Proposed Network Model Research Articles

Remote sensing image classification method based on improved ShuffleNet convolutional neural network

As a list of remotely sensed data sources is available, the effective processing of remote sensing images is of great significance in practical applications in various fields. This paper proposes a new lightweight network to solve the problem of remote sensing image processing by using the method of deep learning. Specifically, the proposed model employs ShuffleNet V2 as the backbone network, appropriately increases part of the convolution kernels to improve the classification accuracy of the network, and uses the maximum overlapping pooling layer to enhance the detailed features of the input images. Finally, Squeeze and Excitation (SE) blocks are introduced as the attention mechanism to improve the architecture of the network. Experimental results based on several multisource data show that our proposed network model has a good classification effect on the test samples and can achieve more excellent classification performance than some existing methods, with an accuracy of 91%, and can be used for the classification of remote sensing images. Our model not only has high accuracy but also has faster training speed compared with large networks and can greatly reduce computation costs. The demo code of our proposed method will be available at https://github.com/li-zi-qi.

Discriminative spatial-temporal feature learning for modeling network intrusion detection systems

Increasing interest and advancement of internet and communication technologies have made network security rise as a vibrant research domain. Network intrusion detection systems (NIDSs) have developed as indispensable defense mechanisms in cybersecurity that are employed in discovery and prevention of malicious network activities. In the recent years, researchers have proposed deep learning approaches in the development of NIDSs owing to their ability to extract better representations from large corpus of data. In the literature, convolutional neural network architecture is extensively used for spatial feature learning, while the long short term memory networks are employed to learn temporal features. In this paper, a novel hybrid method that learn the discriminative spatial and temporal features from the network flow is proposed for detecting network intrusions. A two dimensional convolution neural network is proposed to intelligently extract the spatial characteristics whereas a bi-directional long short term memory is used to extract temporal features of network traffic data samples consequently, forming a deep hybrid neural network architecture for identification and classification of network intrusion samples. Extensive experimental evaluations were performed on two well-known benchmarks datasets: CIC-IDS 2017 and the NSL-KDD datasets. The proposed network model demonstrated state-of-the-art performance with experimental results showing that the accuracy and precision scores of the intrusion detection model are significantly better than those of other existing models. These results depicts the applicability of the proposed model in the spatial-temporal feature learning in network intrusion detection systems.

Head Pose Estimation Based on Multi-Level Feature Fusion

Head Pose Estimation (HPE) has a wide range of applications in computer vision, but still faces challenges: (1) Existing studies commonly use Euler angles or quaternions as pose labels, which may lead to discontinuity problems. (2) HPE does not effectively address regression via rotated matrices. (3) There is a low recognition rate in complex scenes, high computational requirements, etc. This paper presents an improved unconstrained HPE model to address these challenges. First, a rotation matrix form is introduced to solve the problem of unclear rotation labels. Second, a continuous 6D rotation matrix representation is used for efficient and robust direct regression. The RepVGG-A2 lightweight framework is used for feature extraction, and by adding a multi-level feature fusion module and a coordinate attention mechanism with residual connection, to improve the network’s ability to perceive contextual information and pay attention to features. The model’s accuracy was further improved by replacing the network activation function and improving the loss function. Experiments on the BIWI dataset 7:3 dividing the training and test sets show that the average absolute error of HPE for the proposed network model is 2.41. Trained on the dataset 300W_LP and tested on the AFLW2000 and BIWI datasets, the average absolute errors of HPE of the proposed network model are 4.34 and 3.93. The experimental results demonstrate that the improved network has better HPE performance.

