CNN Module Research Articles

MAMCL: Multi-attributes Masking Contrastive Learning for explainable seismic facies analysis

Seismic facies analysis is crucial in hydrocarbon exploration and development. Traditional machine learning approaches typically require manual selection of attributes and lack interpretability analysis. We propose an interpretable framework, multi-attribute masking contrastive learning (MAMCL), designed to adaptively select, explore and aggregate seismic attributes for seismic facies analysis. The MAMCL framework includes a depthwise CNN module for feature extraction and an iTransformer module for feature aggregation. Based on the assumption that different attributes computed on the same seismic sample imply common information associated with the same geologic facies, we formulate an unsupervised strategy of contrastive learning to pre-train the MAMCL framework for refining the attributes. This pre-training method encourages the network to extract and integrate highly correlated attribute features by enhancing the expression of commonalities within the same sample, and implicitly increase the distance between features of different categories by differentiating the expressions of different samples. Ultimately, these refined features only need to be input into a simple clustering algorithm, such as K-Means, to achieve seismic facies classification. MAMCL requires no labels or manual selection of attributes and can utilize the self-attention mechanism of iTransformer to compute adaptive attribute weights, facilitating interpretability analysis. We applied MAMCL framework to both unlogged turbidite channel systems in Canterbury Basin, New Zealand, and logged Chengdao area in Bohai Bay Basin, China, achieving reliable classification results and providing interpretability analysis.

HCAM-CL: A Novel Method Integrating a Hierarchical Cross-Attention Mechanism with CNN-LSTM for Hierarchical Image Classification

Deep learning networks have yielded promising insights in the field of image classification. However, the hierarchical image classification (HIC) task, which involves assigning multiple, hierarchically organized labels to each image, presents a notable challenge. In response to this complexity, we developed a novel framework (HCAM-CL), which integrates a hierarchical cross-attention mechanism with a CNN-LSTM architecture for the HIC task. The HCAM-CL model effectively identifies the relevance between images and their corresponding labels while also being attuned to learning the hierarchical inter-dependencies among labels. Our versatile model is designed to manage both fixed-length and variable-length classification pathways within the hierarchy. In the HCAM-CL model, the CNN module is responsible for the essential task of extracting image features. The hierarchical cross-attention mechanism vertically aligns these features with hierarchical levels, uniformly weighing the importance of different spatial regions. Ultimately, the LSTM module is strategically utilized to generate predictive outcomes by treating HIC as a sequence generation challenge. Extensive experimental evaluations on CIFAR-10, CIFAR-100, and design patent image datasets demonstrate that our HCAM-CL framework consistently outperforms other state-of-the-art methods in hierarchical image classification.

Forecasting Hand-Foot-and-Mouth Disease in Qingdao City Based on CNN-BiLSTM-Attention Model

Purpose:A deep learning model CNN-BiLSTM-Attention was proposed, which realized the prediction of the outbreak rule and trend of HFMD in Qingdao, and could provide scientific basis for the relevant departments to formulate preventive measures..Methods:Based on the data of temperature, humidity and HFMD in Qingdao city, a multi-source heterogeneous data set was constructed and a long-term time series prediction model was proposed based on attention mechanism, which can predict the future incidence trend of HFMD. Then, ablation experiments were performed to verify the importance of each module, and comparison experiments with infectious disease dynamic model (SEIIeQR) and statistical model (ARIMA, SARIMA) proved the accuracy of the proposed model..Results:The ablation experiments demonstrated that the CNN module,Attention module,and BiLSTM module could effectively enhance the model's performance.The comparative experiment results revealed the superiority of the deep learning model in predicting HFMD outbreaks in Qingdao City.Conclusion:The multi-source heterogeneous dataset incorporating average temperature and relative humidity data significantly improved the model's accuracy.The CNN-BiLSTM-Attention model outperforms traditional methods in predicting HFMD incidence in Qingdao City,thereby assisting relevant departments in Qingdao to adopt scientific preventive measures against HFMD.

