To see the other types of publications on this topic, follow the link: Modified convolutional neural network.
Journal articles on the topic 'Modified convolutional neural network'
Create a spot-on reference in APA, MLA, Chicago, Harvard, and other styles
Consult the top 50 journal articles for your research on the topic 'Modified convolutional neural network.'
Next to every source in the list of references, there is an 'Add to bibliography' button. Press on it, and we will generate automatically the bibliographic reference to the chosen work in the citation style you need: APA, MLA, Harvard, Chicago, Vancouver, etc.
You can also download the full text of the academic publication as pdf and read online its abstract whenever available in the metadata.
Browse journal articles on a wide variety of disciplines and organise your bibliography correctly.
1
Sapunov, V. V., S. A. Botman, G. V. Kamyshov, and N. N. Shusharina. "Application of Convolution with Periodic Boundary Condition for Processing Data from Cylindrical Electrode Arrays." INFORMACIONNYE TEHNOLOGII 27, no. 3 (2021): 125–31. http://dx.doi.org/10.17587/it.27.125-131.
Full textAbstract:
In this paper, modification of convolutional neural networks for purposes of processing electromyographic data obtained from cylindrical arrays of electrodes was proposed. Taking into account the spatial symmetry of the array, convolution operation was redefined using periodic boundary conditions, which allowed to construct a neural network that is invariant to rotations of electrodes array around its axis. Applicability of the proposed approach was evaluated by constructing a neural network containing a new type of convolutional layer and training it on the open UC2018 DualMyo dataset in order to classify gestures basing on data from a single myobracelet. The network based on the new type of convolution performed better compared to common convolutions when trained on data without augmentation, which indicates that such a network is invariable to cyclic shifts in the input data. Neural networks with modified convolutional layers and common convolutional layers achieved f-1 scores of 0.96 and 0.65 respectively with no augmentation for input data and f-1 scores of 0.98 and 0.96 in case when train-time augmentation was applied. Test data was augmented in both cases. Potentially, proposed convolution can be applied in processing any data with the same connectivity in such a way that allows to adapt time-tested architectural solutions for networks by replacing common convolutions with modified ones.
2
Wasim Khan. "Image Classification using modified Convolutional Neural Network." Journal of Electrical Systems 20, no. 3 (2024): 3465–72. https://doi.org/10.52783/jes.4982.
Full textAbstract:
Image classification is the field of research since decades. With evaluation of new technologies, the performance of image classification has been improved and this is evident by it’s us in routine life. However there are scopes to use the deep learning networks to further improve the complex image classification problems. In this paper, the Convolution neural network based(CNN) image classification is evaluated by changing the parameters of CNN like number of layers, number of neurons, block size of convolution operation etc. The parametric analysis in terms of accuracy number of iteration for convergence is illustrated in result section. The standard dataset of Intel image classification is used for evaluation of performance. The maximum accuracy has been achieved.
3
Iatsenko, D. V., and B. B. Zhmaylov. "IMPROVING THE EFFICIENCY OF THE CONVOLUTIONAL NEURAL NETWORK USING THE METHOD OF INCREASING THE RECEPTIVE FIELD." Vestnik komp'iuternykh i informatsionnykh tekhnologii, no. 195 (September 2020): 18–24. http://dx.doi.org/10.14489/vkit.2020.09.pp.018-024.
Full textAbstract:
In many pattern recognition problems solved using convolutional neural networks (CNN), one of the important characteristics of network architecture is the size of the convolution kernel, since it coincides with the size of the maximum element that can act as a recognition sign. However, increasing the size of the convolution kernel greatly increases the number of tunable network parameters. The method of effective receptive field was first applied on AlexNet in 2012. The practical application of the method of increasing the effective receptive field without increasing convolution kernel size is discussed in this article. A presented example of a small network designed to recognize a fire in apicture demonstrates the use of an effective receptive field which consists of a stack of smaller convolutions. Comparison of a original network with a large convolution core and a modified network with a stack of smaller cores shows that, with equal network characteristics, such as prediction accuracy, prediction time, the number of parameters in the network with an effective receptive field, the number of tunable parameters is significantly reduced.
4
Iatsenko, D. V., and B. B. Zhmaylov. "IMPROVING THE EFFICIENCY OF THE CONVOLUTIONAL NEURAL NETWORK USING THE METHOD OF INCREASING THE RECEPTIVE FIELD." Vestnik komp'iuternykh i informatsionnykh tekhnologii, no. 195 (September 2020): 18–24. http://dx.doi.org/10.14489/vkit.2020.09.pp.018-024.
