Maximum Pooling Research Articles

An Efficient Homomorphic Argmax Approximation for Privacy-Preserving Neural Networks

Privacy-preserving neural networks offer a promising solution to train and predict without user privacy leakage, and fully homomorphic encryption (FHE) stands out as one of the key technologies, as it enables homomorphic operations over encrypted data. However, only addition and multiplication homomorphisms are supported by FHE, and thus, it faces huge challenges when implementing non-linear functions with ciphertext inputs. Among the non-linear functions in neural networks, one may refer to the activation function, the argmax function, and maximum pooling. Inspired by using a composition of low-degree minimax polynomials to approximate sign and argmax functions, this study focused on optimizing the homomorphic argmax approximation, where argmax is a mathematical operation that identifies the index of the maximum value within a given set of values. For the method that uses compositions of low-degree minimax polynomials to approximate argmax, in order to further reduce approximation errors and improve computational efficiency, we propose an improved homomorphic argmax approximation algorithm that includes rotation accumulation, tree-structured comparison, normalization, and finalization phases. And then, the proposed homomorphic argmax algorithm was integrated into a neural network structure. Comparative experiments indicate that the network with our proposed argmax algorithm achieved a slight increase in accuracy while significantly reducing the inference latency by 58%, as the homomorphic sign and rotation operations were rapidly reduced.

Intelligent algorithm based on deep learning to predict the dosage for anesthesia: A study on prediction of drug efficacy based on deep learning.

Anesthetic drugs play a vital role during surgery, however, due to individual differences and complex physiological mechanisms, the prediction of anesthetic drug dosage has always been a challenging problem. In this study, we propose a model for predicting the dosage of anesthetic drugs based on deep learning to help anesthesiologists better control their dosage during surgical procedures. We design a model based on the artificial neural network to predict the dosage of preoperative anesthetic, and use the SELU activation function and the loss function for weighted regularization to solve the problem of unbalanced sample. Moreover, we design a CNN-based model for the prior extraction of intraoperative features by using a 7 × 1 convolution kernel to enhance the receptive field, and combine maximum pooling and average pooling to extract key features while eliminating noise. A predictive model based on the LSTM network is designed to predict the intraoperative dosage of the anesthetic, and the bidirectional propagation-based LSTM network is used to improve the ability to learn the trend of changes in the physiological states of the patient during surgery. An attention module is added before the connection layer to appropriately attend to areas containing prominent features. The results of experiments showed that the proposed method reduced values of the MAPE to 15.83% and 12.25% compared with the traditional method in predictions of the preoperative and intraoperative doses of the anesthetic, respectively, and increased the values of to 0.887 and 0.915, respectively. The intelligent anesthesia prediction algorithm designed in this study can effectively predict the dosage of anesthetic drugs needed by patients, assist clinical judgment of anesthetic drug dose, and assist the anesthesiologists to ensure the smooth progress of the operation.

A bearing fault diagnosis method based on M-SSCNN and M-LR attention mechanism

Bearing fault diagnosis is vital for mechanical maintenance and fault prediction. It ensures equipment safety, extends lifespan, reduces maintenance costs, and improves production efficiency. Nevertheless, it should be acknowledged that some existing diagnostic methods have achieved high accuracy rates in certain scenarios. However, the challenge lies in their limited generalization capabilities, which can lead to reduced accuracy when applied to diverse or unseen conditions. In this study, we proposed a new bearing fault diagnosis method to address the issue of low accuracy caused by the inadequate generalization of models in the process of rolling bearing fault diagnosis. The method is based on a multi-scale sliding convolution neural network and multi-level residual attention mechanism, the model exhibits high accuracy, strong generalization capability, and lightweight structure. Firstly, the time domain signal of the bearing vibration is converted into a two-dimensional time–frequency map, and the image is pixel-segmented using superpixel segmentation techniques. Next, a multi-scale parallel convolution approach is used to extract features to improve the adaptability and robustness of the model to objects of different sizes and scales. Sliding convolution is used instead of pooling to avoid the problem of feature loss caused by maximum pooling and average pooling. A multi-level attention mechanism is then introduced for all stacked channels to focus on the more important and critical information of the module, and residual connections are added to prevent degradation of the network performance. Finally, the proposed method is passed through the fully connected layer for classification using the Softmax classifier. Experimental verification using public datasets and experimental data of our research group shows that the proposed method has better performance than the existing diagnostic methods and diagnostic models. The proposed method offers an advanced and innovative solution in the domain of bearing fault diagnosis.