Hybridized deep learning goniometry for improved precision in Ehlers-Danlos Syndrome (EDS) evaluation

BackgroundGeneralized Joint Hyper-mobility (GJH) can aid in the diagnosis of Ehlers-Danlos Syndrome (EDS), a complex genetic connective tissue disorder with clinical features that can mimic other disease processes. Our study focuses on developing a unique image-based goniometry system, the HybridPoseNet, which utilizes a hybrid deep learning model.ObjectiveThe proposed model is designed to provide the most accurate joint angle measurements in EDS appraisals. Using a hybrid of CNNs and HyperLSTMs in the pose estimation module of HybridPoseNet offers superior generalization and time consistency properties, setting it apart from existing complex libraries.MethodologyHybridPoseNet integrates the spatial pattern recognition prowess of MobileNet-V2 with the sequential data processing capability of HyperLSTM units. The system captures the dynamic nature of joint motion by creating a model that learns from individual frames and the sequence of movements. The CNN module of HybridPoseNet was trained on a large and diverse data set before the fine-tuning of video data involving 50 individuals visiting the EDS clinic, focusing on joints that can hyperextend. HyperLSTMs have been incorporated in video frames to avoid any time breakage in joint angle estimation in consecutive frames. The model performance was evaluated using Spearman’s coefficient correlation versus manual goniometry measurements, as well as by the human labeling of joint position, the second validation step.OutcomePreliminary findings demonstrate HybridPoseNet achieving a remarkable correlation with manual Goniometric measurements: thumb (rho = 0.847), elbows (rho = 0.822), knees (rho = 0.839), and fifth fingers (rho = 0.896), indicating that the newest model is considerably better. The model manifested a consistent performance in all joint assessments, hence not requiring selecting a variety of pose-measuring libraries for every joint. The presentation of HybridPoseNet contributes to achieving a combined and normalized approach to reviewing the mobility of joints, which has an overall enhancement of approximately 20% in accuracy compared to the regular pose estimation libraries. This innovation is very valuable to the field of medical diagnostics of connective tissue diseases and a vast improvement to its understanding.

Multi-branch CNN and grouping cascade attention for medical image classification

Visual Transformers(ViT) have made remarkable achievements in the field of medical image analysis. However, ViT-based methods have poor classification results on some small-scale medical image classification datasets. Meanwhile, many ViT-based models sacrifice computational cost for superior performance, which is a great challenge in practical clinical applications. In this paper, we propose an efficient medical image classification network based on an alternating mixture of CNN and Transformer tandem, which is called Eff-CTNet. Specifically, the existing ViT-based method still mainly relies on multi-head self-attention (MHSA). Among them, the attention maps of MHSA are highly similar, which leads to computational redundancy. Therefore, we propose a group cascade attention (GCA) module to split the feature maps, which are provided to different attention heads to further improves the diversity of attention and reduce the computational cost. In addition, we propose an efficient CNN (EC) module to enhance the ability of the model and extract the local detail information in medical images. Finally, we connect them and design an efficient hybrid medical image classification network, namely Eff-CTNet. Extensive experimental results show that our Eff-CTNet achieves advanced classification performance with less computational cost on three public medical image classification datasets.

An attention-based deep learning method for safety of uncertain vehicle-bridge system with random near fault earthquakes

In this paper, a novel approach, based on the principle of the deep learning method, is proposed to study the stochastic responses of vehicle-bridge system (VBS) subjected to near fault earthquakes (NFEs), which also considers the effects of uncertain parameters. To generate the training data as the input of the proposed deep learning model, the dynamic formulas of the VBS are deduced by Newmark-β method. The proposed analysis model comprises three modules: the CNN module for seismic data feature extraction, the Attention Mechanism module for enhancing the selection for information between time series to improve the accuracy and efficiency of the final prediction, and the Bidirectional Gated Recurrent Unit (BiGRU) for predicting VBS responses. The mapping connection between earthquake action and the system response is established. The BiGRU model is capable of conveying both the excitation's randomness and the system's uncertain parameters. An actual railway cable-stayed bridge subjected to the running railway vehicle and NFEs is utilized to verify the proposed model. The uncertain train weight, bridge damping ratio and the randomness of NFEs are incorporated into the dynamic responses analysis of VBS. As a result, the time-varying responses obtained by the proposed model show significant agreement with results from a validated dynamic VBS framework. The mean value and standard deviation (STD) of the responses obtained by the proposed method are also compared with those by the Monte Carlo method and probability density evolution method. Therefore, both the individual sample of the dynamic response and the statistical data from diverse stochastic responses are chosen to validate the model's accuracy and efficiency in the VBS analysis under NFEs. In addition, the effects of the stochastic characteristics on the system's random vibrations are also explored through the time-histories of statistical data and the probability density function of the absolute maximum of responses.