Full textAbstract:
In many pattern recognition problems solved using convolutional neural networks (CNN), one of the important characteristics of network architecture is the size of the convolution kernel, since it coincides with the size of the maximum element that can act as a recognition sign. However, increasing the size of the convolution kernel greatly increases the number of tunable network parameters. The method of effective receptive field was first applied on AlexNet in 2012. The practical application of the method of increasing the effective receptive field without increasing convolution kernel size is discussed in this article. A presented example of a small network designed to recognize a fire in apicture demonstrates the use of an effective receptive field which consists of a stack of smaller convolutions. Comparison of a original network with a large convolution core and a modified network with a stack of smaller cores shows that, with equal network characteristics, such as prediction accuracy, prediction time, the number of parameters in the network with an effective receptive field, the number of tunable parameters is significantly reduced.
5
Murinto, Murinto, and Sri Winiarti. "Modified particle swarm optimization (MPSO) optimized CNN’s hyperparameters for classification." International Journal of Advances in Intelligent Informatics 11, no. 1 (2025): 133. https://doi.org/10.26555/ijain.v11i1.1303.
Full textAbstract:
This paper proposes a convolutional neural network architectural design approach using the modified particle swarm optimization (MPSO) algorithm. Adjusting hyper-parameters and searching for optimal network architecture from convolutional neural networks (CNN) is an interesting challenge. Network performance and increasing the efficiency of learning models on certain problems depend on setting hyperparameter values, resulting in large and complex search spaces in their exploration. The use of heuristic-based searches allows for this type of problem, where the main contribution in this research is to apply the MPSO algorithm to find the optimal parameters of CNN, including the number of convolution layers, the filters used in the convolution process, the number of convolution filters and the batch size. The parameters obtained using MPSO are kept in the same condition in each convolution layer, and the objective function is evaluated by MPSO, which is given by classification rate. The optimized architecture is implemented in the Batik motif database. The research found that the proposed model produced the best results, with a classification rate higher than 94%, showing good results compared to other state-of-the-art approaches. This research demonstrates the performance of the MPSO algorithm in optimizing CNN architectures, highlighting its potential for improving image recognition tasks.
6
Sun, Kai, Jiangshe Zhang, Junmin Liu, Shuang Xu, Xiangyong Cao, and Rongrong Fei. "Modified Dynamic Routing Convolutional Neural Network for Pan-Sharpening." Remote Sensing 15, no. 11 (2023): 2869. http://dx.doi.org/10.3390/rs15112869.
Full textAbstract:
Based on deep learning, various pan-sharpening models have achieved excellent results. However, most of them adopt simple addition or concatenation operations to merge the information of low spatial resolution multi-spectral (LRMS) images and panchromatic (PAN) images, which may cause a loss of detailed information. To tackle this issue, inspired by capsule networks, we propose a plug-and-play layer named modified dynamic routing layer (MDRL), which modifies the information transmission mode of capsules to effectively fuse LRMS images and PAN images. Concretely, the lower-level capsules are generated by applying transform operation to the features of LRMS images and PAN images, which preserve the spatial location information. Then, the dynamic routing algorithm is modified to adaptively select the lower-level capsules to generate the higher-level capsule features to represent the fusion of LRMS images and PAN images, which can effectively avoid the loss of detailed information. In addition, the previous addition and concatenation operations are illustrated as special cases of our MDRL. Based on MIPSM with addition operations and DRPNN with concatenation operations, two modified dynamic routing models named MDR–MIPSM and MDR–DRPNN are further proposed for pan-sharpening. Extensive experimental results demonstrate that the proposed method can achieve remarkable spectral and spatial quality.
7
Adhari, Firman Maulana, Taufik Fuadi Abidin, and Ridha Ferdhiana. "License Plate Character Recognition using Convolutional Neural Network." Journal of Information Systems Engineering and Business Intelligence 8, no. 1 (2022): 51–60. http://dx.doi.org/10.20473/jisebi.8.1.51-60.
