Convolutional Neural Network Module Research Articles

Revolutionizing Deepfake Detection and Realtime Video Vision with CNN-based Deep Learning Model

The rapid advancement of deep learning models that can generate and synthesis hyper-realistic videos known as Deepfakes and their ease of access have raised concern on possible malicious intent use. Deep learning techniques can now generate faces, swap faces between two subjects in a video, alter facial expressions, change gender, and alter facial features, to list a few. These powerful video manipulation methods have potential use in many fields. However, they also pose a looming threat to everyone if used for harmful purposes such as identity theft, phishing, and scam. In this work, we propose a Convolutional Vision Transformer for the detection of Deepfakes. The Convolutional Vision Transformer: Convolutional Neural Network (CNN) and Vision Transformer (ViT). The CNN extracts learnable features while the ViT takes in the learned features as input and categorizes them using an attention mechanism. We trained our model on the DeepFake Detection Challenge Dataset (DFDC) and have achieved 91.5 percent accuracy, an AUC value of 0.91, and a loss value of 0.32. Our contribution is that we have added a CNN module to the ViT architecture and have achieved a competitive result on the DFDC dataset.

UViT-Seg: An Efficient ViT and U-Net-Based Framework for Accurate Colorectal Polyp Segmentation in Colonoscopy and WCE Images.

Colorectal cancer (CRC) stands out as one of the most prevalent global cancers. The accurate localization of colorectal polyps in endoscopy images is pivotal for timely detection and removal, contributing significantly to CRC prevention. The manual analysis of images generated by gastrointestinal screening technologies poses a tedious task for doctors. Therefore, computer vision-assisted cancer detection could serve as an efficient tool for polyp segmentation. Numerous efforts have been dedicated to automating polyp localization, with the majority of studies relying on convolutional neural networks (CNNs) to learn features from polyp images. Despite their success in polyp segmentation tasks, CNNs exhibit significant limitations in precisely determining polyp location and shape due to their sole reliance on learning local features from images. While gastrointestinal images manifest significant variation in their features, encompassing both high- and low-level ones, a framework that combines the ability to learn both features of polyps is desired. This paper introduces UViT-Seg, a framework designed for polyp segmentation in gastrointestinal images. Operating on an encoder-decoder architecture, UViT-Seg employs two distinct feature extraction methods. A vision transformer in the encoder section captures long-range semantic information, while a CNN module, integrating squeeze-excitation and dual attention mechanisms, captures low-level features, focusing on critical image regions. Experimental evaluations conducted on five public datasets, including CVC clinic, ColonDB, Kvasir-SEG, ETIS LaribDB, and Kvasir Capsule-SEG, demonstrate UViT-Seg's effectiveness in polyp localization. To confirm its generalization performance, the model is tested on datasets not used in training. Benchmarking against common segmentation methods and state-of-the-art polyp segmentation approaches, the proposed model yields promising results. For instance, it achieves a mean Dice coefficient of 0.915 and a mean intersection over union of 0.902 on the CVC Colon dataset. Furthermore, UViT-Seg has the advantage of being efficient, requiring fewer computational resources for both training and testing. This feature positions it as an optimal choice for real-world deployment scenarios.

BERT-TFBS: a novel BERT-based model for predicting transcription factor binding sites by transfer learning.

Transcription factors (TFs) are proteins essential for regulating genetic transcriptions by binding to transcription factor binding sites (TFBSs) in DNA sequences. Accurate predictions of TFBSs can contribute to the design and construction of metabolic regulatory systems based on TFs. Although various deep-learning algorithms have been developed for predicting TFBSs, the prediction performance needs to be improved. This paper proposes a bidirectional encoder representations from transformers (BERT)-based model, called BERT-TFBS, to predict TFBSs solely based on DNA sequences. The model consists of a pre-trained BERT module (DNABERT-2), a convolutional neural network (CNN) module, a convolutional block attention module (CBAM) and an output module. The BERT-TFBS model utilizes the pre-trained DNABERT-2 module to acquire the complex long-term dependencies in DNA sequences through a transfer learning approach, and applies the CNN module and the CBAM to extract high-order local features. The proposed model is trained and tested based on 165 ENCODE ChIP-seq datasets. We conducted experiments with model variants, cross-cell-line validations and comparisons with other models. The experimental results demonstrate the effectiveness and generalization capability of BERT-TFBS in predicting TFBSs, and they show that the proposed model outperforms other deep-learning models. The source code for BERT-TFBS is available at https://github.com/ZX1998-12/BERT-TFBS.