A multi-granularity hierarchical network for long- and short-term forecasting on multivariate time series data

Multivariate time series forecasting is a significant research problem in many fields such as economics, finance and transportation, where simultaneous long- and short-term forecasting is required. However, current techniques are typically limited to a single short-term or a long-term forecast. To address the limitation, a novel multi-granularity hierarchical network, GNet-LS, is proposed for long- and short-term forecasting on multivariate time series data, which takes into account the separate role of internal correlation and external relationship. First, the original time series sequence is divided into multiple granular sequences based on downsampling, to reduce error accumulation caused by long-term prediction. In order to discover the external relationships between variables, the CNN module slides over the sequence of variables. The global CNN and local CNN are built to implement periodic and nonperiodic extraction, respectively. Next, a self-attention module is used to model dependencies between the output of local CNN and global CNN. The LSTM networks and attention mechanisms are used to mine internal correlation of the target variable on time series. Then, multiple granular external relationships and internal correlation are obtained in parallel. Finally, external relationships and internal correlation are fused together by splicing and overlay to obtain both long-term and short-term forecasts. The experimental results demonstrate that the proposed GNet-LS outperforms a bunch of compared methods in terms of RSE, CORR, MAE and RMSE.

Cm-siRPred: Predicting chemically modified siRNA efficiency based on multi-view learning strategy

The rational modification of siRNA molecules is crucial for ensuring their drug-like properties. Machine learning-based prediction of chemically modified siRNA (cm-siRNA) efficiency can significantly optimize the design process of siRNA chemical modifications, saving time and cost in siRNA drug development. However, existing in-silico methods suffer from limitations such as small datasets, inadequate data representation capabilities, and lack of interpretability. Therefore, in this study, we developed the Cm-siRPred algorithm based on a multi-view learning strategy. The algorithm employs a multi-view strategy to represent the double-strand sequences, chemical modifications, and physicochemical properties of cm-siRNA. It incorporates a cross-attention model to globally correlate different representation vectors and a two-layer CNN module to learn local correlation features. The algorithm demonstrates exceptional performance in cross-validation experiments, independent dataset, and case studies on approved siRNA drugs, and showcasing its robustness and generalization ability. In addition, we developed a user-friendly webserver that enables efficient prediction of cm-siRNA efficiency and assists in the design of siRNA drug chemical modifications. In summary, Cm-siRPred is a practical tool that offers valuable technical support for siRNA chemical modification and drug efficiency research, while effectively assisting in the development of novel small nucleic acid drugs. Cm-siRPred is freely available at https://cellknowledge.com.cn/sirnapredictor/.

A bidirectional interpretable compound-protein interaction prediction framework based on cross attention

The identification of compound-protein interactions (CPIs) plays a vital role in drug discovery. However, the huge cost and labor-intensive nature in vitro and vivo experiments make it urgent for researchers to develop novel CPI prediction methods. Despite emerging deep learning methods have achieved promising performance in CPI prediction, they also face ongoing challenges: (i) providing bidirectional interpretability from both the chemical and biological perspective for the prediction results; (ii) comprehensively evaluating model generalization performance; (iii) demonstrating the practical applicability of these models. To overcome the challenges posed by current deep learning methods, we propose a cross multi-head attention oriented bidirectional interpretable CPI prediction model (CmhAttCPI). First, CmhAttCPI takes molecular graphs and protein sequences as inputs, utilizing the GCW module to learn atom features and the CNN module to learn residue features, respectively. Second, the model applies cross multi-head attention module to compute attention weights for atoms and residues. Finally, CmhAttCPI employs a fully connected neural network to predict scores for CPIs. We evaluated the performance of CmhAttCPI on balanced datasets and imbalanced datasets. The results consistently show that CmhAttCPI outperforms multiple state-of-the-art methods. We constructed three scenarios based on compound and protein clustering and comprehensively evaluated the model generalization ability within these scenarios. The results demonstrate that the generalization ability of CmhAttCPI surpasses that of other models. Besides, the visualizations of attention weights reveal that CmhAttCPI provides chemical and biological interpretation for CPI prediction. Moreover, case studies confirm the practical applicability of CmhAttCPI in discovering anticancer candidates.