Full textAbstract:
Background: In the last decade, the number of registered vehicles has grown exponentially. With more vehicles on the road, traffic jams, accidents, and violations also increase. A license plate plays a key role in solving such problems because it stores a vehicle’s historical information. Therefore, automated license-plate character recognition is needed. Objective: This study proposes a recognition system that uses convolutional neural network (CNN) architectures to recognize characters from a license plate’s images. We called it a modified LeNet-5 architecture. Methods: We used four different CNN architectures to recognize license plate characters: AlexNet, LeNet-5, modified LeNet-5, and ResNet-50 architectures. We evaluated the performance based on their accuracy and computation time. We compared the deep learning methods with the Freeman chain code (FCC) extraction with support vector machine (SVM). We also evaluated the Otsu and the threshold binarization performances when applied in the FCC extraction method. Results: The ResNet-50 and modified LeNet-5 produces the best accuracy during the training at 0.97. The precision and recall scores of the ResNet-50 are both 0.97, while the modified LeNet-5’s values are 0.98 and 0.96, respectively. The modified LeNet-5 shows a slightly higher precision score but a lower recall score. The modified LeNet-5 shows a slightly lower accuracy during the testing than ResNet-50. Meanwhile, the Otsu binarization’s FCC extraction is better than the threshold binarization. Overall, the FCC extraction technique performs less effectively than CNN. The modified LeNet-5 computes the fastest at 7 mins and 57 secs, while ResNet-50 needs 42 mins and 11 secs. Conclusion: We discovered that CNN is better than the FCC extraction method with SVM. Both ResNet-50 and the modified LeNet-5 perform best during the training, with F measure scoring 0.97. However, ResNet-50 outperforms the modified LeNet-5 during the testing, with F-measure at 0.97 and 1.00, respectively. In addition, the FCC extraction using the Otsu binarization is better than the threshold binarization. Otsu binarization reached 0.91, higher than the static threshold binarization at 127. In addition, Otsu binarization produces a dynamic threshold value depending on the images’ light intensity. Keywords: Convolutional Neural Network, Freeman Chain Code, License Plate Character Recognition, Support Vector Machine
8
Misko, Joshua, Shrikant S. Jadhav, and Youngsoo Kim. "Extensible Embedded Processor for Convolutional Neural Networks." Scientific Programming 2021 (April 21, 2021): 1–12. http://dx.doi.org/10.1155/2021/6630552.
Full textAbstract:
Convolutional neural networks (CNNs) require significant computing power during inference. Smart phones, for example, may not run a facial recognition system or search algorithm smoothly due to the lack of resources and supporting hardware. Methods for reducing memory size and increasing execution speed have been explored, but choosing effective techniques for an application requires extensive knowledge of the network architecture. This paper proposes a general approach to preparing a compressed deep neural network processor for inference with minimal additions to existing microprocessor hardware. To show the benefits to the proposed approach, an example CNN for synthetic aperture radar target classification is modified and complimentary custom processor instructions are designed. The modified CNN is examined to show the effects of the modifications and the custom processor instructions are profiled to illustrate the potential performance increase from the new extended instructions.
9
Prochukhan, Dmytro. "IMPLEMENTATION OF TECHNOLOGY FOR IMPROVING THE QUALITY OF SEGMENTATION OF MEDICAL IMAGES BY SOFTWARE ADJUSTMENT OF CONVOLUTIONAL NEURAL NETWORK HYPERPARAMETERS." Information and Telecommunication Sciences, no. 1 (June 24, 2023): 59–63. http://dx.doi.org/10.20535/2411-2976.12023.59-63.
Full textAbstract:
Background. The scientists have built effective convolutional neural networks in their research, but the issue of optimal setting of the hyperparameters of these neural networks remains insufficiently researched. Hyperparameters affect model selection. They have the greatest impact on the number and size of hidden layers. Effective selection of hyperparameters improves the speed and quality of the learning algorithm. It is also necessary to pay attention to the fact that the hyperparameters of the convolutional neural network are interconnected. That is why it is very difficult to manually select the effective values of hyperparameters, which will ensure the maximum efficiency of the convolutional neural network. It is necessary to automate the process of selecting hyperparameters, to implement a software mechanism for setting hyperparameters of a convolutional neural network. The author has successfully implemented the specified task.
 Objective. The purpose of the paper is to develop a technology for selecting hyperparameters of a convolutional neural network to improve the quality of segmentation of medical images..
 Methods. Selection of a convolutional neural network model that will enable effective segmentation of medical images, modification of the Keras Tuner library by developing an additional function, use of convolutional neural network optimization methods and hyperparameters, compilation of the constructed model and its settings, selection of the model with the best hyperparameters.
 Results. A comparative analysis of U-Net and FCN-32 convolutional neural networks was carried out. U-Net was selected as the tuning network due to its higher quality and accuracy of image segmentation. Modified the Keras Tuner library by developing an additional function for tuning hyperparameters. To optimize hyperparameters, the use of the Hyperband method is justified. The optimal number of epochs was selected - 20. In the process of setting hyperparameters, the best model with an accuracy index of 0.9665 was selected. The hyperparameter start_neurons is set to 80, the hyperparameter net_depth is 5, the activation function is Mish, the hyperparameter dropout is set to False, and the hyperparameter bn_after_act is set to True.
 Conclusions. The convolutional neural network U-Net, which is configured with the specified parameters, has a significant potential in solving the problems of segmentation of medical images. The prospect of further research is the use of a modified network for the diagnosis of symptoms of the coronavirus disease COVID-19, pneumonia, cancer and other complex medical diseases.
10
Luo, Guoliang, Bingqin He, Yanbo Xiong, et al. "An Optimized Convolutional Neural Network for the 3D Point-Cloud Compression." Sensors 23, no. 4 (2023): 2250. http://dx.doi.org/10.3390/s23042250.