Research on lung sound classification model based on dual-channel CNN-LSTM algorithm

ulmonary diseases have a significant impact on human health and life safety, and abnormalities in the lungs are a direct response to lung diseases. Establishing an effective lung sound classification model that can assist in diagnosis is of great significance for electronic auscultation.In addressing the issue of lung sound signal classification, this study introduces a deep learning classification model based on a dual-channel CNN-LSTM algorithm. Initially, Mel-scale Frequency Cepstral Coefficients (MFCC) are employed for feature extraction from the dataset, transforming lung sound signals into Mel spectrograms. On this foundation, a dual-channel algorithm classification model is constructed, with parallel Convolutional Neural Network (CNN) and Long Short-Term Memory (LSTM) modules. The CNN module is designed to capture spatial dimension features of the input data, while the LSTM module focuses on temporal dimension features. These two feature sets are fused together, enabling the model to classify lung sounds and thereby assisting in diagnosing pulmonary diseases for healthcare practitioners. This experiment used the ICBHI2017 Challenge Lungs dataset and obtained 5054 pieces of data through data augmentation and sampling techniques.The results show that the accuracy, recall, and F1 score of this model reach 99.01%, 99.13%, and 0.9915, respectively, significantly superior to other models, highlighting its practical application value.

CSPFormer: A cross-spatial pyramid transformer for visual place recognition

Recently, the Vision Transformer (ViT), which applied the Transformer structure to various visual detection tasks, has outperformed convolutional neural networks (CNNs). Nonetheless, due to the lack of scale representation ability of the Transformer, how to extract the local features of the scene to effectively form a global descriptor is still a challenging problem. In the paper, we propose a Cross-Spatial Pyramid Transformer (CSPFormer) to learn the discriminative global descriptors from multi-scale visual features for efficient visual place recognition. Specifically, we first develop a pyramid CNN module that can extract multi-scale visual feature representations. Then, the extracted feature representations of multi-scales are input to multiple connected spatial pyramid Transformer modules that adaptively learn the spatial relationship of the different scale descriptors, where the multiple self-attention is applied to learn a global descriptor from discriminative local descriptors. CNN pyramid features and Transformer multi-scale features are mutually weighted to perform cross-spatial feature representation. The multiple self-attention enhances the long-term dependencies of multi-scale visual descriptors and reduces the computational cost. To obtain the final place-matching result accurately, the cosine function is used to calculate the spatial similarity between the two scenes. Experimental results on public place datasets show that the proposed method achieves state-of-the-art on large-scale visual place recognition tasks. Our model has achieved 94.7%, 92.8%, 91.3%, and 95.7% average recall based on the top 1% candidate scenario on KITTI, Nordland, VPRICE, and EuRoc datasets, respectively.

Integrating prior knowledge into a bibranch pyramid network for medical image segmentation

Medical image segmentation is crucial for obtaining accurate diagnoses, and while convolutional neural network (CNN)-based methods have made strides in recent years, they struggle with modeling long-range dependencies. Transformer-based methods improve this task but require more computational resources. The segment anything model (SAM) can generate pixel-level segmentation results for natural images using sparse manual prompts, but it performs poorly on low-contrast, noisy ultrasound images. To address this issue, we propose a new medical image segmentation network architecture that integrates transformer components, CNN modules, and an SAM encoder into a unified framework. This allows us to simultaneously capture both long-range dependencies and local features. Additionally, we incorporate the image features extracted from the SAM model as prior knowledge to achieve further improved segmentation accuracy with limited training data. To reduce the imposed computational stress, we employ an axial attention mechanism to approximate a transformer's effects by expanding the receptive field. Instead of replacing the transformer components with lightweight attention modules, our model is divided into a global branch and a local branch. The global branch extracts context features with the transformer components, while the local branch processes patch tokens with the axial attention mechanism. We also construct an image pyramid to excavate internal statistics and multiscale representations to obtain more accurate segmentation regions. This bibranch pyramid transformer (Bi-BPT) architecture is effective and robust for medical image segmentation, surpassing other related segmentation network architectures. The experimental results obtained on various medical image datasets demonstrate its effectiveness.

