An improved image texture synthesis based on algorithm convolution neural network

Texture synthesis is the hot research topic in the field of computer vision, computer graphics and image processing. Sample-based texture synthesis method has been proposed and becomes a new texture tiling technique with the development of the texture mapping and procedural texture synthesis. Image Quilting stitching algorithm is an ideal algorithm for the texture stitching. In this article, by using the image Quilting algorithm to finish the texture transfer and stitch the objective texture image, whose texture style does not exist in the initial image. In experiments, by transferring the style of the human face image and character image respectively, verified the effectiveness of this proposed algorithm.

In the research of virtual hepatic surgery, the synthesis of hepatic texture space and the texture mapping of the hepatic body model are inseparable. Different methods for hepatic volume texture on the authenticity and mapping speed tend to have much difference. Based on computer unified device architecture (CUDA), this paper tries to present a texture synthesis and mapping method for the accelerating of hepatic body, which is used to solve the problem that traditional method under the hepatic volumetric texture synthesis and mapping process cost too much time. This new method may eliminate the traditional serial correlation of texture synthesis. What’s more, it may improve the efficiency of texture synthesis when the multithreading parallel processing for synthesis in the hepatic volumetric texture space in selecting and distributing blocks based on CUDA architecture.

In this work, we design a neural network named MCRNN for classifying signals with slight distinction. This model combines advantages of both Convolutional Neural Network and Recurrent Neural Network, allowing the network to distinguish between long signals with long time-frequency maps. We use an architecture involving both convolutional layers, for extracting high-level features and reduce the dimension of data from time-frequency maps, and recurrent layers, for aggregating long-term dependencies. We apply techniques like Adam optimizer, batch normalization, and softmax layers, obtaining highly competitive results of 99.9% accuracy even in a low SNR of -2dB. Moreover, we conduct extensive experiment through a range of noisy scenarios from -10dB to 30dB. The model can be extended to signal dataset with short time-frequency maps easily. We leverage open source dataset like DeepSig as verification.

Convolutional Neural Networks (CNNs) are popular in deep learning, especially in computer vision. But CNNs are poor at extracting spatial information, such as position and direction of entities in an image. A recently proposed model called Capsule network could effectively learn the spatial relations among entities, but it has weak feature extraction ability. The inception structure could extract multi-scale features. So this paper modifies the inception-v1 structure and adds it into Capsule network to strengthen the feature extraction ability. In the modified inception-v1, the max pooling branch is removed to reduce the loss of feature information. And Batch Normalization (BN) layer is added after each convolution to accelerate convergence and reduce over fitting. To organize categories information, a fully connected layer is added after digit Capsules. This paper conducted experiment on two public datasets, and the results show that the proposed model outperforms the original model in accuracy.

A bearing fault diagnosis method based on an improved convolutional neural network(CNN) is proposed to address the problem of low accuracy of traditional convolutional neural network for rolling bearing fault identification. First, the convolutional kernels of the first convolutional layer of the original network are widened to accommodate the bearing fault signal with one-dimensional input. Then, the number of convolutional kernels is reduced while maintaining the feature extraction capability of the network to ensure the deepening of the network while strongly suppressing the overfitting phenomenon of the network. Finally, the batch normalization(BN) layer is added after the convolutional and fully connected layers of the convolutional neural network to accelerate the convergence of the network and prevent the network from gradient disappearance or gradient explosion. Experimental results demonstrate that the proposed method achieves higher diagnostic accuracy and stability than traditional convolutional neural network.

In the training process of convolutional neural networks (CNN), a batch normalization (BN) layer is often inserted after a convolution layer to accelerate the convergence of CNN training. In this work, we propose a BN processor that supports both the training and inference processes. To speed up the training of CNN, the proposed work develops an efficient dataflow integrating a novel BN processor design and the processing elements for convolution acceleration. We exploited the similarities in the calculations required for the BN forward and backward passes by sharing hardware elements between both passes, therefore reducing the area overhead. In addition to functional verification of the BN processor, we also completed Automatic Placement & Routing (APR) and conducted post-APR simulation on neural network training. Finally, the proposed solution not only significantly speeds up the CNN training process, but also achieves hardware saving.