Full textAbstract:
Due to the tremendous volume taken by the 3D point-cloud models, knowing how to achieve the balance between a high compression ratio, a low distortion rate, and computing cost in point-cloud compression is a significant issue in the field of virtual reality (VR). Convolutional neural networks have been used in numerous point-cloud compression research approaches during the past few years in an effort to progress the research state. In this work, we have evaluated the effects of different network parameters, including neural network depth, stride, and activation function on point-cloud compression, resulting in an optimized convolutional neural network for compression. We first have analyzed earlier research on point-cloud compression based on convolutional neural networks before designing our own convolutional neural network. Then, we have modified our model parameters using the experimental data to further enhance the effect of point-cloud compression. Based on the experimental results, we have found that the neural network with the 4 layers and 2 strides parameter configuration using the Sigmoid activation function outperforms the default configuration by 208% in terms of the compression-distortion rate. The experimental results show that our findings are effective and universal and make a great contribution to the research of point-cloud compression using convolutional neural networks.
11
M., Rajeshkumar. "Quad Histogram based Color Feature Extraction and Modified Convolutional Neural Network for Weed Classification." Journal of Advanced Research in Dynamical and Control Systems 12, SP4 (2020): 85–96. http://dx.doi.org/10.5373/jardcs/v12sp4/20201469.
Full text
12
Ko, Kyeong-Nam, and Moon-Sik Kang. "High-efficiency ECG Data Analysis Scheme using Modified Residual Convolutional Neural Network Model." Journal of the Institute of Electronics and Information Engineers 58, no. 10 (2021): 42–48. http://dx.doi.org/10.5573/ieie.2021.58.10.42.
Full text
13
Lukman, Achmad, Wahju Tjahjo Saputro, and Erni Seniwati. "Improving Performance Convolutional Neural Networks Using Modified Pooling Function." MATRIK : Jurnal Manajemen, Teknik Informatika dan Rekayasa Komputer 23, no. 2 (2024): 343–52. http://dx.doi.org/10.30812/matrik.v23i2.3763.
Full textAbstract:
The Visual Geometry Group-16 (VGG16) network architecture, as part of the development of convolutional neural networks, has been popular among researchers in solving classification tasks, so in this paper, we investigated the number of layers to find better performance. In addition, we also proposed two pooling function techniques inspired by existing research on mixed pooling functions, namely Qmax and Qavg. The purpose of the research was to see the advantages of our method; we conducted several test scenarios, including comparing several modified network configurations based on VGG16 as a baseline and involving our pooling technique and existing pooling functions. Then, the results of the first scenario, we selected a network that can adapt well to our pooling technique, whichwas then carried out several tests involving the Cifar10, Cifar100, TinyImageNet, and Street View House Numbers (SVHN) datasets as benchmarks. In addition, we were also involved in several existing methods. The experiment results showed that Net-E has the highest performance, with 93.90% accuracy for Cifar10, 71.17% for Cifar100, and 52.84% for TinyImageNet. Still, the accuracy was low when the SVHN dataset was used. In addition, in comparison tests with several optimization algorithms using the Qavg pooling function, it can be seen that the best accuracy results lie in the SGD optimization algorithm, with 89.76% for Cifar10 and 89.06% for Cifar100.
14
Yang, Lulu, Junjiang Zhu, Tianhong Yan, Zhaoyang Wang, and Shangshi Wu. "A Modified Convolutional Neural Network for ECG Beat Classification." Journal of Medical Imaging and Health Informatics 10, no. 3 (2020): 654–60. http://dx.doi.org/10.1166/jmihi.2020.2913.
Full textAbstract:
Most convolutional neural networks (CNNs) used to classify electrocardiogram (ECG) beats tend to focus only on the beat, ignoring its relationships with its surrounding beats. This study aimed to propose a hybrid convolutional neural network (HCNN) structure, which classified ECG beats based on the beat's morphology and relationship such as RR intervals. The difference between the HCNN and the traditional CNN lies in the fact that the relationship can be added to any layer in the former. The HCNN was fed with RR intervals at 3 different positions, trained using data from 2170 patients. It was then evaluated with labeled clinical data from 2102 patients to classify ECG beats into premature ventricular contraction beat, atrial premature contraction beat (APC), left bundle branch block beat, right bundle branch block beat, and normal sinus beat. The results showed that the performance of the proposed HCNN method (with an average score of 86.61% on 12 leads) was 3.31% higher than that of the traditional CNN (83.30%) on the test set. In particular, the APC improved most significantly from 57.67% to 76.92% in terms of sensitivity and from 58.80% to 78.46% in terms of the positive predictive value in lead V1.
15
Xu, Yang, Yuequan Bao, Jiahui Chen, Wangmeng Zuo, and Hui Li. "Surface fatigue crack identification in steel box girder of bridges by a deep fusion convolutional neural network based on consumer-grade camera images." Structural Health Monitoring 18, no. 3 (2018): 653–74. http://dx.doi.org/10.1177/1475921718764873.