Deep learning-driven underwater polarimetric target detection based on the dispersion of polarization characteristics

Underwater target detection especially in turbidity environments is a crucial and challenging area of study due to its extensive applications. In this work, we propose an underwater target detection method that combines the dispersion of polarization characteristics with a neural network framework. The polarization dispersion distribution features are effective at reducing the influence of the scattering effect of particulate matter in a turbidity environment, and highlighting the polarization state variations, especially in the edge contour features between the target and background. According to the physical detection model of dispersion of polarization characteristics, the neural network is constructed to extract dispersion values of the angle of polarization (AOP) and degree of linear polarization (DOLP) from the underwater polarization image datasets with different turbidity levels, which we then used to train the network to map physical characteristic parameters of the target for the detection. When compared to target detection methods based on light intensity images and polarization characteristic images (AOP and DOLP), the experimental results indicate that the proposed network model with polarization dispersion images has a significant improvement in locating and identifying targets of different materials, particularly in high turbidity underwater environments. These results provide deeper understanding of polarization polarimetric target detection, and further improve the functionality of a polarimetric target detection optical system.

Design of an efficient neural network model for detection and classification of phase loss faults for three-phase induction motor

AbstractIn industrial applications, three-phase induction motors (IMs) are widely used, and they are subjected to many types of faults. One such fault is the loss of a motor phase caused by a blown fuse, a broken wire, mechanical damage, etc. When this fault occurs during motor operation, it continues to rotate but experiences rapid heating, which can ultimately lead to motor failure. Therefore, various protection devices are available to protect the motor against this fault, but most traditional protection devices do not offer a comprehensive classification of such a fault. So, in this paper, an efficient neural network model is presented for detecting and classifying 12 types of phase loss faults for a three-phase induction motor (IM) based on factors such as the unhealthy phase, fault location, and motor action modes (standstill, transient, and steady-state modes). Thus, the main goal of this work is to determine the motor mode during the fault, the defective phase, and its location to help the maintenance team repair the fault quickly. The system is simulated and tested using the “MATLAB/Simulink” software, employing a feed-forward neural network. The simulation results demonstrate that the proposed network achieves correct detection and classification of phase loss faults within a short time frame from the occurrence of the fault. Therefore, the proposed network model proves to be a simple and reliable solution for integration into the protection system of a three-phase IM, enabling the detection and classification of various phase loss faults.

Best low-cost methods for real-time detection of the eye and gaze tracking

Abstract The study of gaze tracking is a significant research area in computer vision. It focuses on real-world applications and the interface between humans and computers. Recently, new eye-tracking applications have boosted the need for low-cost methods. The eye region is a crucial aspect of tracking the direction of the gaze. In this paper, several new methods have been proposed for eye-tracking by using methods to determine the eye area as well as find the direction of gaze. Unmodified webcams can be used for eye-tracking without the need for specialized equipment or software. Two methods for determining the eye region were used: facial landmarks or the Haar cascade technique. Moreover, the direct method, based on the convolutional neural network model, and the engineering method, based on distances determining the iris region, were used to determine the eye’s direction. The paper uses two engineering techniques: drawing perpendicular lines on the iris region to identify the gaze direction junction point and dividing the eye region into five regions, with the blackest region representing the gaze direction. The proposed network model has proven effective in determining the eye’s gaze direction within limited mobility, while engineering methods improve their effectiveness in wide mobility.

IMD-Net: Interpretable multi-scale detection network for infrared dim and small objects.

This study proposed an interpretable multi-scale infrared small object detection network (IMD-Net) design method to improve the precision of infrared small object detection and contour segmentation in complex backgrounds. To this end, a multi-scale object enhancement module was constructed, which converted artificially designed features into network structures. The network structure was used to enhance actual objects and extract shallow detail and deep semantic features of images. Next, a global object response, channel attention, and multilayer feature fusion modules were introduced, combining context and channel information and aggregated information, selected data, and decoded objects. Finally, the multiple loss constraint module was constructed, which effectively constrained the network output using multiple losses and solved the problems of high false alarms and high missed detections. Experimental results showed that the proposed network model outperformed local energy factor (LEF), self-regularized weighted sparse model (SRWS), asymmetric contextual modulation (ACM), and other state of the art methods in the intersection-over-union (IoU) and Fmeasure values by 10.8% and 11.3%, respectively. The proposed method performed best on the currently available datasets, achieving accurate detection and effective segmentation of dim and small objects in various infrared complex background images.