Efficient Near-Infrared Spectrum Detection in Nondestructive Wood Testing via Transfer Network Redesign.

This study systematically developed a deep transfer network for near-infrared spectrum detection using convolutional neural network modules as key components. Through meticulous evaluation, specific modules and structures suitable for constructing the near-infrared spectrum detection model were identified, ensuring its effectiveness. This study extensively analyzed the basic network components and explored three unsupervised domain adaptation structures, highlighting their applications in the nondestructive testing of wood. Additionally, five transfer networks were strategically redesigned to substantially enhance their performance. The experimental results showed that the Conditional Domain Adversarial Network and Globalized Loss Optimization Transfer network outperformed the Direct Standardization, Piecewise Direct Standardization, and Spectral Space Transformation models. The coefficients of determination for the Conditional Domain Adversarial Network and Globalized Loss Optimization Transfer network are 82.11% and 83.59%, respectively, with root mean square error prediction values of 12.237 and 11.582, respectively. These achievements represent considerable advancements toward the practical implementation of an efficient and reliable near-infrared spectrum detection system using a deep transfer network.

Approach to Perforation Interval Selection Uses AI-Assisted Image Interpretation

_ This article, written by JPT Technology Editor Chris Carpenter, contains highlights of paper SPE 216856, “ML-Driven Integrated Approach for Perforation Interval Selection Based on Advanced Borehole-Image AI-Assisted Interpretation,” by Alexander Petrov, SPE, Mounir Belouahchia, SPE, and Abdelwahab Noufal, SPE, ADNOC. The paper has not been peer reviewed. _ In the complete paper, the authors propose an artificial-intelligence (AI)-assisted work flow that uses machine-learning (ML) techniques to identify sweet spots in carbonate reservoirs. This process involves annotation of geologic features using a well database, with supervision from subject-matter experts (SMEs). The resulting ML model is tested on new wells and can identify pay zones, perforation intervals, and stress analysis. The models successfully detect fractures, breakouts, bedding planes, vugs, and slippage passages with pixel-level precision, reducing borehole-image (BHI) analysis time. BHI Interpretation and Preprocessing The use of BHIs requires manual interpretation and data identification, heavily relying on the expertise and time of SMEs. A widely adopted approach to address this challenge is the use of supervised computer-vision algorithms, a subfield of AI. These algorithms optimize the task function or model based on examples they have learned from data during training. However, when applied to BHIs, certain ML challenges must be addressed, including the following: - Detecting features in wells from different reservoirs using a model trained on wells from one reservoir can be highly challenging because reservoirs may exhibit distinct geological characteristics. - The handling of parts of BHIs with missing data, depicted by vertically slanted white strips, poses considerable difficulty. Therefore, the authors created a deep-learning approach based on a generative adversarial network architecture to fill the gaps automatically (Fig. 1). - The labels provided by geologists often do not have pixelwise precision, causing the machine to become confused while trying to learn inconsistent patterns. The authors use a convolutional neural network (CNN) to compute a probability map for pixels belonging to specific classes. In this application, a class is defined as any of the heterogeneities in the BHI; however, this method is applicable to any type of heterogeneities in an image. After training, the CNN module provides the optimal probability for each pixel in the image. To classify regions in the BHI based on heterogeneities, a class-specific threshold is established. Pixels with values above the thresholds are assigned to the corresponding class, while those below the thresholds are assigned to the background. BHI-Derived Porosity A new approach for borehole-derived porosity was developed in-house to overcome the limitations of existing techniques widely used in the industry. This approach capitalizes on BHIs for multiple analyses, including structural dip assessment, fault and fracture identification, and determination of minimum and maximum horizontal stress orientation. However, its primary strength lies in quantifying the fraction of secondary porosity in heterogeneous or dual-porosity carbonate formations. The authors have devised a novel method that uses borehole electrical images to conduct porosity and image connectivity analysis. By implementing this technique, essential information can be extracted regarding the spatial distribution of porosity and the extent of secondary porosity fraction.

