A 3D CNN-LSTM-Based Image-to-Image Foreground Segmentation

Online leakage current classification using convolutional neural network long short-term memory for high voltage insulators on web-based service

Early and accurate detection of retinal pathologies is critical for preventing vision loss and enabling timely clinical intervention. Traditional computer vision techniques, such as thresholding, edge detection, morphological filtering, and Hough transforms, have long been used to extract features from retinal fundus images, yet their performance is often constrained by image variability and complex pathological presentations. This study presents a hybrid deep learning architecture that integrates Convolutional Neural Networks (CNNs) for image-based classification with Recurrent Neural Networks (RNNs), specifically Long Short-Term Memory (LSTM) units, to model geometric and anatomical features derived from classical methods. This architecture allows for the fusion of pixel-level deep features with clinically interpretable descriptors, including optic disc-fovea distance, lesion spatial distribution, and vessel curvature sequences. Comparative analysis demonstrates that the proposed hybrid model achieves superior diagnostic accuracy, reaching 97%, significantly outperforming both conventional image processing approaches and CNN-only baselines. The results indicate that incorporating structured domain knowledge into neural models improves both performance and interpretability, offering a robust framework for real-world retinal disease screening applications.

Deep learning models, particularly one‐dimensional convolutional neural networks (1D CNNs), have shown great potential in the fault diagnosis of rotating machines. However, standard 1D CNNs face challenges in capturing long‐term dependencies in time series data. To overcome this, various studies have proposed hybrid models that combine 1D CNN with long short‐term memory (LSTM) networks. Despite these improvements, current 1D CNN‐LSTM methods still encounter issues such as low diagnostic accuracy, limited adaptability to changing conditions, poor generalization, and difficulty detecting compound faults. In response to these issues, this paper presents an improved hybrid fault diagnosis method based on a combination of 1D CNN and LSTM for rotating machines. In this approach, the 1D CNN extracts meaningful features from raw vibration data, which are then processed by the LSTM to model long‐term dependencies within the feature set. The experimental results show diagnosis accuracies of 99.57% for bearing data and 99.15% for the gearbox data, outperforming existing methods. These findings support the practical applicability of the proposed 1D CNN‐LSTM in real‐world industrial applications.

Depth image-based rendering (DIBR) has recently received significant attention as an efficient concept for generating virtual views. One of the main challenges in the view synthesis process is that holes will appear in the background (BG) of the virtual views because of occlusion. The existing methods either utilize spatial or temporal information from the original views and depth maps to fill the holes. However, the performance of the existing methods is seriously affected by the quality of the depth maps. Foreground (FG) texture will be wrongly introduced to the BG when the depth maps are not accurate enough. We develop a hole-filling approach for DIBR based on convolutional neural network, which shows reduced dependency on the quality of the depth map. More specifically, FG objects are detected on the RGB image by combining the Laplacian operator with a graph cut algorithm to avoid dependencies on the depth map quality. Furthermore, we learn an end-to-end mapping between the warped virtual view and the ground-truth view image with FG awareness. The learning-based approach exhibits excellent superiority in terms of saving time. The experimental results also show that the proposed approach outperforms current state-of-the-art techniques quantitatively and qualitatively.