Research on inter-shaft bearing fault diagnosis method based on STFT-CNN modeling

Inter-shaft bearings are an essential component of aircraft engines, and their operational status determines the safety of aircraft engine operation. Therefore, to improve the accuracy of fault type prediction and enrich the feature information in vibration signals of aircraft engine inter-shaft bearings, this paper proposes an STFT-CNN model based on the AlexNet architecture, extending its application to the research of aircraft engine inter-shaft bearing fault diagnosis. This approach addresses the common reliance on personnel experience for fault type diagnosis in traditional aircraft engine inter-shaft bearing fault diagnosis. Firstly, real vibration fault signals from inter-shaft bearings are collected through experiments to enrich feature information in non-stationary signals using STFT time-frequency methods. Secondly, utilizing the high interpretability of the STFT-CNN model, fault feature data from inter-shaft bearings under various operating conditions are extracted to refine our understanding of fault feature information. Finally, leveraging the robustness of the STFT-CNN model, fault types are classified and predicted. The training process involves comparative analysis using different pooling algorithms, time-frequency analysis methods, and various deep learning network models. The results demonstrate that the STFT-CNN model, employing the maximum pooling algorithm, outperforms other models in predicting inter-shaft bearing faults, achieving an average fault prediction accuracy of 98.8% .

MACN: A cascade defect detection for complex background based on mixture attention mechanism

AbstractDefect detection in complex background is a critical issue. To address this issue, this paper proposes the mixture attention mechanism cascade network, in which the new channel attention network is linked with the spatial attention network to create an effective mixed attention network that takes advantage of their respective advantages, adaptively suppresses background noise, and highlights defect features. To ensure the efficiency and effectiveness of effective mixed attention network, the new channel attention network splices the output features of the global average pooling layer and the global maximum pooling layer and then sends the spliced features into a shared network, which is a one‐dimensional convolutional network, and uses cross‐channel interaction for fusion. Furthermore, in order to provide more discriminative feature representation, the authors extract the intermediate features of the region proposal network and input them into effective mixed attention network. Finally, the cascade head is used to refine the predicted bounding box to achieve high‐quality defect location. To demonstrate the superiority and usefulness of this method, it is compared to the latest method using widely used PCB and NEU data sets. A large number of trials demonstrate that this strategy outperforms other methods for detecting defects in complicated backgrounds.

PointMM: Point Cloud Semantic Segmentation CNN under Multi-Spatial Feature Encoding and Multi-Head Attention Pooling

For the actual collected point cloud data, there are widespread challenges such as semantic inconsistency, density variations, and sparse spatial distribution. A network called PointMM is developed in this study to enhance the accuracy of point cloud semantic segmentation in complex scenes. The main contribution of PointMM involves two aspects: (1) Multi-spatial feature encoding. We leverage a novel feature encoding module to learn multi-spatial features from the neighborhood point set obtained by k-nearest neighbors (KNN) in the feature space. This enhances the network’s ability to learn the spatial structures of various samples more finely and completely. (2) Multi-head attention pooling. We leverage a multi-head attention pooling module to address the limitations of symmetric function-based pooling, such as maximum and average pooling, in terms of losing detailed feature information. This is achieved by aggregating multi-spatial and attribute features of point clouds, thereby enhancing the network’s ability to transmit information more comprehensively and accurately. Experiments on publicly available point cloud datasets S3DIS and ISPRS 3D Vaihingen demonstrate that PointMM effectively learns features at different levels, while improving the semantic segmentation accuracy of various objects. Compared to 12 state-of-the-art methods reported in the literature, PointMM outperforms the runner-up by 2.3% in OA on the ISPRS 3D Vaihingen dataset, and achieves the third best performance in both OA and MioU on the S3DIS dataset. Both achieve a satisfactory balance between OA, F1, and MioU.