Design of 3D Environment Combining Digital Image Processing Technology and Convolutional Neural Network

As virtual reality technology advances, 3D environment design and modeling have garnered increasing attention. Applications in networked virtual environments span urban planning, industrial design, and manufacturing, among other fields. However, existing 3D modeling methods exhibit high reconstruction error precision, limiting their practicality in many domains, particularly environmental design. To enhance 3D reconstruction accuracy, this study proposes a digital image processing technology that combines binocular camera calibration, stereo correction, and a convolutional neural network (CNN) algorithm for optimization and improvement. By employing the refined stereo-matching algorithm, a 3D reconstruction model was developed to augment 3D environment design and reconstruction accuracy while optimizing the 3D reconstruction effect. An experiment using the ShapeNet dataset demonstrated that the evaluation indices—Chamfer distance (CD), Earth mover’s distance (EMD), and intersection over union—of the model constructed in this study outperformed those of alternative methods. After incorporating the CNN module in the ablation experiment, CD and EMD increased by an average of 0.1 and 0.06, respectively. This validates that the proposed CNN module effectively enhances point cloud reconstruction accuracy. Upon adding the CNN module, the CD index and EMD index in the dataset increased by an average of 0.34 and 0.54, respectively. These results indicate that the proposed CNN module exhibits strong predictive capabilities for point cloud coordinates. Furthermore, the model demonstrates good generalization performance.

MSDSE: Predicting drug-side effects based on multi-scale features and deep multi-structure neural network

Unexpected side effects may accompany the research stage and post-marketing of drugs. These accidents lead to drug development failure and even endanger patients' health. Thus, it is essential to recognize the unknown drug-side effects. Most existing methods in silico find the answer from the association network or similarity network of drugs while ignoring the drug-intrinsic attributes. The limitation is that they can only handle drugs in the maturation stage.To be suitable for early drug-side effect screening, we conceive a multi-structural deep learning framework, MSDSE, which synthetically considers the multi-scale features derived from the drug. MSDSE can jointly learn SMILES sequence-based word embedding, substructure-based molecular fingerprint, and chemical structure-based graph embedding. In the preprocessing stage of MSDSE, we project all features to the abstract space with the same dimension. MSDSE builds a bi-level channel strategy, including a convolutional neural network module with an Inception structure and a multi-head Self-Attention module, to learn and integrate multi-modal features from local to global perspectives. Finally, MSDSE regards the prediction of drug-side effects as pair-wise learning and outputs the pair-wise probability of drug-side effects through the inner product operation. MSDSE is evaluated and analyzed on benchmark datasets and performs optimally compared to other baseline models. We also set up the ablation study to explain the rationality of the feature approach and model structure. Moreover, we select model partial prediction results for the case study to reveal actual capability. The original data are available at http://github.com/yuliyi/MSDSE.

A Novel Unsupervised Segmentation Method of Canopy Images from UAV Based on Hybrid Attention Mechanism

Crown segmentation is a pivotal process in the acquisition of tree parameters. In light of the high expenses associated with satellite remote sensing and LiDAR technologies, our study leverages the cost-effective and efficient UAV remote sensing technology for capturing crown images. In addition, considering the expense and sensitivity associated with labeling data for supervised learning and its implications on model generalization and label quality, this paper introduces an innovative unsupervised learning framework based on convolutional neural networks (CNN). To address the limited receptive field of CNN, we have introduced a novel hybrid attention module following each CNN module. This enhancement ensures the integrity of the segmentation results and the coherence of the boundaries. Furthermore, in response to the growing need for user interaction, we have incorporated a scribble interaction function. Through the semantic segmentation of the collected crown images, our proposed method attains remarkable results, achieving an accuracy of 98.15%, an F1_score of 97.01%, and an mIoU of 95.58%. Additionally, we have conducted a comparative analysis of our proposed method with two clustering algorithms, namely K-Means and GMM, and two CNN models, DeepLab and U-Net. The results reveal that our segmentation structures outperform other methods significantly. The experimental findings demonstrate the immense application potential of this method in diverse fields, including forestry management, environmental protection, and ecosystem monitoring.