COVID-19 pandemic has indeed plunged the global community especially African countries into an alarming difficult situationculminating into a great deal amounts of catastrophes such as economic recession, political instability and loss of jobs. Thepandemic spreads exponentially and causes loss of lives. Following the outbreak of the omicron new variant of concern,forecasting and identification of the COVID-19 infection cases is very vital for government at various levels. Hence, havingknowledge of the spread at a particular point in time, swift actions can be taken by government at various levels with a view toaccordingly formulate new policies and modalities towards minimizing the trajectory of the consequences of COVID-19 pandemicto both public health and economic sectors. Here, a potent combination of Convolutional Neural Network (CNN) learning algorithm along with Long Short Term Memory(LSTM) learning algorithm has been proposed in this work in order to produce a hybrid of a deep learning algorithm ConvolutionalNeural Network - Long Short Term Memory (CNN-LSTM) for forecasting COVID-19 infection cases particularly in Nigeria, SouthAfrica and Botswana. Forecasting models for COVID-19 infection cases in Nigeria, South Africa and Botswana, were developedfor 10 days using deep learning-based approaches namely CNN, LSTM and CNN-LSTM deep learning algorithm respectively. The models were evaluated on the basis of four standard performance evaluation metrics which include accuracy, MSE, MAEand RMSE respectively. However, the CNN-LSTM deep learning-based forecasting model achieved the best accuracy of98.30%, 97.60%, and 97.74% for Nigeria, South Africa and Botswana respectively; and in the same manner, achieved lesserMSE, MAE and RMSE values compared to models developed with CNN and LSTM respectively. Taken together, the CNN-LSTM deep learning-based forecasting model for COVID-19 infection cases in Nigeria, South Africaand Botswana dramatically surpasses the two other DL based forecasting models (CNN and LSTM) for COVID-19 infectioncases in Nigeria, South Africa and Botswana in terms of not only the best accuracy of with 98.30%, 97.60%, and 97.74% but alsoin terms of lesser MSE, MAE and RMSE.

IoT systems face vulnerabilities due to their data processing requirements and resource constraints. With 13 billion connected devices globally, this research investigates the economic viability of AI-based intrusion detection systems (IDSs), specifically analyzing the automation costs of implementing a Convolutional Neural Network (CNN) with Long Short-Term Memory (LSTM) for classifying malicious sensor traffic. This study introduces an innovative framework that evaluates six distinct architectural components of CNN and LSTM: image input processing, convolutional layer operations, max pooling layer functionality, fully connected layer characteristics, softmax output activation, and class determination mechanisms. The framework employs six metrics: matrix size, feature vector number, input vector size, output vector size, and number of runs for dual data points. Experiments on the IoT-23 dataset showed our proposed CNN model outperformed LSTM, achieving 93% accuracy for binary classification and 96% for multi-class classification. The trained CNN demonstrated predictable resource utilization with increasing classification complexity, providing a framework for quantifying IoT IDS costs. The proposed framework provides a systematic methodology for evaluating machine learning classifiers in IoT environments, using quantitative metrics to assess implementation and operational costs, enabling data-driven selection of optimal security solutions based on specific deployment constraints.

This research aims to implement deep learning techniques to determine fact and fake news in Indonesian language. The methods used are Convolutional Neural Network (CNN) and Long Short Term Memory (LSTM). The stages of the research consisted of collecting data, labeling data, preprocessing data, word embedding, splitting data, forming CNN and LSTM models, evaluating, testing new input data and comparing evaluations of the established CNN and LSTM models. The Data are collected from a fact and fake news provider site that is valid, namely TurnbackHoax.id. There are 1786 news used in this study, with 802 fact and 984 fake news. The results indicate that the CNN and LSTM methods were successfully applied to determine fact and fake news in Indonesian language properly. CNN has an accuracy test, precision and recall value of 0.88, while the LSTM model has an accuracy test and precision value of 0.84 and a recall of 0.83. In testing the new data input, all of the predictions obtained by CNN are correct, while the prediction results obtained by LSTM have 1 wrong prediction. Based on the evaluation results and the results of testing the new data input, the model produced by the CNN method is better than the model produced by the LSTM method.

Retailers need good-quality product images with clear background on their Web sites. Most of these product images captured have diverse backgrounds, posing a challenge to separate the foreground from the background along with the enhancement of the product image. Currently, most of these activities are done manually. Our study proposes a computer vision (CV)- and machine learning (ML)-based approach to separate foreground (FG) and background (BG) from retail product images and enhance them. This automated process of BG/FG extraction involves two steps. A neural network (NN) classifier to identify if the BG has a monocolor gradient or not, followed by the separation of FG from BG and enhancement applied on the FG from the input image. Our results show 91% accuracy for BG/FG extraction and identifying the product region of interest (ROI).