Intrusion detection plays a critical role in safeguarding computer networks from malicious activities and unauthorized access. Traditional machine learning (ML) models have been widely employed for intrusion detection, but their effectiveness can be limited due to the complex and evolving nature of network attacks. An efficient Convolutional Neural Network (CNN) that utilizes one-dimensional convolutions, batch normalization, and max pooling layers is designed to capture the attack patterns in network traffic data. By leveraging the inherent feature extraction capabilities of CNNs, the proposed architecture demonstrates improved performance in identifying network intrusions compared to traditional ML models. The effectiveness of the novel CNN architecture is evaluated by conducted comprehensive experiments on two benchmark intrusion detection datasets. The designed CNN performance was compared with four other ML models such as logistic regression, k-nearest neighbors, decision trees, and random forest. The experimental results revealed that the proposed CNN architecture outperformed the traditional ML models with highest accuracy of 97.68% and 97.39% and highest F1-score of 97.68% and 97.40% for. UNSW-NB15 and CICIDS2017 datasets, respectively. The proposed CNN architecture serves as a promising alternative to traditional ML models, offering improved performance in identifying and mitigating network attacks.

Homogeneity of appearance attributes of bell peppers is essential for consumers and food industries. This research aimed to develop an in-line sorting system using a deep convolutional neural network (DCNN) which is considered the state-of-the-art in the field of machine vision-based classifications, for grading bell peppers into five classes. According to export standards, the crop should be graded based on maturity stage and size. For that, the fully connected layer in the ResNet50 architecture of DCNN was replaced with a developed classifier block, including a global average-pooling layer, dense layers, batch normalization, and dropout layer. The developed model was trained and evaluated through the five-fold cross-validation method. The required processing time to classify each sample in the proposed model was estimated as 4ms which is fast enough for real-time applications. Accordingly, the DCNN model was integrated with a machine vision-based designed sorting machine. Then, the developed system was evaluated in the in-line phase. The performance parameters in the in-line phase include accuracy, precision, sensitivity, specificity, F1-score, and overall accuracies were 98.7%, 97%, 96.9%, 99%, 96.9%, and 96.9%, respectively. The total rate of sorting the bell pepper was also measured as approximately 3000 sample/h with one sorting line. The proposed sorting system demonstrates a very good capability that allows it to be used in industrial applications. PRACTICAL APPLICATION: A developed intelligent model was integrated with a machine vision-based designed sorting machine for bell peppers. The developed system can sort the crop according to export criteria with an accuracy of 96.9%. The proposed sorting system demonstrated a very good capability that allows it to be used in industrial applications.

Automatic target recognition (ATR) is a challenging task for several computer vision applications. It requires efficient, accurate, and robust methods for target detection and target identification. Deep learning has shown great success in many computer vision applications involving color RGB images. However, the performance of these networks in ATR with infrared sensor data needs further investigation. In this paper, we propose a multistage automatic target detection and recognition (ATDR) system that performs both target detection and target classification on infrared (IR) imagery using deep learning. Our system processes large IR image frames where targets take <1 % of the total number of pixels. First, we train a state-of-the-art object detector you only look once (YOLO) to localize all potential targets in the input image frame. Then, we train a convolutional neural network (CNN) to identify these detections as targets or false alarms. In this second phase, we adapt and analyze the performance of three CNN architectures: a compact and fully connected CNN, VGG16 with batch normalization, and a wide residual neural network (WRN). We also explore the use of a loss function that optimizes directly the area under the receiver operating characteristic (ROC) curve (AUC), and adapt it to our ATR application. To enhance the robustness of the proposed ATR to perturbation and variations introduced during the detection stage, we train our CNN classifiers on automatically detected targets using YOLO, in addition to ground truth bounding boxes and apply selected data augmentation techniques. To simulate real testing environments, where the spatial location of the targets within the image frame is unknown, only YOLO-detected boxes are used during validation. We evaluate our ATDR on a real benchmark dataset that includes different vehicles captured at different resolutions. Our experiments have shown that YOLO can detect most of the targets at the expense of generating a high number of false alarms. We show that the VGG-16 network with batch normalization, which is the best performing model, can correctly identify the classes of the targets, as well as classify the majority of YOLO’s false detections into an additional nontarget class. We also show that the proposed training modification to optimize an AUC-based loss function for ATR proved to be advantageous mainly in identifying difficult targets.