Hybrid Convolution neural Network and Graph Neural network for Detection of Leukocyte

In pathology and medical diagnostics, the identification of leukocytes, white blood cells essential for immune system function, is significant. The hybrid neural network model used in this study, which combines the strengths of convolutional neural networks (CNNs) and graph neural networks (GNNs), gives a unique method for the identification of leukocytes. Due to the intricate spatial and relational patterns visible in microscopic pictures of blood samples, leukocyte identification is difficult. The proposed hybrid model incorporates a GNN module to record the contextual associations among leukocytes in a blood sample and a CNN module to extract fine-grained characteristics from individual leukocyte pictures. Each leukocyte picture is seen in this paradigm as a node in a network, with the edges denoting the interactions between the cells' locations or contexts. While the GNN module uses graph-based representations to capture the connections and dependencies between leukocytes within a blood sample, the CNN module efficiently extracts local visual characteristics from leukocyte pictures. These two modules are used to produce a thorough and context-sensitive depiction of the leukocyte detection issue. The importance of this study resides in its potential to increase the precision and effectiveness of leukocyte identification in pathology and medical diagnostics, leading to better patient care and illness diagnosis. This hybrid CNN-GNN model may also be used for a variety of other medical image analysis tasks that call for taking both local and contextual information into account. In successfully identifying leukocytes in microscopic images, this hybrid CNN-GNN technique shows promising results. Accuracy, precision, recall, and F1-score are common assessment metrics used to assess the model's performance.

Enhanced Feature Extraction Network Based on Acoustic Signal Feature Learning for Bearing Fault Diagnosis.

The method of acoustic radiation signal detection not only enables contactless measurement but also provides comprehensive state information during equipment operation. This paper proposes an enhanced feature extraction network (EFEN) for fault diagnosis of rolling bearings based on acoustic signal feature learning. The EFEN network comprises four main components: the data preprocessing module, the information feature selection module (IFSM), the channel attention mechanism module (CAMM), and the convolutional neural network module (CNNM). Firstly, the one-dimensional acoustic signal is transformed into a two-dimensional grayscale image. Then, IFSM utilizes three different-sized convolution filters to process input image data and fuse and assign weights to feature information that can attenuate noise while highlighting effective fault information. Next, a channel attention mechanism module is introduced to assign weights to each channel. Finally, the convolutional neural network (CNN) fault diagnosis module is employed for accurate classification of rolling bearing faults. Experimental results demonstrate that the EFEN network achieves high accuracy in fault diagnosis and effectively detects rolling bearing faults based on acoustic signals. The proposed method achieves an accuracy of 98.52%, surpassing other methods in terms of performance. In comparative analysis of antinoise experiments, the average accuracy remains remarkably high at 96.62%, accompanied by a significantly reduced average iteration time of only 0.25 s. Furthermore, comparative analysis confirms that the proposed algorithm exhibits excellent accuracy and resistance against noise.

IPSI(2L)-EDL: a Two-layer Predictor for Identifying Promoters and their Types based on Ensemble Deep Learning

Abstract: Promoters are DNA fragments located near the transcription initiation site, they can be divided into strong promoter type and weak promoter type according to transcriptional activation and expression level. Identifying promoters and their strengths in DNA sequences is essential for understanding gene expression regulation. Therefore, it is crucial to further improve predictive quality of predictors for real-world application requirements. Here, we constructed the latest training dataset based on the RegalonDB website, where all the promoters in this dataset have been experimentally validated, and their sequence similarity is less than 85%. We used one-hot and nucleotide chemical property and density (NCPD) to represent DNA sequence samples. Additionally, we proposed an ensemble deep learning framework containing a multi-head attention module, long short-term memory present, and a convolutional neural network module. The results showed that iPSI(2L)-EDL outperformed other existing methods for both promoter prediction and identification of strong promoter type and weak promoter type, the AUC and MCC for the iPSI(2L)-EDL in identifying promoter were improved by 2.23% and 2.96% compared to that of PseDNC-DL on independent testing data, respectively, while the AUC and MCC for the iPSI(2L)- EDL were increased by 3.74% and 5.86% in predicting promoter strength type, respectively. The results of ablation experiments indicate that CNN plays a crucial role in recognizing promoters, the importance of different input positions and long-range dependency relationships among features are helpful for recognizing promoters. Furthermore, to make it easier for most experimental scientists to get the results they need, a userfriendly web server has been established and can be accessed at http://47.94.248.117/IPSW(2L)-EDL.