Full textAbstract:
This study conducts crack identification from real-world images containing complicated disturbance information (cracks, handwriting scripts, and background) inside steel box girders of bridges. Considering the multilevel and multi-scale features of the input images, a modified fusion convolutional neural network architecture is proposed. As input, 350 raw images are taken with a consumer-grade camera and divided into sub-images with resolution of 64 × 64 pixels (67,200 in total). A regular convolutional neural network structure is employed as baseline to demonstrate the accuracy benefits from the proposed fusion convolutional neural network structure. The confusion matrix is defined for prediction performance evaluation on the test set. A total of six additional entire raw images are used to investigate the robustness and feasibility of the proposed approach. A binary conversion process based on the optimal entropy threshold method is applied and closely followed to identify the crack pixels in the sub-images. The effect of the super-resolution inputs on accuracy is investigated. Results show that the trained modified fusion convolutional neural network can automatically detect the cracks, handwriting, and background from the raw images. The recognition errors of the fusion convolutional neural network in both the training and validation processes are smaller than those of the regular convolutional neural network. The super-resolution process hurts the general identification accuracy.
16
Khan, Muhammad Ashfaq. "HCRNNIDS: Hybrid Convolutional Recurrent Neural Network-Based Network Intrusion Detection System." Processes 9, no. 5 (2021): 834. http://dx.doi.org/10.3390/pr9050834.
Full textAbstract:
Nowadays, network attacks are the most crucial problem of modern society. All networks, from small to large, are vulnerable to network threats. An intrusion detection (ID) system is critical for mitigating and identifying malicious threats in networks. Currently, deep learning (DL) and machine learning (ML) are being applied in different domains, especially information security, for developing effective ID systems. These ID systems are capable of detecting malicious threats automatically and on time. However, malicious threats are occurring and changing continuously, so the network requires a very advanced security solution. Thus, creating an effective and smart ID system is a massive research problem. Various ID datasets are publicly available for ID research. Due to the complex nature of malicious attacks with a constantly changing attack detection mechanism, publicly existing ID datasets must be modified systematically on a regular basis. So, in this paper, a convolutional recurrent neural network (CRNN) is used to create a DL-based hybrid ID framework that predicts and classifies malicious cyberattacks in the network. In the HCRNNIDS, the convolutional neural network (CNN) performs convolution to capture local features, and the recurrent neural network (RNN) captures temporal features to improve the ID system’s performance and prediction. To assess the efficacy of the hybrid convolutional recurrent neural network intrusion detection system (HCRNNIDS), experiments were done on publicly available ID data, specifically the modern and realistic CSE-CIC-DS2018 data. The simulation outcomes prove that the proposed HCRNNIDS substantially outperforms current ID methodologies, attaining a high malicious attack detection rate accuracy of up to 97.75% for CSE-CIC-IDS2018 data with 10-fold cross-validation.
17
Zhang, Yulin, Feipeng Li, Haoke Xu, Xiaoming Li, and Shan Jiang. "Efficient Convolutional Neural Networks Utilizing Fine-Grained Fast Fourier Transforms." Electronics 13, no. 18 (2024): 3765. http://dx.doi.org/10.3390/electronics13183765.
Full textAbstract:
Convolutional Neural Networks (CNNs) are among the most prevalent deep learning techniques employed across various domains. The computational complexity of CNNs is largely attributed to the convolution operations. These operations are computationally demanding and significantly impact overall model performance. Traditional CNN implementations convert convolutions into matrix operations via the im2col (image to column) technique, facilitating parallelization through advanced BLAS libraries. This study identifies and investigates a significant yet intricate pattern of data redundancy within the matrix-based representation of convolutions, a pattern that, while complex, presents opportunities for optimization. Through meticulous analysis of the redundancy inherent in the im2col approach, this paper introduces a mathematically succinct matrix representation for convolution, leading to the development of an optimized FFT-based convolution with finer FFT granularity. Benchmarking demonstrates that our approach achieves an average speedup of 14 times and a maximum speedup of 17 times compared to the regular FFT convolution. Similarly, it outperforms the Im2col+GEMM approach from NVIDIA’s cuDNN library, achieving an average speedup of three times and a maximum speedup of five times. Our FineGrained FFT convolution approach, when integrated into Caffe, a widely used deep learning framework, leads to significant performance gains. Evaluations using synthetic CNNs designed for real-world applications show an average speedup of 1.67 times. Furthermore, a modified VGG network variant achieves a speedup of 1.25 times.
18
Jiao, Licheng, Sibo Zhang, Lingling Li, Fang Liu, and Wenping Ma. "A modified convolutional neural network for face sketch synthesis." Pattern Recognition 76 (April 2018): 125–36. http://dx.doi.org/10.1016/j.patcog.2017.10.025.