In this paper, we propose an emotion recognition model based on convolutional neural network (CNN), long short term memory (LSTM) and channel attention mechanism, aiming at the low classification accuracy of machine learning methods and the uneven spatial distribution of electroencephalogram (EEG) electrodes. This model can effectively integrate the frequency, space and time information of EEG signals, and improve the accuracy of emotion recognition by adding channel attention mechanism after the last convolutional layer of the model. Firstly, construct a 4-dimensional structure representing EEG signals. Then, a CLSTM model structure combining CNN and LSTM is designed. CNN is used to extract frequency and spatial information from 4-dimensional input, and LSTM is used to extract time information. Finally, the channel attention module is added after the last convolutional layer of CLSTM model structure to allocate the weight of different electrodes. In this paper, an emotion recognition model based on CLSTM and channel attention mechanism was proposed from the perspective of integrating the frequency, space and time 3-dimensional information of EEG signals. The average classification accuracy of the model on SEED public data set reached 93.36%, which was significantly improved over the existing CNN and LSTM emotion recognition models.

In this paper, a software comparative analysis of two neural network models is presented, namely, Convolutional Neural Network (CNN), and Long Short Term Memory (LSTM) neural network. The evaluation is performed using the famous deep learning database the “MNIST” to check the accuracy, model size, speed and complexity of the two models for future digital realization on reconfigurable hardware. In addition to that, we optimize the size of the two models by quantizing the weights width to 8-bits instead of 32-bits. The results show an extensive reduction in the size of each model (by 10X) with a slight drop in the accuracy. The results also show that the CNN is more accurate and much faster than LSTMs making it the best model to be implemented on reconfigurable hardware.

In motion compensated frame interpolation (MCFI), an interpolated frame is produced by placing objects according to their motion estimated between two neighbouring frames. However, multiple motion vectors associated with the background (BG) and foreground (FG) objects can pass through a single location in the interpolated frame. In such motion ambiguity (MA) regions, annoying artefacts can be induced by adopting the motion of the BG object instead of the FG object. Introduced is a novel MCFI algorithm which can accurately infer the motion of the FG object at the MA region with low complexity. Simulation results show that the proposed method achieves higher visual quality for the interpolated frame without annoying artefacts as compared with conventional MCFI algorithms.

Improving the performance of Deep Learning (DL) algorithms is a challenging problem. However, DL is applied to different types of Deep Neural Networks, and Long Short-Term Memory (LSTM) is one of them that deals with time series or sequential data. This paper attempts to overcome this problem by optimizing LSTM parameters using the Bees Algorithm (BA), which is a nature-inspired algorithm that mimics the foraging behavior of honey bees. In particular, it was used to optimize the adjustment factors of the learning rate in the forget, input, and output gates, in addition to cell candidate, in both forward and backward sides. Furthermore, the BA was used to optimize the learning rate factor in the fully connected layer. In this study, artificial porosity images were used for testing the algorithms; since the input data were images, a Convolutional Neural Network (CNN) was added in order to extract the features in the images to feed into the LSTM for predicting the percentage of porosity in the sequential layers of artificial porosity images that mimic real CT scan images of products manufactured by the Selective Laser Melting (SLM) process. Applying a Convolutional Neural Network Long Short-Term Memory (CNN-LSTM) yielded a porosity prediction accuracy of 93.17%. Although using Bayesian Optimization (BO) to optimize the LSTM parameters mentioned previously did not improve the performance of the LSTM, as the prediction accuracy was 93%, adding the BA to optimize the same LSTM parameters did improve its performance in predicting the porosity, with an accuracy of 95.17% where a hybrid Bees Algorithm Convolutional Neural Network Long Short-Term Memory (BA-CNN-LSTM) was used. Furthermore, the hybrid BA-CNN-LSTM algorithm was capable of dealing with classification problems as well. This was shown by applying it to Electrocardiogram (ECG) benchmark images, which improved the test set classification accuracy, which was 92.50% for the CNN-LSTM algorithm and 95% for both the BO-CNN-LSTM and BA-CNN-LSTM algorithms. In addition, the turbofan engine degradation simulation numerical dataset was used to predict the Remaining Useful Life (RUL) of the engines using the LSTM network. A CNN was not needed in this case, as there was no feature extraction for the images. However, adding the BA to optimize the LSTM parameters improved the prediction accuracy in the testing set for the LSTM and BO-LSTM, which increased from 74% to 77% for the hybrid BA-LSTM algorithm.