Incep-FrictionNet-Based Pavement Texture Friction Level Classification Prediction Method

Pavement skid resistance is crucial for driving safety, and pavement texture significantly impacts skid resistance performance. To realize the application of pavement texture data in assessing pavement skid resistance performance, this paper proposes a convolutional neural network model based on the InceptionV4 module to predict the pavement friction level from the pavement texture dataset. The surface texture data of indoor test-rutted slabs were collected using a portable laser scanner. The surface friction coefficient of rutted slabs was measured using a pendulum tribometer. After data pre-processing, a total of nine types of texture data that are in the range of 0.4 to 0.8 skid resistance levels are selected at an interval of 0.05 for training, validation, and testing of the network model. The same dataset and training parameters were also used to train a conventional convolutional network model for comparison. The results showed that the proposed network model achieved 97.89% classification accuracy on the test set, which was 11.94 percentage points higher than the comparison model. This demonstrates that the proposed model in this paper can evaluate pavement friction levels by non-contact scanning of textures and has higher evaluation accuracy.

Variation Analysis Method Based on Product Feature Information Network

Abstract Dimensional and geometric variations are significant factors of products at the manufacturing stage. Because of these variations, the physical appearance or functionality of the final product may deviate from expectations. As of the present, research on variation analysis has been conducted at the feature level. To model the information and analyze the variation transfers of products, a graphical model is constructed by using the product feature and information. Through analysis of the relationship between the product and network model, a modeling process for the feature information network is proposed. Nodes, lines, and constraints in the network are defined in detail, and the dimension unit is defined to represent the dimension information within a part. Variations caused by connections between parts are divided into two categories of influence. Combining the dimension unit and the influence between parts, a variation analysis process is devised based on the proposed network model. To verify the effectiveness and feasibility of the proposed method, a case study is performed based on the grand assembly of a hull block. The result shows that the product can be modeled and the variation can be analyzed by the proposed network model.

MLGPnet: Multi-granularity neural network for 3D shape recognition using pyramid data

This paper presents a Multi-Granularity 3D shape recognition network comprising point-granularity, line-granularity, and Pyramid-granularity networks, as well as multi-granularity convolutional layers (MLGPnet). The network takes pyramid data with high-level features generated from mesh data as input. The point-granularity, line-granularity, and pyramid-granularity networks respectively generate features at the point, line, and pyramid levels. Finally, two multi-granularity convolutional layers merge the features from these different levels to generate more efficient 3D shape global features. Compared to some classical 3D shape recognition network models, the proposed network achieves superior results on three publicly general-purpose datasets. Notably, among all mesh-based recognition networks, the proposed network demonstrates the best recognition accuracy and retrieval rate. Furthermore, the proposed network model performs better in terms of training time and model complexity, with faster training time and fewer model parameters, resulting in faster recognition speed.

Rumor detection methodology based on sentiment analysis and the transformer model with decision-level fusion