Pure large kernel convolutional neural network transformer for medical image registration

Deformable medical image registration is a fundamental and critical task in medical image analysis. Recently, deep learning-based methods have rapidly developed and have shown impressive results in deformable image registration. However, existing approaches still suffer from limitations in registration accuracy or generalization performance. To address these challenges, in this paper, we propose a pure convolutional neural network module (CVTF) to implement hierarchical transformers and enhance the registration performance of medical images. CVTF has a larger convolutional kernel, providing a larger global effective receptive field, which can improve the network’s ability to capture long-range dependencies. In addition, we introduce the spatial interaction attention (SIA) module to compute the interrelationship between the target feature pixel points and all other points in the feature map. This helps to improve the semantic understanding of the model by emphasizing important features and suppressing irrelevant ones. Based on the proposed CVTF and SIA, we construct a novel registration framework named PCTNet. We applied PCTNet to generate displacement fields and register medical images, and we conducted extensive experiments and validation on two public datasets, OASIS and LPBA40. The experimental results demonstrate the effectiveness and generality of our method, showing significant improvements in registration accuracy and generalization performance compared to existing methods. Our code has been available at https://github.com/fz852/PCTNet.

Joint Measurement of Thermal Discomfort by Occupant Pose, Motion and Appearance in Indoor Surveillance Videos for Building Energy Saving

To accurately describe the thermal comfort of indoor occupant used to regulate heating, ventilation and air conditioning (HVAC) system is a key goal to reduce energy consumption in intelligent buildings. In this paper, we propose a noncontact measurement of occupant thermal discomfort behavior as an index of thermal comfort. The method takes the existing monitoring image data in the building as the input to infer the occupant thermal discomfort directly, which saves the cost because there is no need to install new sensors in the building and the occupant does not need to wear additional equipment. The framework combined three channels of body posture, motion and performance information to infer occupant thermal discomfort behavior, it consists of a human detection and crop module, a posture analysis module, an optical flow extraction module and a 3D convolutional neural network module. The three channels describe the actions from different perspectives, and the proposed method makes full use of the complementarity of the three modalities to identify the occupant’s thermal discomfort behaviors. Sixteen postures related to thermal discomfort were identified through a questionnaire, and 14,800 video clips containing these postures were collected for experimental evaluation. The results demonstrate the superior performances of our approach to the state-of-the-art techniques. The framework achieves noninvasive, cost-effective thermal comfort evaluation, and has potential value in improving energy efficiency of HVAC systems.

SGNet: Sequence-Based Convolution and Ligand Graph Network for Protein Binding Affinity Prediction.

Protein-ligand binding can play an important role in many fields. It is of great importance to accurately predict the binding affinity between molecules by computational methods. Most computational binding affinity methods require molecular structures. However, there are still a large number of protein molecules with known amino acid sequences whose structures have not yet been solved. To address this issue, this paper proposes a sequence-based convolution and ligand graph network, called SGNet, to fuse the molecular graph information and the amino acid sequence information. This method integrates Conjoint Triad (CT) encoding of amino acid sequence and one-dimensional convolutional neural network module to extract protein molecules, develops graph attention network to extract molecular features of ligand, and then fuses the two feature sets to predict the binding affinity between molecules from the fully connected layer. As a result, SGNet achieves good prediction performance on both KIKD and IC50 data sets, with prediction error RMSEs of 1.287 and 1.58, and correlation Pearson Rs of 0.687 and 0.592, respectively. Comparative experimental results under the same conditions showed that SGNet outperformed Kdeep and GraphDTA in predicting binding affinities between protein-ligand molecules.

SeriesSleepNet: an EEG time series model with partial data augmentation for automatic sleep stage scoring.