Air Traffic Flow Management Delay Prediction Based on Feature Extraction and an Optimization Algorithm

Air Traffic Flow Management (ATFM) delay can quantitatively reflect the congestion caused by the imbalance between capacity and demand in an airspace network. Furthermore, it is an important parameter for the ex-post analysis of airspace congestion and the effectiveness of ATFM strategy implementation. If ATFM delays can be predicted in advance, the predictability and effectiveness of ATFM strategies can be improved. In this paper, a short-term ATFM delay regression prediction method is proposed for the characteristics of the multiple sources, high dimension, and complexity of ATFM delay prediction data. The method firstly constructs an ATFM delay prediction network model, specifies the prediction object, and proposes an ATFM delay prediction index system by integrating common flow control information. Secondly, an ATFM delay prediction method based on feature extraction modules (including CNN, TCN, and attention modules), a heuristic optimization algorithm (sparrow search algorithm (SSA)), and a prediction model (LSTM) are proposed. The method constructs a CNN-LSTM-ATT model based on SSA optimization and a TCN-LSTM-ATT model based on SSA optimization. Finally, four busy airports and their major waypoints in East China are selected as the ATFM delay prediction network nodes for example validation. The experimental results show that the MAEs of the two models proposed in this paper for ATFM delay regression prediction are 4.25 min and 4.38 min, respectively. Compared with the CNN-LSTM model, the errors are reduced by 2.71 min and 2.59 min, respectively. Compared with the TCN-LSTM model, the times are 3.68 min and 3.55 min, respectively. In this paper, two improved LSTM models are constructed to improve the prediction accuracy of ATFM delay duration so as to provide support for the establishment of an ATFM delay early warning mechanism, further improve ATFM delay management, and enhance resource allocation efficiency.

A bimodal feature fusion convolutional neural network for detecting obstructive sleep apnea/hypopnea from nasal airflow and oximetry signals

The most prevalent sleep-disordered breathing condition is Obstructive Sleep Apnea (OSA), which has been linked to various health consequences, including cardiovascular disease (CVD) and even sudden death. Therefore, early detection of OSA can effectively help patients prevent the diseases induced by it. However, many existing methods have low accuracy in detecting hypopnea events or even ignore them altogether. According to the guidelines provided by the American Academy of Sleep Medicine (AASM), two modal signals, namely nasal pressure airflow and pulse oxygen saturation (SpO2), offer significant advantages in detecting OSA, particularly hypopnea events. Inspired by this notion, we propose a bimodal feature fusion CNN model that primarily comprises of a dual-branch CNN module and a feature fusion module for the classification of 10-second-long segments of nasal pressure airflow and SpO2. Additionally, an Efficient Channel Attention mechanism (ECA) is incorporated into the second module to adaptively weight feature map of each channel for improving classification accuracy. Furthermore, we design an OSA Severity Assessment Framework (OSAF) to aid physicians in effectively diagnosing OSA severity. The performance of both the bimodal feature fusion CNN model and OSAF is demonstrated to be excellent through per-segment and per-patient experimental results, based on the evaluation of our method using two real-world datasets consisting of polysomnography (PSG) recordings from 450 subjects.

ETUNet:Exploring efficient transformer enhanced UNet for 3D brain tumor segmentation

Medical image segmentation is a crucial topic in medical image processing. Accurately segmenting brain tumor regions from multimodal MRI scans is essential for clinical diagnosis and survival prediction. However, similar intensity distributions, variable tumor shapes, and fuzzy boundaries pose severe challenges for brain tumor segmentation. Traditional segmentation networks based on UNet struggle to establish explicit long-range dependencies from the feature space due to the limitations of the CNN receptive field. This is particularly crucial for dense prediction tasks such as brain tumor segmentation. Recent works have incorporated the powerful global modeling capability of Transformer into UNet to achieve more precise segmentation results. Nevertheless, these methods encounter some issues: (1) the global information is often modeled by simply stacking Transformer layers for a specific module, resulting in high computational complexity and underutilization of the potential of the UNet architecture; (2) the rich boundary information of tumor subregions in multi-scale features is often overlooked. Motivated by these challenges, we propose an advanced fusion of Transformer with UNet by reexamining the core three parts (encoder, bottleneck, and skip connections). Firstly, we introduce a CNN-Transformer module in the encoder to replace the traditional CNN module, enabling the capture of deep spatial dependencies from input images. To address high-level semantic information, we incorporate a computationally efficient spatial-channel attention layer in the bottleneck for global interaction, highlighting important semantic features from the encoder path output. For irregular lesions, we fuse the multi-scale features from the encoder output and the decoder features in the skip connections by calculating cross-attention. This adaptive querying of valuable information from multi-scale features enhances the boundary localization ability of the decoder path and suppresses redundant features with low correlation. Compared to existing methods, our model further enhances the learning capacity of the overall UNet architecture while maintaining low computational complexity. Experimental results on the BraTS2018 and BraTS2020 datasets for brain tumor segmentation tasks demonstrate that our model achieves comparable or superior results compared to recent CNN or Transformer-based models. The average DSC and HD95 on the two datasets are 0.854, 6.688, and 0.862, 5.455 respectively. At the same time, our model achieves optimal segmentation of Enhancing tumors, showcasing the effectiveness of our method. Our code will be made publicly available at https://github.com/wzhangck/ETUnet.