HP3D-V2V: High-Precision 3D Object Detection Vehicle-to-Vehicle Cooperative Perception Algorithm.

Cooperative perception in the field of connected autonomous vehicles (CAVs) aims to overcome the inherent limitations of single-vehicle perception systems, including long-range occlusion, low resolution, and susceptibility to weather interference. In this regard, we propose a high-precision 3D object detection V2V cooperative perception algorithm. The algorithm utilizes a voxel grid-based statistical filter to effectively denoise point cloud data to obtain clean and reliable data. In addition, we design a feature extraction network based on the fusion of voxels and PointPillars and encode it to generate BEV features, which solves the spatial feature interaction problem lacking in the PointPillars approach and enhances the semantic information of the extracted features. A maximum pooling technique is used to reduce the dimensionality and generate pseudoimages, thereby skipping complex 3D convolutional computation. To facilitate effective feature fusion, we design a feature level-based crossvehicle feature fusion module. Experimental validation is conducted using the OPV2V dataset to assess vehicle coperception performance and compare it with existing mainstream coperception algorithms. Ablation experiments are also carried out to confirm the contributions of this approach. Experimental results show that our architecture achieves lightweighting with a higher average precision (AP) than other existing models.

3D attention-focused pure convolutional target detection algorithm for insulator defect detection

To ensure the timely detection of safety hazards in transmission lines and to enhance accurately the detection of insulator defects in complicated environments, this study proposes a 3D attention-focused pure convolutional target detection algorithm (CMYOLOv7) based on you only look once v7 (YOLOv7) for defect detection on insulators in complicated environments. Firstly, to address the incapacity of focusing on the target in the backbone feature extraction networks, this study proposes a focused pure convolutional feature extraction module (ConvSimCB) to enhance the extraction and focus capability on insulator defect features. Secondly, to solve the problem of loss of key detail feature information caused by maximum pooling in spatial pyramid pooling module (SPPCSPC), this study proposes a mixed spatial pyramid pooling module (MIXPCSPC) to retain abundant image texture detail information and increase accuracy in detection of tiny insulator defects. Finally, a lightweight generic upsampling operator (CARAFE) is introduced to enhance the feature map resolution to address image distortion caused by the Nearest Neighbor Method of upsampling. This study proposed CMYOLOv7 achieves 98.37% precision, 90.59% recall, 95.68% mean average precision (MAP), and 94% F1 score, higher than YOLOv7 by 0.61%, 8.64%, 5.41%, and 5%.

Joint estimation model for FSO channel parameters and performance evaluation based on CNNs.

Free space optical (FSO) communication systems experience turbulence-induced fading. As a possible solution, adaptive transmission, which adjusts transmitter parameters based on instantaneous channel state information (CSI), can be used. Most of the existing channel estimation methods ignore the impact of detection noise at the receiver, which will lead to additional estimation errors. In this paper, a joint estimation model based on convolutional neural networks (CNNs) is proposed to estimate detection noise and turbulence fading parameters. We obtained turbulence channel simulation data sets considering the background of detection noise based on the edge probability distribution function of the receive signal. The training of the CNN estimator is carried out through maximum pooling, adaptive learning rate, and regularization, ultimately accurately estimating channel characteristics based on the optimal output results of the network. The simulation results show that the proposed CNN joint estimator performs better in high-detection-noise environments compared with traditional maximum likelihood estimators, and it has better generalization ability in different real atmospheric environments.

BIOMEDICAL IMAGE SEGMENTATION BASED ON DEEP LEARNING ALGORITHMS

A new biomedical image segmentation method based on deep learning networks has been constructed. Under the framework of deep learning, a dual-branch deep learning network structure was designed to perform average pooling and maximum pooling on input image data, respectively. The results of pooling processing are sent to multi-layer convolution for further processing, where 2D convolution and dilated convolution are used, respectively, and the more flexible SoftMax function is selected for activation processing. Multiple fully connected processes were used between each link and between two branches to form better fusion criteria. The experimental results show that our method has a more ideal segmentation effect in both homologous and heterogeneous training segmentation experiments, with AC, SE, and SP indicators reaching over 95%, 84%, and 99%, respectively.