Despite the great success of Convolutional Neural Networks (CNNs) in Computer Vision and Natural Language Processing, the working mechanism behind CNNs is still under extensive discussions and research. Driven by a strong demand for the theoretical explanation of neural networks, some researchers utilize information theory to provide insight into the black box model. However, to the best of our knowledge, employing information theory to quantitatively analyze and qualitatively visualize neural networks has not been extensively studied in the visualization community. In this paper, we combine information entropies and visualization techniques to shed light on how CNN works. Specifically, we first introduce a data model to organize the data that can be extracted from CNN models. Then we propose two ways to calculate entropy under different circumstances. To provide a fundamental understanding of the basic building blocks of CNNs (e.g., convolutional layers, pooling layers, normalization layers) from an information-theoretic perspective, we develop a visual analysis system, CNNSlicer. CNNSlicer allows users to interactively explore the amount of information changes inside the model. With case studies on the widely used benchmark datasets (MNIST and CIFAR-10), we demonstrate the effectiveness of our system in opening the blackbox of CNNs.

The advent of 6G/NextG networks offers numerous benefits, including extreme capacity, reliability, and efficiency. To mitigate emerging security threats, 6G/NextG networks incorporate advanced artificial intelligence algorithms. However, existing studies on intrusion detection predominantly rely on deep neural networks with static components that are not conditionally dependent on the input, thereby limiting their representational power and efficiency. To address these issues, we present the first study to integrate a Mixture of Experts (MoE) architecture for the identification of malicious traffic. Specifically, we use network traffic data and convert the 1D feature array into a 2D matrix. Next, we pass this matrix through a convolutional neural network (CNN) layer, followed by batch normalization and max pooling layers. Subsequently, a sparsely gated MoE layer is used. This layer consists of a set of expert networks (dense layers) and a router that assigns weights to each expert's output. Sparsity is achieved by selecting only the most relevant experts from the full set. Finally, we conduct a series of ablation experiments to demonstrate the effectiveness of our proposed model. Experiments are conducted on the 5G-NIDD dataset, a network intrusion detection dataset generated from a real 5G test network, and the NANCY dataset, which includes cyberattacks from the O-RAN 5G Testbed Dataset. The results show that our introduced approach achieves accuracies of up to 99.96% and 79.59% on the 5G-NIDD and NANCY datasets, respectively. The findings also show that our proposed model offers multiple advantages over state-of-the-art approaches.

In recent years, AI(Artificial Intelligence) has achieved great development in modern society. More and more modern technologies are applied in surveillance and monitoring. Healthcare monitoring is growing ubiquitous in modern wearable devices, such as a smart watch, electrocardiogram (ECG) necklace, smart band. Many sensors are attached to these smart devices to record and monitor physiological signals caused by activities, and then propagated those recorded electrical data to be further processed to give health diagnosis, disease prevention or making a distress call automatically. Obstructive sleep apnea (OSA) is a sleep disorder with a high occurrence in adult people and observed as an autonomous risk factor for circulatory problems such as ischemic heart attacks and stroke. Numerous traditional neural network based methods have been developed to detect OSA, where these methods however could not provide the intended result because they rely on shallow network. In this paper, we propose an effective OSA detection based on Convolutional neural network. Our method first extracts features from Apnea-Electrocardiogram (ECG) recordings using RR-intervals (time interval from one R-wave to the next R-wave in an ECG signal) and then CNN model having three convolution layers and three fully connected layers is trained with extracted features and applied for OSA detection. The first two convolution layers are followed by batch normalization and pooling layer, and softmax is connected to the last fully connected layer to give final decision. Experimental results on extracted feature of Apnea-ECG signal reveal that our model have better results in terms of performance measure sensitivity, specificity and accuracy. It is expected that the related technology can be applied into smart sensors, especially wearable devices.