A short-term photovoltaic power interval forecasting method based on fuzzy granular computing and CNN-BiGRU

Abstract This paper presents a short-term PV power interval prediction method combining fuzzy information granulation and CNN-BiGRU model. First, historical data of PV power generation is processed using fuzzy information granulation to determine the interval range. Subsequently, a CNN-BiGRU model is constructed, where the CNN module extracts local features of the interval range and the BiGRU module captures temporal patterns. The interval range is then fed into the CNN-BiGRU model for training, which enables accurate prediction of short-term PV power generation intervals. Finally, the predicted power generation interval ranges are given. The experimental results show that this hybrid interval prediction method is first applied to the prediction of short-term PV power scenarios, which fully utilizes the advantages of information granularity to express the data intervals and CNN-BiGRU to learn the complex time series patterns, and realizes the accurate and reliable prediction of short-term PV power intervals. Compared with direct numerical prediction, the method provides an expression of prediction uncertainty, which provides an important reference for the operation decision of PV power plants.

A hybrid cloud load balancing and host utilization prediction method using deep learning and optimization techniques

Virtual machine (VM) integration methods have effectively proven an optimized load balancing in cloud data centers. The main challenge with VM integration methods is the trade-off among cost effectiveness, quality of service, performance, optimal resource utilization and compliance with service level agreement violations. Deep Learning methods are widely used in existing research on cloud load balancing. However, there is still a problem with acquiring noisy multilayered fluctuations in workload due to the limited resource-level provisioning. The long short-term memory (LSTM) model plays a vital role in the prediction of server load and workload provisioning. This research presents a hybrid model using deep learning with Particle Swarm Intelligence and Genetic Algorithm (“DPSO-GA”) for dynamic workload provisioning in cloud computing. The proposed model works in two phases. The first phase utilizes a hybrid PSO-GA approach to address the prediction challenge by combining the benefits of these two methods in fine-tuning the Hyperparameters. In the second phase, CNN-LSTM is utilized. Before using the CNN-LSTM approach to forecast the consumption of resources, a hybrid approach, PSO-GA, is used for training it. In the proposed framework, a one-dimensional CNN and LSTM are used to forecast the cloud resource utilization at various subsequent time steps. The LSTM module simulates temporal information that predicts the upcoming VM workload, while a CNN module extracts complicated distinguishing features gathered from VM workload statistics. The proposed model simultaneously integrates the resource utilization in a multi-resource utilization, which helps overcome the load balancing and over-provisioning issues. Comprehensive simulations are carried out utilizing the Google cluster traces benchmarks dataset to verify the efficiency of the proposed DPSO-GA technique in enhancing the distribution of resources and load balancing for the cloud. The proposed model achieves outstanding results in terms of better precision, accuracy and load allocation.

ABCNet: A comprehensive highway visibility prediction model based on attention, Bi-LSTM and CNN.

Meteorological disasters along highways significantly reduce road traffic efficiency. Low visibility caused by heavy fog is a severe meteorological disaster that greatly increases highway traffic accidents. Accurately predicting highway visibility and taking timely response measures can reduce the impact of meteorological disasters and improve traffic safety. We proposed an Attention-based BiLSTM-CNN (ABCNet) model, which synergized attention mechanisms with BiLSTM and CNN technologies to forecast atmospheric visibility more accurately. First, the Bi-LSTM module processed information both forward and backward, capturing intricate temporal dependencies in the model. Second, the multi-head attention mechanism following the Bi-LSTM distilled and prioritized salient features from multiple aspects of the sequence data. Third, the CNN module recognized local spatial features, and a singular attention mechanism refined the feature map after the CNN module, further enhancing the model's accuracy and predictive capability. Experiments showed that the model was accurate, effective, and significantly advanced compared to conventional models. It could fully extract the spatiotemporal characteristics of meteorological elements. The model was integrated into practical systems with positive results. Additionally, this study provides a self-collected meteorological dataset for highways in high-altitude mountainous areas.