The use of transformer models in natural language processing (NLP) has gained significant attention in recent years due to their exceptional performance in various language tasks. This paper explores the application of transformer models in rumor detection, the relevant research on rumor detection, the use of transformer models, and the techniques used to boost the models performance. Ultimately, the purpose of this paper is to provide insight into the potential of transformer models in detecting rumors on social media. Unlike other rumor-detecting models, the author adds a sentiment analysis model as a supplement to rumor detection. Also, to address the issue of insufficient information in early-stage comments on rumors, this paper proposes a decision-level fusion method before the output layer, which effectively utilizes information from different sources and minimizes the negative impact of insufficient data sources. The early-stage rumor detection accuracy of the model is greatly enhanced by this method, therefore, the articles main contributions can be regarded as follows: First, this paper proposes a combination of an aspect level text sentiment analysis method according to syntactic features, gated recurrent units, and a self-attention mechanism. Experimental findings demonstrate that, compared to the original model without taking the sentiment analysis method into account, the proposed network model has advantages in accuracy and Macro F1 evaluation indexes. Second, a cross-text rumor-detecting method based on Decision-level fusion is proposed. Its advantage is that when the cross-text data source is incomplete and a certain text is missing, another text can be used to continue the analysis. Experimental findings show the effectiveness of this method in improving the accuracy of emotion recognition by integrating data from different modes. Third, a comparison is conducted between the performance of the Transformer-sentiment model and other related models, Text-CNN, Bi-LSTM, etc. The result shows that this integrated Transformer-sentiment model can not only solve the rumor detection tasks at higher accuracy, but can also overcome the shortcomings of the lack of datasets, which means that the model is more robust, and is able to detect rumors at the early stage of the rumor spreading process.

Computer vision-based six layered ConvNeural network to recognize sign language for both numeral and alphabet signs

People who have trouble communicating verbally are often dependent on sign language, which can be difficult for most people to understand, making interaction with them a difficult endeavor. The Sign Language Recognition (SLR) system takes an input expression from a hearing or speaking-impaired person and outputs it in the form of text or voice to a normal person. The existing study related to the Sign Language Recognition system has some drawbacks, such as a lack of large datasets and datasets with a range of backgrounds, skin tones, and ages. This research efficiently focuses on Sign Language Recognition to overcome previous limitations. Most importantly, we use our proposed Convolutional Neural Network (CNN) model, “ConvNeural”, in order to train our dataset. Additionally, we develop our own datasets, “BdSL_OPSA22_STATIC1” and “BdSL_OPSA22_STATIC2”, both of which have ambiguous backgrounds. “BdSL_OPSA22_STATIC1” and “BdSL_OPSA22_STATIC2” both include images of Bangla characters and numerals, a total of 24,615 and 8437 images, respectively. The “ConvNeural” model outperforms the pre-trained models with accuracy of 98.38% for “BdSL_OPSA22_STATIC1” and 92.78% for “BdSL_OPSA22_STATIC2”. For “BdSL_OPSA22_STATIC1” dataset, we get precision, recall, F1-score, sensitivity and specificity of 96%, 95%, 95%, 99.31% , and 95.78% respectively. Moreover, in case of “BdSL_OPSA22_STATIC2” dataset, we achieve precision, recall, F1-score, sensitivity and specificity of 90%, 88%, 88%, 100%, and 100% respectively.

Multivariable System Prediction Based on TCN-LSTM Networks with Self-Attention Mechanism and LASSO Variable Selection.

Intelligent prediction of key output variables that are difficult to measure online in complex systems has important research significance. In this paper, by using the least absolute shrinkage and selection operator (LASSO) algorithm to analyze the principal elements of input variables, a temporal convolutional network fused with long short-term memory (TCN-LSTM) network and self-attention mechanism (SAM) is designed to realize dynamic modeling of multivariate feature sequences. For complex processes with multiple input variables, each variable has different effects on the output, so it is necessary to use the LASSO algorithm to perform regression analysis on the input and output data for selecting the principal component variables and reducing the redundancy and computation burden of the network. The TCN network is used to extract the features of the input variables efficiently. The long-term memory performance of time series is enhanced by applying an LSTM network. The multihead SAM is used to optimize the network, and the role of key features is enhanced by assigning weights with probability to further improve the accuracy of sequence prediction. Finally, by comparison with the existing network model, the offline data generated by the high and low converters in the synthetic ammonia industry is used to predict the CO content so as to verify the superiority and applicability of the proposed network model.