Full text
19
Zhao, Ying. "Evolutionary Neural Network-Based Online Ecological Governance Monitoring of Industrial Water Pollution." International Journal of Swarm Intelligence Research 16, no. 1 (2025): 1–23. https://doi.org/10.4018/ijsir.370397.
Full textAbstract:
This paper proposes ENNOEIGS, an evolutionary neural network-based online ecological industrial governance system that integrates advanced neural architectures with evolutionary optimization for robust pollution monitoring. The framework combines convolutional neural networks for dimensional reduction of sensor data, external attention mechanisms for discovering pollution pattern correlations, and convolutional long short-term memory networks for modeling the spatiotemporal evolution of contaminants. A genetic algorithm continuously optimizes the neural network parameters, enabling adaptation to changing industrial conditions. Experimental validation using industrial wastewater monitoring data demonstrates ENNOEIGS's superior performance, achieving a 94.8% anomaly detection rate with 2.3% false alarms, outperforming existing approaches. The framework reduces the mean modified absolute error to 0.028 mg/L while maintaining faster convergence during training.
20
Wang, Lulu. "Holographic Microwave Image Classification Using a Convolutional Neural Network." Micromachines 13, no. 12 (2022): 2049. http://dx.doi.org/10.3390/mi13122049.
Full textAbstract:
Holographic microwave imaging (HMI) has been proposed for early breast cancer diagnosis. Automatically classifying benign and malignant tumors in microwave images is challenging. Convolutional neural networks (CNN) have demonstrated excellent image classification and tumor detection performance. This study investigates the feasibility of using the CNN architecture to identify and classify HMI images. A modified AlexNet with transfer learning was investigated to automatically identify, classify, and quantify four and five different HMI breast images. Various pre-trained networks, including ResNet18, GoogLeNet, ResNet101, VGG19, ResNet50, DenseNet201, SqueezeNet, Inception v3, AlexNet, and Inception-ResNet-v2, were investigated to evaluate the proposed network. The proposed network achieved high classification accuracy using small training datasets (966 images) and fast training times.
21
Chen, Jing, Xiaoxuan Wang, and Yujing Wu. "Internet street view image fusion method using convolutional neural network." Journal of Computational Methods in Sciences and Engineering 24, no. 3 (2024): 1665–78. http://dx.doi.org/10.3233/jcm-247272.
Full textAbstract:
The use of image fusion technology in the area of information processing is continuing to advance in depth thanks to ongoing hardware advancements and related research. An enhanced convolutional neural network approach is developed to fuse visible and infrared images, and image pre-processing is carried out utilising an image alignment method with edge detection in order to gain more accurate and trustworthy image information. The performance of the fast wavelet decomposition, convolutional neural network, and modified convolutional neural network techniques is compared and examined using four objective assessment criteria. The experimental findings demonstrated that the picture alignment was successful with an offset error of fewer than 3 pixels in the horizontal direction and an angle error of less than 0.3∘ in both directions. The revised convolutional neural network method increased the information entropy, mean gradient, standard deviation, and edge detection information by an average of 46.13%, 39.40%, 19.91%, and 3.72%. The runtime of the modified approach was lowered by 19.42% when compared to the convolutional neural network method, which enhanced the algorithm’s performance and boosted the effectiveness of picture fusion. The image fusion accuracy reached 98.61%, indicating that the method has better fusion performance and is of practical value for improving image fusion quality.
22
Zherebukh, Oleh, and Ihor Farmaha. "Using Neural Networks to Identify Objects in an Image." Computer Design Systems. Theory and Practice 6, no. 1 (2024): 232–40. http://dx.doi.org/10.23939/cds2024.01.232.
Full textAbstract:
A modified neural network model based on Yolo V5 was developed and the quality metrics of object classification on video images built on the basis of existing known basic neural network architectures were compared. The application of convolutional neural networks for processing images from video surveillance cameras is considered in order to develop an optimized algorithm for detecting and classifying objects on video images. The existing models and architectures of neural networks for image analysis were analyzed and compared. The possibilities of optimizing the process of image analysis using neural networks are considered.
23
Deng, Guohao, Dang Wang, and Weixin Gao. "Active and Reactive Power Coordination Optimization of the Active Distribution Network." Journal of Physics: Conference Series 2450, no. 1 (2023): 012023. http://dx.doi.org/10.1088/1742-6596/2450/1/012023.
