists of two convolutional neural networks (CNN) in dual domains and the phase contrast Radon inversion layer (PCRIL) to connect them. PCRIL can achieve PCCT reconstruction, and it allows the gradients to backpropagate from the image domain to the projection sinogram domain while training. Therefore, parameters of CNNs in dual domains are updated simultaneously. It could overcome the limitations that the enhancement in the image domain causes blurred images and the enhancement in the projection sinogram domain introduces unpredictable artifacts. Considering the grating-based PCCT as an example, the proposed framework is validated and demonstrated with experiments of the simulated datasets and experimental datasets. This work can generate high-quality PCCT images with given incomplete projections and has the potential to push the applications of PCCT techniques in the field of composite imaging and biomedical imaging.

Classification of unexposed potsherd cavities by using deep learning

The aim of the Deep Research for Akkon project is to use machine-learning techniques, specifically convolutional neural networks (CNNs), to analyze the large corpus of archaeological pottery fragments belonging to the Late Jomon period (ca. 4000 to 3200 aBP) in a non-invasive and non-destructive manner. In Japan, recent research conducted by using the ”impression method” revealed that ceramic vessels belonging to that era contain impressions of plant seeds. Studying these impressions allows archaeologists to better understand the cultural practices of the Jomon people and the path of rice diffusion in Japan. Most of the analysis was conducted by visually inspecting X-ray images. However, results based on using only X-rays are often inconclusive, leading researchers to use other invasive techniques that damage the potsherds. In this paper, we present a method that classifies X-ray images of potsherds by using deep learning. A dataset composed of 1036 images with seven classes was used to evaluate our approach. We generated different models using different CNN architectures and parameters and analyzed them separately. Then, we applied techniques such as ensemble and test-time augmentation to evaluate how such techniques impact our model. The best result was obtained by combining EfficientNetB7 trained with different parameters, achieving a classification rate of 90%.

Unsupervised Segmentation of Muscle Precursor Cell Images In Situ

In vitro culture of muscle stem cells on a large scale could bring light to the treatment of muscle-related diseases. However, the current work related to muscle stem cell culture is still only performed in specialized biological laboratories that are very much limited by manual experience. There are still some difficulties to achieve an automated culture of complex morphological cells in terms of live cell observation and morphological analysis. In this paper, a set of bright-field cell in situ imaging devices is designed to perform non-contact and invasive imaging of muscle precursor cells in vitro, and a neural network structured lightweight unsupervised semantic segmentation algorithm is proposed for the acquired images to achieve online extraction of cell regions of interest without manual annotation and pre-training. The algorithm first uses a graph-based super-pixel segmentation to obtain a coarse segmentation, then aggregates the coarse segmentation results with the help of Laplace operators as a reference to a four-layer convolutional neural network (CNN). The CNN parameters learn to refine the boundaries of the cells which helps the final segmentation accuracy and mean intersection–merge ratio reach 88% and 77%, respectively.

Person-Specific Gaze Estimation from Low-Quality Webcam Images.

Gaze estimation is an established research problem in computer vision. It has various applications in real life, from human-computer interactions to health care and virtual reality, making it more viable for the research community. Due to the significant success of deep learning techniques in other computer vision tasks-for example, image classification, object detection, object segmentation, and object tracking-deep learning-based gaze estimation has also received more attention in recent years. This paper uses a convolutional neural network (CNN) for person-specific gaze estimation. The person-specific gaze estimation utilizes a single model trained for one individual user, contrary to the commonly-used generalized models trained on multiple people's data. We utilized only low-quality images directly collected from a standard desktop webcam, so our method can be applied to any computer system equipped with such a camera without additional hardware requirements. First, we used the web camera to collect a dataset of face and eye images. Then, we tested different combinations of CNN parameters, including the learning and dropout rates. Our findings show that building a person-specific eye-tracking model produces better results with a selection of good hyperparameters when compared to universal models that are trained on multiple users' data. In particular, we achieved the best results for the left eye with 38.20 MAE (Mean Absolute Error) in pixels, the right eye with 36.01 MAE, both eyes combined with 51.18 MAE, and the whole face with 30.09 MAE, which is equivalent to approximately 1.45 degrees for the left eye, 1.37 degrees for the right eye, 1.98 degrees for both eyes combined, and 1.14 degrees for full-face images.