Ensemble fusion model for improved lung abnormality classification: Leveraging pre-trained models

Lung abnormalities pose significant health concerns, underscoring the need for swift and accurate diagnoses to facilitate timely medical intervention. This study introduces a novel methodology for the sub-classification of lung abnormalities within chest X-rays captured via smartphones. An accurate and timely diagnosis of lung abnormalities is essential for the successful implementation of appropriate therapy. In this paper, we propose a novel approach using a Convolutional neural network (CNN) with three maximum pooling layers and early fusion for sub-classifying lung abnormalities from chest Xrays. Based on the kind of abnormality, the CheXpert dataset is divided into 13 sub-classes, each of which is trained using a different sub-model. An early fusion procedure is then used to integrate the outputs of the sub-model.•3M-CNN (Method 1): We employed a Convolutional Neural Network (CNN) with three max pooling layers and an early fusion strategy to train dedicated sub-models for each of the 13 distinct sub-classes of lung abnormalities using the CheXpert dataset.•Ensemble Model (Method 2): Our ‘Ensemble model’ integrated the outputs of the trained sub-models, providing a powerful approach for the sub-classification of lung abnormalities.•Exceptional Accuracy: Our ‘3M-CNN’ and ‘fused model’ achieved an accuracy of 98.79%, surpassing established methodologies, which is beneficial in resource-constrained environments embracing smartphone-based imaging.

A Refined Wind Power Forecasting Method with High Temporal Resolution Based on Light Convolutional Neural Network Architecture

With a large proportion of wind farms connected to the power grid, it brings more pressure on the stable operation of power systems in shorter time scales. Efficient and accurate scheduling, operation control and decision making require high time resolution power forecasting algorithms with higher accuracy and real-time performance. In this paper, we innovatively propose a high temporal resolution wind power forecasting method based on a light convolutional architecture—DC_LCNN. The method starts from the source data and novelly designs the dual-channel data input mode to provide different combinations of feature data for the model, thus improving the upper limit of the learning ability of the whole model. The dual-channel convolutional neural network (CNN) structure extracts different spatial and temporal constraints of the input features. The light global maximum pooling method replaces the flat operation combined with the fully connected (FC) forecasting method in the traditional CNN, extracts the most significant features of the global method, and directly performs data downscaling at the same time, which significantly improves the forecasting accuracy and efficiency of the model. In this paper, the experiments are carried out on the 1 s resolution data of the actual wind field, and the single-step forecasting task with 1 s ahead of time and the multi-step forecasting task with 1~10 s ahead of time are executed, respectively. Comparing the experimental results with the classical deep learning models in the current field, the proposed model shows absolute accuracy advantages on both forecasting tasks. This also shows that the light architecture design based on simple deep learning models is also a good solution in performing high time resolution wind power forecasting tasks.

RPEA: A Residual Path Network with Efficient Attention for 3D pedestrian detection from LiDAR point clouds

Efficiently detecting pedestrians from 3D point cloud data is a significantly challenging perception task in numerous robotic and autonomous driving applications, primarily because of the sparsity of point cloud data representing pedestrian objects and the significant deformations in pedestrian body poses. To address these challenges, we present a Residual Path network with Efficient Attention (RPEA), an end-to-end trainable single-stage 3D pedestrian detection network. We first introduce the Residual Path (ResPath) architecture, which incorporates multiple residual blocks to retain the spatial information lost during downsampling and combines features of different resolution scales. To suppress noise in point clouds while generalizing various pedestrian representations, we propose an efficient Channel Attention module with Average and Maximum pooling strategies (CAAM). Experimental results demonstrate that our RPEA ranks first on the JRDB 3D object detection leaderboard among all solutions, while significantly surpassing the ranks second by up to 5.6% average precision. Additionally, our RPEA achieves real-time pedestrian detection at 39 frame-per-second (fps). Since our method has higher accuracy and faster inference, it can be deployed more effectively in vehicles and mobile robots. The code is publicly available at https://github.com/jinzhengguang/RPEA.