Full textAbstract:
Abstract The operation and control of the active distribution network are faced with great challenges due to a mass of tunable and controllable devices connected to the network, resulting in large active power loss and voltage deviation. In this paper, a method of active and reactive power coordination optimization for the active distribution network based on a one-dimensional convolutional neural network (1D-CNN) is proposed. This method can mine valuable information from the historical data of distribution networks, and use one-dimensional convolutional neural networks to map the complex nonlinear relationship between node load and optimization strategy. The simulation results of the modified IEEE33 node distribution network system show that the active power loss and the node voltage deviation of the proposed method are significantly reduced.
24
Fan, Weiwei, Feng Zhou, Xueru Bai, Mingliang Tao, and Tian Tian. "Ship Detection Using Deep Convolutional Neural Networks for PolSAR Images." Remote Sensing 11, no. 23 (2019): 2862. http://dx.doi.org/10.3390/rs11232862.
Full textAbstract:
Ship detection plays an important role in many remote sensing applications. However, the performance of the PolSAR ship detection may be degraded by the complicated scattering mechanism, multi-scale size of targets, and random speckle noise, etc. In this paper, we propose a ship detection method for PolSAR images based on modified faster region-based convolutional neural network (Faster R-CNN). The main improvements include proposal generation by adopting multi-level features produced by the convolution layers, which fits ships with different sizes, and the addition of a Deep Convolutional Neural Network (DCNN)-based classifier for training sample generation and coast mitigation. The proposed method has been validated by four measured datasets of NASA/JPL airborne synthetic aperture radar (AIRSAR) and uninhabited aerial vehicle synthetic aperture radar (UAVSAR). Performance comparison with the modified constant false alarm rate (CFAR) detector and the Faster R-CNN has demonstrated that the proposed method can improve the detection probability while reducing the false alarm rate and missed detections.
25
Manabe, Keisuke, Yusuke Asami, Tomonari Yamada, and Hiroyuki Sugimori. "Improvement in the Convolutional Neural Network for Computed Tomography Images." Applied Sciences 11, no. 4 (2021): 1505. http://dx.doi.org/10.3390/app11041505.
Full textAbstract:
Background and purpose. This study evaluated a modified specialized convolutional neural network (CNN) to improve the accuracy of medical images. Materials and Methods. We defined computed tomography (CT) images as belonging to one of the following 10 classes: head, neck, chest, abdomen, and pelvis with and without contrast media, with 10,000 images per class. We modified the CNN based on the AlexNet with an input size of 512 × 512. We resized the filter sizes of the convolution layer and max pooling. Using these modified CNNs, various models were created and evaluated. The improved CNN was evaluated to classify the presence or absence of the pancreas in the CT images. We compared the overall accuracy, which was calculated from images not used for training, to that of the ResNet. Results. The overall accuracies of the most improved CNN and ResNet in the 10 classes were 94.8% and 89.3%, respectively. The filter sizes of the improved CNN for the convolution layer were (13, 13), (7, 7), (5, 5), (5, 5), and (5, 5) in order from the first layer, and that of max-pooling was (7, 7). The calculation times of the most improved CNN and ResNet were 56 and 120 min, respectively. Regarding the classification of the pancreas, the overall accuracies of the most improved CNN and ResNet were 75.75% and 58.25%, respectively. The calculation times of the most improved CNN and ResNet were 36 and 55 min, respectively. Conclusion. By optimizing the filter size of the convolution layer and max-pooling of 512 × 512 images, we quickly obtained a highly accurate medical image classification model. This improved CNN can be useful for classifying lesions and anatomies for related diagnostic aid applications.
26
Sohn, Chanyoung, Heejong Choi, Kangil Kim, Jinwook Park, and Junhyug Noh. "Line Chart Understanding with Convolutional Neural Network." Electronics 10, no. 6 (2021): 749. http://dx.doi.org/10.3390/electronics10060749.
Full textAbstract:
Visual understanding of the implied knowledge in line charts is an important task affecting many downstream tasks in information retrieval. Despite common use, clearly defining the knowledge is difficult because of ambiguity, so most methods used in research implicitly learn the knowledge. When building a deep neural network, the integrated approach hides the properties of individual subtasks, which can hinder finding the optimal configurations for the understanding task in academia. In this paper, we propose a problem definition for explicitly understanding knowledge in a line chart and provide an algorithm for generating supervised data that are easy to share and scale-up. To introduce the properties of the definition and data, we set well-known and modified convolutional neural networks and evaluate their performance on real and synthetic datasets for qualitative and quantitative analyses. In the results, the knowledge is explicitly extracted and the generated synthetic data show patterns similar to human-labeled data. This work is expected to provide a separate and scalable environment to enhance research into technical document understanding.
27
Ali Ramdhani, Muhammad, Dian Sa’adillah Maylawati, and Teddy Mantoro. "Indonesian news classification using convolutional neural network." Indonesian Journal of Electrical Engineering and Computer Science 19, no. 2 (2020): 1000. http://dx.doi.org/10.11591/ijeecs.v19.i2.pp1000-1009.