A Multi-Scale Recursive Attention Feature Fusion Network for Image Super-Resolution Reconstruction Algorithm

In recent years, deep convolutional neural networks (CNNs) have made significant progress in single-image super-resolution (SISR) tasks. Despite their good performance, the single-image super-resolution task remains a challenging one due to problems with underutilization of feature information and loss of feature details. In this paper, a multi-scale recursive attention feature fusion network (MSRAFFN) is proposed for this purpose. The network consists of three parts: a shallow feature extraction module, a multi-scale recursive attention feature fusion module, and a reconstruction module. The shallow features of the image are first extracted by the shallow feature extraction module. Then, the feature information at different scales is extracted by the multi-scale recursive attention feature fusion network block (MSRAFFB) to enhance the channel features of the network through the attention mechanism and fully fuse the feature information at different scales in order to improve the network’s performance. In addition, the image features at different levels are integrated through cross-layer connections using residual connections. Finally, in the reconstruction module, the upsampling capability of the deconvolution module is used to enlarge the image while extracting its high-frequency information in order to obtain a sharper high-resolution image and achieve a better visual effect. Through extensive experiments on a benchmark dataset, the proposed network model is shown to have better performance than other models in terms of both subjective visual effects and objective evaluation metrics.

Automatic Detection and Segmentation of Brain Hemorrhage Based on Improved U-Net Model.

Brain hemorrhage is one of the leading causes of death due to the sudden rupture of a blood vessel in the brain, resulting in bleeding in the brain parenchyma. The early detection and segmentation of brain damage are extremely important for prompt treatment. Some previous studies focused on localizing cerebral hemorrhage based on bounding boxes without specifying specific damage regions. However, in practice, doctors need to detect and segment the hemorrhage area more accurately. In this paper, we propose a method for automatic brain hemorrhage detection and segmentation using the proposed network models, which are improved from the U-Net by changing its backbone with typical feature extraction networks, i.e., DenseNet-121, ResNet-50, and MobileNet-V2. The U-Net architecture has many outstanding advantages. It does not need to do too many preprocessing techniques on the original images and it can be trained with a small dataset providing low error segmentation in medical images. We use the transfer learning approach with the head CT dataset gathered on Kaggle including two classes, bleeding and non-bleeding. Besides, we give some comparison results between the proposed models and the previous works to provide an overview of the suitable model for cerebral CT images. On the head CT dataset, our proposed models achieve a segmentation accuracy of up to 99%.

Research on Integrated Energy Distributed Sharing in Distribution Network Considering AC Power Flow and Demand Response

Under the constraint of the AC power flow architecture considering reactive power regulation, the examination of integrated energy distributed transactions among multiple subsystems can promote the research in the field of energy sharing. It is difficult to fully cover the consideration of AC power flow, demand response, integrated energy, and other factors in traditional related research. In response, a study is therefore conducted in this paper on integrated energy sharing in the distribution network. First, this paper introduces the system operation framework of the proposed distribution network model, and explains the interaction between all the players. Secondly, a distribution network power flow model and an integrated energy subsystem model are respectively. In particular, the subsystem model specifically considers new energy, demand response, integrated energy, and other factors. Then, a cooperative game model is constructed based on the cooperative relationship among subsystems in the distribution network system, followed by the analysis of the benefits brought by cooperation to the distribution network and the subsystems themselves. Finally, a distributed solution flow is established for the model based on the Alternating Direction Method of Multipliers (ADMM) algorithm. The results of the example analysis reveal the effectiveness of the model proposed in increasing the degree of energy utilization and further absorbing new energy in the distribution network system, each subsystem can generate up to 12% more absorption capacity than it would otherwise operate separately to accommodate more renewable energy in the distribution system.