Introduction: We propose an automatic sleep stage scoring model, referred to as SeriesSleepNet, based on convolutional neural network (CNN) and bidirectional long short-term memory (bi-LSTM) with partial data augmentation. We used single-channel raw electroencephalography signals for automatic sleep stage scoring. Methods: Our framework was focused on time series information, so we applied partial data augmentation to learn the connected time information in small series. In specific, the CNN module learns the time information of one epoch (intra-epoch) whereas the bi-LSTM trains the sequential information between the adjacent epochs (inter-epoch). Note that the input of the bi-LSTM is the augmented CNN output. Moreover, the proposed loss function was used to fine-tune the model by providing additional weights. To validate the proposed framework, we conducted two experiments using the Sleep-EDF and SHHS datasets. Results and Discussion: The results achieved an overall accuracy of 0.87 and 0.84 and overall F1-score of 0.80 and 0.78 and kappa value of 0.81 and 0.78 for five-class classification, respectively. We showed that the SeriesSleepNet was superior to the baselines based on each component in the proposed framework. Our architecture also outperformed the state-of-the-art methods with overall F1-score, accuracy, and kappa value. Our framework could provide information on sleep disorders or quality of sleep to automatically classify sleep stages with high performance.

Rice disease identification method based on improved CNN-BiGRU

In the field of precision agriculture, diagnosing rice diseases from images remains challenging due to high error rates, multiple influencing factors, and unstable conditions. While machine learning and convolutional neural networks have shown promising results in identifying rice diseases, they were limited in their ability to explain the relationships among disease features. In this study, we proposed an improved rice disease classification method that combines a convolutional neural network (CNN) with a bidirectional gated recurrent unit (BiGRU). Specifically, we introduced a residual mechanism into the Inception module, expanded the module's depth, and integrated an improved Convolutional Block Attention Module (CBAM). We trained and tested the improved CNN and BiGRU, concatenated the outputs of the CNN and BiGRU modules, and passed them to the classification layer for recognition. Our experiments demonstrate that this approach achieves an accuracy of 98.21% in identifying four types of rice diseases, providing a reliable method for rice disease recognition research.

Eff-PCNet: An Efficient Pure CNN Network for Medical Image Classification

With the development of deep learning, convolutional neural networks (CNNs) and Transformer-based methods have become key techniques for medical image classification tasks. However, many current neural network models have problems such as high complexity, a large number of parameters, and large model sizes; such models obtain higher classification accuracy at the expense of lightweight networks. Moreover, such larger-scale models pose a great challenge for practical clinical applications. Meanwhile, Transformer and multi-layer perceptron (MLP) methods have some shortcomings in terms of local modeling capability and high model complexity, and need to be used on larger datasets to show good performance. This makes it difficult to utilize these networks in clinical medicine. Based on this, we propose a lightweight and efficient pure CNN network for medical image classification (Eff-PCNet). On the one hand, we propose a multi-branch multi-scale CNN (M2C) module, which divides the feature map into four parallel branches along the channel dimensions by a certain scale factor and carries out a deep convolution operation using different scale convolution kernels, and this multi-branch multi-scale operation effectively replaces the large kernel convolution. This multi-branch multi-scale operation effectively replaces the large kernel convolution. It reduces the computational cost of the module while fusing the feature information between different channels and thus obtains richer feature information. Finally, the four feature maps are then spliced along the channel dimensions to fuse the multi-scale and multi-dimensional feature information. On the other hand, we introduce the structural reparameterization technique and propose the structural reparameterized CNN (Rep-C) module. Specifically, it utilizes multiple linear operators to generate different feature maps during the training process and fuses all the participants into one through parameter fusion to achieve fast inference while providing a more effective solution for feature reuse. A number of experimental results show that our Eff-PCNet performs better than current methods based on CNN, Transformer, and MLP in the classification of three publicly available medical image datasets. Among them, we achieve 87.4% Acc on the HAM10000 dataset, 91.06% Acc on the SkinCancer dataset, and 97.03% Acc on the Chest-Xray dataset. Meanwhile, our approach achieves a better trade-off between the number of parameters; computation; and other performance metrics as well.