DASECount: Domain-Agnostic Sample-Efficient Wireless Indoor Crowd Counting via Few-Shot Learning

Accurate indoor crowd counting (ICC) is a key enabler to many smart home/office applications. Recent development of the WiFi-based ICC technology relies on detecting the variation of wireless channel state information (CSI) caused by human motions and has gained increasing popularity due to its low hardware cost, reliability under all lighting conditions, and privacy preservation in sensing data processing. To attain high estimation accuracy, existing WiFi-based ICC methods often require a large amount of labeled CSI training data samples for each application domain, i.e., a particular WiFi transceiver or background deployment. This makes large-scale deployment of the WiFi-based ICC technology across dissimilar domains extremely difficult and costly. In this article, we propose a Domain-Agnostic and Sample-Efficient wireless indoor crowd Counting (DASECount) framework that suffices to attain robust cross-domain detection accuracy given very limited data samples in new domains. DASECount leverages the wisdom of the few-shot learning (FSL) paradigm consisting of two major stages: 1) source domain meta training and 2) target domain meta testing. Specifically, in the meta-training stage, we design and train two separate convolutional neural network (CNN) modules on the source domain data set to fully capture the implicit amplitude and phase features of CSI measurements related to human activities. A subsequent knowledge distillation procedure is designed to iteratively update the CNN parameters for better generalization performance. In the meta-testing stage, we use the partial CNN modules to extract low-dimension features out of the high-dimension input target domain CSI data. With the obtained low-dimension CSI features, we can even use very few amounts of target domain data samples (e.g., 5-shot samples) to train a lightweight logistic regression (LR) classifier, and attain very high cross-domain ICC accuracy. Experiment results show that the proposed DASECount method achieves over 92.68%, and on average 96.37% detection accuracy in a 0–8 people counting task under various domain setups, which significantly outperforms the other representative benchmark methods considered.

FSConv: Flexible and separable convolution for convolutional neural networks compression

Because of limited computation resources, convolutional neural networks (CNNs) are difficult to deploy on mobile devices. To overcome this issue, many methods have successively reduced parameters in CNNs with the idea of removing redundancy among feature maps. We observe similarities between feature maps at the same layer but not complete consistency. Intuitively, the difference between similar feature maps is an essential ingredient for the success of CNNs. Therefore, we propose a flexible and separable convolution (FSConv) in a different perspective to embrace redundancy while requiring less computation, which can implicitly cluster feature maps into different clusters without introducing similarity measurements. Our proposed model extracts intrinsic information from the representative part through ordinary convolution in each cluster and reveals tiny hidden details from the redundant part through groupwise/depthwise convolution. Experimental results demonstrate that FSConv-equipped networks always perform better than previous state-of-the-art CNNs compression algorithms. Code is available at https://github.com/Clarkxielf/FSConv-Flexible-and-Separable-Convolution-for-Convolutional-Neural-Networks-Compression.

Smart evaluation for deep learning model: churn prediction as a product case study

Customer churn prediction recently is one of the vital issues that confronts diverse business industries to sustain the customers base and profits. On the other hand, data scientists employ gigantic customer data to automate the data modelling process to offer these models as a generally portable service. This research has two main contributions: deep learning customer churn prediction model and smart evaluation prediction model service. So, this service harnesses any customer data to automate building, evaluation, and deployment of the churn prediction model. The research consists of three main parts. Firstly, it illustrates the dataset labelling which annotates customers data into churn or non-churn. Secondly, the deep learning churn prediction framework using convolutional neural network (CNN) algorithm. Finally, a case study is presented to show how churn prediction service is automatically trained and generated based on real customer data, where CNN parameters are adapted to achieve the most reliable performance in line with customers' behavior. The applied case study achieves accuracy 0.77, area under the curve (AUC) 0.84 and f1 score 0.83.

Deep-learning convolutional neural network-based scatter correction for contrast enhanced digital breast tomosynthesis in both cranio-caudal and mediolateral-oblique views.