CNN-based pavement defects detection using grey and depth images

This paper introduces a method for detecting pavement defects based on convolutional neural networks. First, grey and depth image data were acquired using a 3D pavement information collection system, followed by pre-processing and labelling of the data. Subsequently, two network structures were developed to accommodate the image data characteristics: classic U-shaped and double-headed structures. Attention modules were integrated into the models to enhance the accuracy of defect detection. Finally, a quantitative analysis of four types of pavement defects was conducted. The numerical evaluation results demonstrated that training the network with a combination of grey and depth images significantly improves the detection accuracy, resulting in a 10% enhancement in mean intersection over union (MIoU). The proposed model attained a global pixel accuracy (GPA) of 97.36% and an MIoU of 80.28%. The proposed network model was found to have an increased focus on the pavement defect areas, making it highly effective.

Improved YOLOv3 Integrating SENet and Optimized GIoU Loss for Occluded Pedestrian Detection.

Occluded pedestrian detection faces huge challenges. False positives and false negatives in crowd occlusion scenes will reduce the accuracy of occluded pedestrian detection. To overcome this problem, we proposed an improved you-only-look-once version 3 (YOLOv3) based on squeeze-and-excitation networks (SENet) and optimized generalized intersection over union (GIoU) loss for occluded pedestrian detection, namely YOLOv3-Occlusion (YOLOv3-Occ). The proposed network model considered incorporating squeeze-and-excitation networks (SENet) into YOLOv3, which assigned greater weights to the features of unobstructed parts of pedestrians to solve the problem of feature extraction against unsheltered parts. For the loss function, a new generalized intersection over unionintersection over groundtruth (GIoUIoG) loss was developed to ensure the areas of predicted frames of pedestrian invariant based on the GIoU loss, which tackled the problem of inaccurate positioning of pedestrians. The proposed method, YOLOv3-Occ, was validated on the CityPersons and COCO2014 datasets. Experimental results show the proposed method could obtain 1.2% MR-2 gains on the CityPersons dataset and 0.7% mAP@50 improvements on the COCO2014 dataset.

A classification method for soybean leaf diseases based on an improved ConvNeXt model

Deep learning technologies have enabled the development of a variety of deep learning models that can be used to detect plant leaf diseases. However, their use in the identification of soybean leaf diseases is currently limited and mostly based on machine learning methods. In this investigation an enhanced deep learning network model was developed to recognize soybean leaf diseases more accurately. The improved network model consists of three parts: feature extraction, attention calculation, and classification. The dataset used was first diversified through data augmentation operations such as random masking to enhance network robustness. An attention module was then used to generate feature maps at various depths. This increased the network’s focus on discriminative features, reduced background noise, and enabled the use of the LeakyReLu activation function in the attention module to prevent situations in which neurons fail to learn when the input is negative. Finally, the extracted features were then integrated using a fully connected layer, and the predicted disease category inferred to improve the classification accuracy of soybean leaf diseases. The average recognition accuracy of the improved network model for soybean leaf diseases was 85.42% both higher than the six deep learning comparison models (ConvNeXt (66.41%), ResNet50 (72.22%), Swin Transformer (77.00%), MobileNetV3 (67.27%), ShuffleNetV2 (59.89%), and SqueezeNet (72.92%)), thus proving the effectiveness of the improved method.The model proposed in this paper was also tested on the grapevine leaf dataset, and the performance ability of the improved network model remained due to other common network models, and overall the proposed network model was very effective in leaf disease identification.

Image-to-image translation for improved digital holographic reconstruction based on a generative adversarial network learning framework

Based on the generative-discriminative model, a digital holographic reconstruction generative adversarial network is established (DHR-GAN), in which the objective function is optimized on the original model to evaluate the perceptual holographic image. Performing the goals of different optical characteristics, the experimental acquisition system of digital holographic images is designed and constructed for preparing the digital holographic reconstructed image dataset (DHR-dataset), which achieves supervised training and testing of DHR-GAN. From an extensive qualitative and quantitative comparative discussion, the reconstruction results are more stable, with higher contrast and sharper local details, demonstrating the effectiveness of the proposed network model.