MRI-based model for accurate prediction of P53 gene status in gliomas

<abstract> <p>The accurate diagnosis and treatment of gliomas depends largely on the understanding of the P53 gene status. In our study, we presented a robust deep learning model, CTD-RegNet (improved RegNet integrating CNN, vision transformer, and truth discovery), tailored for predicting P53 gene status in gliomas. Our model addressed common challenges of existing deep learning models, such as incomplete feature extraction and uncertainty. First, the model used the RegNet network as a basis for predicting P53 gene mutations by skillfully extracting heterogeneous features. Next, the RegNet network was enhanced by integrating the CNN and ViT modules to optimise feature extraction and computational efficiency. Finally, using the truth discovery algorithm, we iteratively refined model uncertainties, thereby improving prediction accuracy. Our experiments demonstrated the effectiveness of the CTD-RegNet model, achieving an impressive accuracy of 95.57% and an AUC score of 0.9789, outperforming existing P53 gene status prediction models. The non-invasive nature of our model minimised the economic burden and physical and psychological stress on patients, while providing critical insights for accurate clinical diagnosis and treatment of gliomas.</p> </abstract>

A Novel CNN-BiLSTM Ensemble Model With Attention Mechanism for Sit-to-Stand Phase Identification Using Wearable Inertial Sensors.

Sit-to-stand transition phase identification is vital in the control of a wearable exoskeleton robot for assisting patients to stand stably. In this study, we aim to propose a method for segmenting and identifying the sit-to-stand phase using two inertial sensors. First, we defined the sit-to-stand transition into five phases, namely, the initial sitting phase, the flexion momentum phase, the momentum transfer phase, the extension phase, and the stable standing phase based on the preprocessed acceleration and angular velocity data. We then employed a threshold method to recognize the initial sitting and the stable standing phases. Finally, we designed a novel CNN-BiLSTM-Attention algorithm to identify the three transition phases, namely, the flexion momentum phase, the momentum transfer phase, and the extension phase. Fifteen subjects were recruited to perform sit-to-stand transition experiments under a specific paradigm. A combination of the acceleration and angular velocity data features for the sit-to-stand transition phase identification were validated for the model performance improvements. The integration of the CNN, Bi-LSTM, and Attention modules demonstrated the reasonableness of the proposed algorithms. The experimental results showed that the proposed CNN-BiLSTM-Attention algorithm achieved the highest average classification accuracy of 99.5% for all five phases when compared to both traditional machine learning algorithms and deep learning algorithms on our customized dataset (STS-PD). The proposed sit-to-stand phase recognition algorithm could serve as a foundation for the control of wearable exoskeletons and is important for the further development of intelligent wearable exoskeleton rehabilitation robots.

CT-CPI：基于整合CNN模块与Transformer的化合物–蛋白质相互作用深度学习模型

CT-CPI：基于整合CNN模块与Transformer的化合物–蛋白质相互作用深度学习模型

EMViT-Net: A novel transformer-based network utilizing CNN and multilayer perceptron for the classification of environmental microorganisms using microscopic images

Environmental microbes are certainly present in our surroundings since they are essential to the growth and survival of human advancement. The detailed analysis of environmental microorganisms (EMs) is very important to recognize, understand and make use of microbes as well and prevent damage. Extracting the discriminatory features from a limited-size dataset is very challenging for a deep learning model and a pure transformer-based network cannot achieve good classification results on a limited-size dataset due to the lack of muti-scale features. In this study, a novel vision transformer-based deep neural network is proposed by integrating the transformer with CNN for the classification of EM using microscopic images. The proposed network EMViT-Net has three main modules: a transformer module, a CNN module and a multilayer perceptron module. The transformer model extracted multiscale features to generate more discriminatory information from the images. A new separable convolutional parameter-sharing attention (SCPSA) block is integrated with the CNN module in the core of EMViT-Net, which makes the model robust to capture the local and global features, and simultaneously reduces the computational complexity of the model. The data augmentation is performed to introduce the variability in the dataset and counter the problem of overfitting and data imbalance. After extensive experiments and detailed analysis, it has been determined that the proposed model EMViT-Net outperforms the other existing methods and achieves state-of-the-art results with an accuracy of 71.17% which proves the effectiveness of the model for the classification of environmental microbes.

Scale Variant Vehicle Object Recognition by CNN Module of Multi-Pooling-PCA Process

Scale Variant Vehicle Object Recognition by CNN Module of Multi-Pooling-PCA Process