Scatter radiation in contrast-enhanced digital breast tomosynthesis (CEDBT) reduces the image quality and iodinated lesion contrast. Monte Carlo simulation can provide accurate scatter estimation at the cost of computational burden. A model-based convolutional method trades off accuracy for processing speed. The purpose of this study is to develop a fast and robust deep-learning (DL) convolutional neural network (CNN)-based scatter correction method for CEDBT. Projection images and scatter maps of digital anthropomorphic breast phantoms were generated using Monte Carlo simulations. Experiments were conducted to validate the simulated scatter-to-primary ratio (SPR) at different locations of a breast phantom. Simulated projection images were used for CNN training and testing. Two separate U-Nets [low-energy (LE)-CNN and high-energy (HE)-CNN] were trained for LE and HE spectrum, respectively. CNN-based scatter correction was applied to a clinical case with a malignant iodinated mass to evaluate the influence on the lesion detection. The average and standard deviation of mean absolute percentage error of LE-CNN and HE-CNN estimated scatter map are and , respectively. For clinical cases, the lesion signal difference to noise ratio average improvement was 190% after CNN-based scatter correction. To conduct scatter correction on clinical CEDBT images, the whole process of loading CNNs parameters and scatter correction for LE and HE images took , with 9GB GPU computational cost. The SPR variation across the breast agrees between experimental measurements and Monte Carlo simulations. We developed a CNN-based scatter correction method for CEDBT in both CC view and mediolateral-oblique view with high accuracy and fast speed.

Joint Cardiac T1 Mapping and Cardiac Cine Using Manifold Modeling

The main focus of this work is to introduce a single free-breathing and ungated imaging protocol to jointly estimate cardiac function and myocardial T1 maps. We reconstruct a time series of images corresponding to k-space data from a free-breathing and ungated inversion recovery gradient echo sequence using a manifold algorithm. We model each image in the time series as a non-linear function of three variables: cardiac and respiratory phases and inversion time. The non-linear function is realized using a convolutional neural networks (CNN) generator, while the CNN parameters, as well as the phase information, are estimated from the measured k-t space data. We use a dense conditional auto-encoder to estimate the cardiac and respiratory phases from the central multi-channel k-space samples acquired at each frame. The latent vectors of the auto-encoder are constrained to be bandlimited functions with appropriate frequency bands, which enables the disentanglement of the latent vectors into cardiac and respiratory phases, even when the data are acquired with intermittent inversion pulses. Once the phases are estimated, we pose the image recovery as the learning of the parameters of the CNN generator from the measured k-t space data. The learned CNN generator is used to generate synthetic data on demand by feeding it with appropriate latent vectors. The proposed approach capitalizes on the synergies between cine MRI and T1 mapping to reduce the scan time and improve patient comfort. The framework also enables the generation of synthetic breath-held cine movies with different inversion contrasts, which improves the visualization of the myocardium. In addition, the approach also enables the estimation of the T1 maps with specific phases, which is challenging with breath-held approaches.

Improving training efficiency for scalable automated fault detection and diagnosis in chilled water plants by transfer learning

Automated fault detection and diagnosis (AFDD) is crucial for improving the energy efficiency of air conditioning systems, and its quantitative effects have become clearer in recent years. Although many AFDD methods are proposed in the literature, there is insufficient research on their scalability to different systems. The authors previously proposed an AFDD method using a fault dataset created by simulation that can be used to train convolutional neural network (CNN); however, this AFDD method is difficult to apply to different systems because it requires significant computation time to generate a fault dataset by simulation and train the CNN. In this study, we focused on transfer learning and examined whether reducing the size of a fault dataset and re-training a CNN with only some parameters of the originally-trained CNN would reduce the computation time and make training more efficient. Specifically, we ran simulations, calculated the fault dataset, trained the CNN, and applied transfer learning using two real chilled-water plants. As a result, it was confirmed that by reducing the fault dataset by a certain amount and the limiting the number of epochs for re-training, it is possible to achieve reasonable diagnostic performance while reducing the computation time to less than half compared to our previous method. This study also has value in that it examined the application of transfer learning using multiple real systems.

EKConv: Compressing Convolutional Neural Networks with Evolutionary Kernel Convolution

Convolutional neural networks (CNNs) have achieved tremendous success in visual recognition tasks but mainly rely on massive learnable parameters. To solve this problem, many effective and efficient convolution operators have been proposed, such as group-wise convolution, point-wise convolution, and depth-wise convolution. However, the above convolution operations model and optimize the weight relationship within the same convolutional layer. To reduce the network parameters, we explicitly construct the relationship between convolution kernels of adjacent layers. Specifically, we propose an evolutionary kernel convolution, namely EKConv, to generate weight parameters by group-wise convolution efficiently. In particular, EKConv makes the kernel parameters of the current convolutional layer inherit from its preceding adjacent kernel, which promotes the information exchange between convolution kernels. More importantly, EKConv is a novel plug-and-play module that can be easily embedded into mainstream CNNs. Extensive experimental results show that EKConv can compress the parameters of CNNs by a large margin yet barely sacrifice image classification performance.