SegNet Network Architecture for Deep Learning Image Segmentation and Its Integrated Applications and Prospects

Semantic image segmentation is a crucial task in computer vision, with applications ranging from autonomous driving to medical image analysis. In recent years, deep learning has revolutionized this field, leading to the development of various neural network models aimed at improving segmentation accuracy. One such architecture is SegNet, which we explore in this article.SegNet's architecture consists of an encoder network, a corresponding decoder network, and a pixel-wise classification layer. The encoder network, resembling VGG16 with 13 convolutional layers, extracts high-level features from input images. The innovation lies in the decoder network's approach to upsampling, utilizing pooled indices from the encoder's maximum pooling step to perform non-linear up sampling. This eliminates the need for additional learning during up sampling, making SegNet efficient in both storage and computation.SegNet represents an exciting advancement in deep learning image segmentation. Its efficient architecture, memory-conscious design, and potential for real-time applications make it a valuable tool in the field of computer vision with promising integrated applications and prospects.

A Machine-Learning Strategy to Detect Mura Defects in a Low-Contrast Image by Piecewise Gamma Correction.

A detection and classification machine-learning model to inspect Thin Film Transistor Liquid Crystal Display (TFT-LCD) Mura is proposed in this study. To improve the capability of the machine-learning model to inspect panels' low-contrast grayscale images, piecewise gamma correction and a Selective Search algorithm are applied to detect and optimize the feature regions based on the Semiconductor Equipment and Materials International Mura (SEMU) specifications. In this process, matching the segment proportions to gamma values of piecewise gamma is a task that involves derivative-free optimization which is trained by adaptive particle swarm optimization. The detection accuracy rate (DAR) is approximately 93.75%. An enhanced convolutional neural network model is then applied to classify the Mura type through using the Taguchi experimental design method that identifies the optimal combination of the convolution kernel and the maximum pooling kernel sizes. A remarkable defect classification accuracy rate (CAR) of approximately 96.67% is ultimately achieved. The entire defect detection and classification process can be completed in about 3 milliseconds.

Remote sensing scene classification using multi-domain sematic high-order network

Recently, convolutional neural networks (CNNs), which obtain powerful deep features in an end-to-end manner, have achieved powerful performance in remote sensing scene classification. However, the average or maximum pooling operations defined in the spatial domain and coarser-resolution features with high levels cannot extract reliable features and clear boundaries for small-scale targets in remote sensing scene imagery. This paper attempts to address these problems and proposes a multi-domain sematic high-order network for scene classification, named MSHNet. First, wavelet-spatial and detachable pooling blocks defined in the wavelet and spatial domains are inserted at the end of the convolutional block to learn the features in a more structural fusion manner. Second, multi-scale and multi-resolution semantic embedding modules are proposed to take full advantage of the complementary information and effectively maintain the spatial structures of learned deep features. Third, we employ a factorized bilinear coding approach to obtain compact and discriminative second-order features. MSHNet is thoroughly evaluated on two publicly available benchmarks, i.e., AID (Aerial Image Dataset) and NWPU-RESISC45 (Northwestern Polytechnical University-Remote Sensing Image Scene Classification 45). The extensive results illustrate that our MSHNet is competitive with other related multi-scale deep neural networks.

LiteMixer: Cauliflower Disease Diagnosis based on a Novel Lightweight Neural Network

Abstract Cauliflower, a globally cultivated and nutritionally rich crop, confronts significant challenges in quality and yield due to the rising prevalence of diseases. Traditional manual detection methods, suitable for empiricists or plant pathologists, prove inefficient. Furthermore, existing automated disease identification methods in cauliflower often neglect crucial computational performance metrics within computer vision algorithms, such as complexity, inference speed and training time. This study introduces LiteMixer, a novel lightweight model designed to address these challenges. The Lightweight Mixed-Domain Feature Extraction module (LMFE) meticulously captures global image features, followed by a maximum pooling layer that downscales the resulting multidimensional feature matrix. The Plug-and-Play Multi-Scale Lightweight Convolutional Attention Fusion module (MLCAF) integrates multichannel spatial features, connecting to fully connected layers for the final classification. Ablation experiments highlight the effectiveness of the LMFE module coupled with the MLCAF module. Comparative analyses against state-of-the-art and other lightweight models demonstrate LiteMixer achieving the highest accuracy in identifying cauliflower diseases at 99.86%. Notably, LiteMixer exhibits optimal computational performance, featuring minimal storage costs (4.02M) and the lowest parameter count, resulting in cost-effective computational expenses (16.78M). LiteMixer also boasts the fastest inference time (4.69 ms) and the shortest training time (865 s). This study positions LiteMixer as an advanced solution for diagnosing cauliflower leaf diseases in agricultural settings, underscoring its efficacy and practicality in overcoming the unique challenges associated with cauliflower disease detection within the realm of computer vision algorithms.