Heterogeneous data have become a key issue restricting the monitoring accuracy of volcanic ash cloud and rapid application of remote sensing. In view of the characteristics of classification and heterogeneous data in volcanic ash cloud monitoring, a monitoring method of volcanic ash cloud using feature fusion, convolutional neural networks (CNN) and long short-term memory (LSTM) (FF–CNN–LSTM) is presented in this paper. In this method, firstly, the target features in image are identified by CNN and the time sequence information in text is extracted by LSTM. Secondly, the mapping relationship between text information and image features is learned by fusing image target and text high-level features, and then the identification and diffusion of volcanic ash cloud from heterogeneous data containing only image and text were performed. Finally, the presented FF–CNN–LSTM method is tested by the simulation experiment and the true heterogeneous data of Enta volcanic ash cloud case. The experimental results show that compared with the single CNN, LSTM and the simple combination between CNN and LSTM (CNN–LSTM), the presented FF–CNN–LSTM method in this paper can be fitted with less training steps and has high accuracy and low loss rate; the obtained distribution of volcanic ash cloud is clear and intuitive and has the characteristics with fewer model parameters, simple calculation and high accuracy. It also shows the feasibility and effectiveness of the presented method in volcanic ash cloud monitoring to some extent. The results reveal that the presented method can potentially contribute the monitoring of volcanic ash cloud and disaster prevention and mitigation.

ABSTRACTIn this paper, the convolutional recurrent neural network (ConvLSTM) architecture is proposed to predict individual stock prices. The characteristics of stock data are automatically extracted through convolutional neural network (CNN). Afterward, the extracted features are inputted into a long short-term memory (LSTM) model with memory characteristics for prediction. Since CNN has been a representation learning model, it is quite appropriate for automatic feature extraction. Besides, the LSTM architecture of the recurrent neural network could effectively surmount the issues of gradient disappearance and expansion of the time series data. Ten stock historical data had been collected in the experimental data set. Furthermore, many commonly used technical indicators are calculated in advance for the expansion of the dimension of the training samples. The experimental results obtain a 3.449 RMSE (root-mean-square error) in average.

Classification can significantly impact treatment decisions and patient outcomes. This study evaluates and compares the performance of three machine learning models Extreme Learning Machine (ELM), Long Short-Term Memory (LSTM), and Convolutional Neural Networks (CNN) in breast cancer classification. ELM, known for its fast-learning speed and strong generalization, is compared with LSTM, which is effective in capturing long-term dependencies in sequential data, and CNN, which is renowned for its ability to automatically extract features from images and structured data. The models were trained and tested on a breast cancer dataset, focusing on accuracy and computational efficiency. The results revealed that while CNNs demonstrated better accuracy in feature-rich data, LSTMs excelled in handling sequential data patterns. On the other hand, ELM offers a good balance between training speed and classification performance. This comparative analysis provides valuable insights into the strengths and limitations of each model, contributing to the development of more effective breast cancer diagnostic tools. In this case, LSTM outperformed ELM by 0.91%, outperformed CNN significantly by 3.72%, and outperformed Improved LSTM by 0.91%. This indicate that the LSTM model shows higher accuracy in breast cancer classification