Optimizing CNN‐LSTM hybrid classifier using HCA for biomedical image classification

AbstractIn medical science, imaging is the most effective diagnostic and therapeutic tool. Almost all modalities have transitioned to direct digital capture devices, which have emerged as a major future healthcare option. Three diseases such as Alzheimer's (AD), Haemorrhage (HD), and COVID‐19 have been used in this manuscript for binary classification purposes. Three datasets (AD, HD, and COVID‐19) were used in this research out of which the first two, that is, AD and HD belong to brain Magnetic Resonance Imaging (MRI) and the last one, that is, COVID‐19 belongs to Chest X‐Ray (CXR) All of the diseases listed above cannot be eliminated, but they can be slowed down with early detection and effective medical treatment. This paper proposes an intelligent method for classifying brain (MRI) and CXR images into normal and abnormal classes for the early detection of AD, HD, and COVID‐19 based on an ensemble deep neural network (DNN). In the proposed method, the convolutional neural network (CNN) is used for automatic feature extraction from images and long‐short term memory (LSTM) is used for final classification. Moreover, the Hill‐Climbing Algorithm (HCA) is implemented for finding the best possible value for hyper parameters of CNN and LSTM, such as the filter size of CNN and the number of units of LSTM while fixing the other parameters. The data‐set is pre‐processed (resized, cropped, and noise removed) before feeding the train images to the proposed models for accurate and fast learning. Forty‐five MR images of AD, Sixty MR images of HD, and 600 CXR images of COVID‐19 were used for testing the proposed model ‘CNN‐LSTM‐HCA’. The performance of the proposed model is evaluated using six types of statistical assessment metrics such as; Accuracy, Sensitivity, Specificity, F‐measure, ROC, and AUC. The proposed model compared with the other three types of hybrid models such as CNN‐LSTM‐PSO, CNN‐LSTM‐Jaya, and CNN‐LSTM‐GWO and also with state‐of‐art techniques. The overall accuracy of the proposed model received was 98.87%, 85.75%, and 99.1% for COVID‐19, Haemorrhage, and Alzheimer's data sets, respectively.

Deep learning for skillful long-lead ENSO forecasts

El Niño-Southern Oscillation (ENSO) is one of the fundamental drivers of the Earth's climate variability. Thus, its skillful prediction at least a few months to years ahead is of utmost importance to society. Using both dynamical and statistical methods, several studies reported skillful ENSO predictions at various lead times. Predictions with long lead times, on the other hand, remain difficult. In this study, we propose a convolutional neural network (CNN)-based statistical ENSO prediction system with heterogeneous CNN parameters for each season with a modified loss function to predict ENSO at least 18–24 months ahead. The developed prediction system indicates that the CNN model is highly skillful in predicting ENSO at long lead times of 18–24 months with high skills in predicting extreme ENSO events compared with the Scale Interaction Experiment-Frontier ver. 2 (SINTEX-F2) dynamical system and several other statistical prediction systems. The analysis indicates that the CNN model can overcome the spring barrier, a major hindrance to dynamical prediction systems, in predicting ENSO at long lead times. The improvement in the prediction skill can partly be attributed to the heterogeneous parameters of seasonal CNN models used in this study and also to the use of a modified loss function in the CNN model. In this study, we also attempted to identify various precursors to ENSO events using CNN heatmap analysis.

RBEBT: A ResNet-Based BA-ELM for Brain Tumor Classification

Brain tumor refers to the formation of abnormal cells in the brain. It can be divided into benign and malignant. The main diagnostic methods for brain tumors are plain X-ray film, Magnetic resonance imaging (MRI), and so on. However, these artificial diagnosis methods are easily affected by external factors. Scholars have made such impressive progress in brain tumors classification by using convolutional neural network (CNN). However, there are still some problems: (i) There are many parameters in CNN, which require much calculation. (ii) The brain tumor data sets are relatively small, which may lead to the overfitting problem in CNN. In this paper, our team proposes a novel model (RBEBT) for the automatic classification of brain tumors. We use fine-tuned ResNet18 to extract the features of brain tumor images. The RBEBT is different from the traditional CNN models in that the randomized neural network (RNN) is selected as the classifier. Meanwhile, our team selects the bat algorithm (BA) to optimize the parameters of RNN. We use five-fold cross-validation to verify the superiority of the RBEBT. The accuracy (ACC), specificity (SPE), precision (PRE), sensitivity (SEN), and F1-score (F1) are 99.00%, 95.00%, 99.00%, 100.00%, and 100.00%. The classification performance of the RBEBT is greater than 95%, which can prove that the RBEBT is an effective model to classify brain tumors.