Broad-deep network-based fuzzy emotional inference model with personal information for intention understanding in human–robot interaction

A broad-deep fusion network-based fuzzy emotional inference model with personal information (BDFEI) is proposed for emotional intention understanding in human–robot interaction. It aims to understand students’ intentions in the university teaching scene. Initially, we employ convolution and maximum pooling for feature extraction. Subsequently, we apply the ridge regression algorithm for emotional behavior recognition, which effectively mitigates the impact of complex network structures and slow network updates often associated with deep learning. Moreover, we utilize multivariate analysis of variance to identify the key personal information factors influencing intentions and calculate their influence coefficients. Finally, a fuzzy inference method is employed to gain a comprehensive understanding of intentions. Our experimental results demonstrate the effectiveness of the BDFEI model. When compared to existing models, namely FDNNSA, ResNet-101+GFK, and HCFS, the BDFEI model achieved superior accuracy on the FABO database, surpassing them by 12.21%, 1.89%, and 0.78%, respectively. Furthermore, our self-built database experiments yielded an impressive 82.00% accuracy in intention understanding, confirming the efficacy of our emotional intention inference model.

Pulmonary Nodule Detection from 3D CT Image with a Two-Stage Network

Early detection of lung nodules is an important means of reducing the lung cancer mortality rate. In this paper, we propose a three-dimensional CT image lung nodule detection method based on parallel pooling and dense blocks, which includes two parts, i.e., candidate nodule extraction and false positive suppression. First, a dense U-shaped backbone network with parallel pooling is proposed to obtain the candidate nodule probability map. The parallel pooling structure uses multiple pooling operations for downsampling to capture spatial information comprehensively and address the problem of information loss resulting from maximum and average pooling in the shallow layers. Then, a parasitic network with parallel pooling, dense blocks, and attention modules is designed to suppress false positive nodules. The parasitic network takes the multiscale feature maps of the backbone network as the input. The experimental results demonstrate that the proposed method significantly improves the accuracy of lung nodule detection, achieving a CPM score of 0.91, which outperforms many existing methods.

SCGNet: efficient sparsely connected group convolution network for wheat grains classification.

Efficient and accurate varietal classification of wheat grains is crucial for maintaining varietal purity and reducing susceptibility to pests and diseases, thereby enhancing crop yield. Traditional manual and machine learning methods for wheat grain identification often suffer from inefficiencies and the use of large models. In this study, we propose a novel classification and recognition model called SCGNet, designed for rapid and efficient wheat grain classification. Specifically, our proposed model incorporates several modules that enhance information exchange and feature multiplexing between group convolutions. This mechanism enables the network to gather feature information from each subgroup of the previous layer, facilitating effective utilization of upper-layer features. Additionally, we introduce sparsity in channel connections between groups to further reduce computational complexity without compromising accuracy. Furthermore, we design a novel classification output layer based on 3-D convolution, replacing the traditional maximum pooling layer and fully connected layer in conventional convolutional neural networks (CNNs). This modification results in more efficient classification output generation. We conduct extensive experiments using a curated wheat grain dataset, demonstrating the superior performance of our proposed method. Our approach achieves an impressive accuracy of 99.56%, precision of 99.59%, recall of 99.55%, and an F 1-score of 99.57%. Notably, our method also exhibits the lowest number of Floating-Point Operations (FLOPs) and the number of parameters, making it a highly efficient solution for wheat grains classification.