In recent years, the development of Low Probability of Detection (LPD) communication systems has gained significant attention as a means to enhance communication security. Consequently, the need for effective signal interception technologies capable of detecting such signals has also increased. This paper proposes a novel spectrum sensing method based on Convolutional Neural Networks (CNNs) to determine the presence or absence of signals. The proposed method addresses the limitations of conventional energy detection techniques that rely on fixed thresholds, by learning diverse signal patterns to enable more accurate detection. Received signals are first sampled at a high rate and transformed into frequency-domain representations using the Fast Fourier Transform (FFT). These frequency spectra are then accumulated over time to form two-dimensional spectrograms, which are used as input to the CNN model. The proposed CNN classifier comprises four convolutional layers, along with batch normalization and pooling layers. Simulation results demonstrate that the proposed approach consistently outperforms traditional threshold-based energy detection methods, achieving approximately a 2 dB performance gain across all SNR conditions. Under –6 dB SNR, the method achieves an improvement of about 35% in detection accuracy.

At present, beam pumping units are the most extensively-applied component in rod pumping systems, and the analysis of the indicator diagram of a rod pump is an important means of judging its downhole working condition. However, the synthetic study and judgment of the indicator diagram by manual means has a low efficiency, large error, and poor immediacy, and it is difficult to apply the conclusions in time and accurately to adjust the operating parameters of the pumping units. Moreover, expert systems rely on expert experience and conventional machine learning requires manual pre-selection of geometric features such as moments and vector curves, which will reduce the accuracy of recognition when similar indicator diagrams appear. To solve the above technical defects, in this paper, a deep-learning convolutional neural network (CNN) is proposed using the CNN model based on AlexNet. The automatic recognition of the indicator diagram is thus realized, and, on the basis of previous studies, this model simplifies the structure of the model and takes into account 15 common downhole working conditions of the pumping unit. In this model, the batch normalization (BN) layer is used to replace the local response normalization (LRN) and dropout layers and all kinds of indicator diagrams are put into the same model frame for automatic identification. The experimental application of the measured data shows that the model not only has a short training time, but also has a working-condition diagnosis accuracy of 96.05%, which can solve the deficiencies and defects of artificial identification, expert systems, and conventional machine learning to a certain extent. A deep-learning CNN can provide a new reference for fast working-condition diagnosis of indicator diagram, making indicator-diagram judgment timely and accurate, and thus it is possible to provide a direct basis for parameter adjustment of pumping units.

In order to overcome the effects of posture, illumination, expression and other factors on face recognition, this paper proposes an algorithm which is based on local binary pattern (LBP) and convolutional neural network (CNN). LBP is a texture description method which describes the local texture features of an image. It has good robustness of illumination and posture. CNN can effectively extract the spatial features of images and reduce the dimensions of features. This paper combines the advantages of LBP and CNN to improve the accuracy of face recognition. The CNN in this algorithm has four convolution layers, two max-pooling layers, one activation layer, one fully connected layer, and one output layer. In order to optimize the network structure, batch normalization layer is added after the convolution layer. We get the local binary pattern coded images and put the images as the input of the CNN and train the network. Hence, we can use the well-trained CNN for classification and identification. The Experiments on the CMU-PIE face database show that our algorithm can effectively improve the rate of face recognition.