Full textAbstract:
<span>Every language has unique characteristics, structures, and grammar. Thus, different styles will have different processes and result in processed in Natural Language Processing (NLP) research area. In the current NLP research area, Data Mining (DM) or Machine Learning (ML) technique is popular, especially for Deep Learning (DL) method. This research aims to classify text data in the Indonesian language using Convolutional Neural Network (CNN) as one of the DL algorithms. The CNN algorithm used modified following the Indonesian language characteristics. Thereby, in the text pre-processing phase, stopword removal and stemming are particularly suitable for the Indonesian language. The experiment conducted using 472 Indonesian News text data from various sources with four categories: ‘hiburan’ (entertainment), ‘olahraga’ (sport), ‘tajuk utama’ (headline news), and ‘teknologi’ (technology). Based on the experiment and evaluation using 377 training data and 95 testing data, producing five models with ten epoch for each model, CNN has the best percentage of accuracy around 90,74% and loss value around 29,05% for 300 hidden layers in classifying the Indonesian News data.</span>
28
Muhammad, Ali Ramdhani, Sa'adillah Maylawati Dian, and Mantoro Teddy. "Indonesian news classification using convolutional neural network." Indonesian Journal of Electrical Engineering and Computer Science (IJEECS) 19, no. 2 (2020): 1000–1009. https://doi.org/10.11591/ijeecs.v19.i2.pp1000-1009.
Full textAbstract:
Every language has unique characteristics, structures, and grammar. Thus, different styles will have different processes and result in processed in Natural Language Processing (NLP) research area. In the current NLP research area, Data Mining (DM) or Machine Learning (ML) technique is popular, especially for Deep Learning (DL) method. This research aims to classify text data in the Indonesian language using Convolutional Neural Network (CNN) as one of the DL algorithms. The CNN algorithm used modified following the Indonesian language characteristics. Thereby, in the text pre-processing phase, stopword removal and stemming are particularly suitable for the Indonesian language. The experiment conducted using 472 Indonesian News text data from various sources with four categories: „hiburan" (entertainment), „olahraga" (sport), „tajuk utama" (headline news), and „teknologi" (technology). Based on the experiment and evaluation using 377 training data and 95 testing data, producing five models with ten epoch for each model, CNN has the best percentage of accuracy around 90,74% and loss value around 29,05% for 300 hidden layers in classifying the Indonesian News data.
29
SHIN, Soo-Yeon, Dong-Myung KIM, and Jae-Won SUH. "Image Denoiser Using Convolutional Neural Network with Deconvolution and Modified Residual Network." IEICE Transactions on Information and Systems E102.D, no. 8 (2019): 1598–601. http://dx.doi.org/10.1587/transinf.2018edl8175.
Full text
30
Liu, Ruiqi, Jing Tian, Yuemei Li, et al. "Nailfold Microhemorrhage Segmentation with Modified U-Shape Convolutional Neural Network." Applied Sciences 12, no. 10 (2022): 5068. http://dx.doi.org/10.3390/app12105068.
Full textAbstract:
Nailfold capillaroscopy is a reliable way to detect and analyze microvascular abnormalities. It is safe, simple, noninvasive, and inexpensive. Among all the capillaroscopic abnormalities, nailfold microhemorrhages are closely associated with early vascular damages and might be present in numerous diseases such as glaucoma, diabetes mellitus, and systemic sclerosis. Segmentation of nailfold microhemorrhages provides valuable pathological information that may lead to further investigations. A novel deep learning architecture named DAFM-Net is proposed for the accurate segmentation in this study. The network mainly consists of U-shape backbone, dual attention fusion module, and group normalization layer. The U-shape backbone generates rich hierarchical representations while the dual attention fusion module utilizes the captured features for fine adjustment. Group normalization is introduced as an effective normalization method to effectively improve the convergence ability of our deep neural network. The effectiveness of the proposed model is validated through ablation studies and segmentation experiments; the proposed method DAFM-Net achieves competitive performance for nailfold microhemorrhage segmentation with an IOU score of 78.03% and Dice score of 87.34% compared to the ground truth.
31
Cari, Cari, Mohtar Yunianto, and Aisyah Ajibah Rahmah. "Lung Cancer Detection Using a Modified Convolutional Neural Network (CNN)." INDONESIAN JOURNAL OF APPLIED PHYSICS 14, no. 1 (2024): 52. http://dx.doi.org/10.13057/ijap.v14i1.77032.
Full textAbstract:
<p><span>Image processing is used to classify lung images with malignant or normal nodules. The Convolutional Neural Network (CNN) method is often used to classify images. This study uses a modified CNN architecture with various layers, filters, batch size, dropout, and epoch values. Variations were made to determine the best accuracy value and reduce the overfitting value of the proposed CNN architecture. This study implements the method using the Keras library with the Python programming language. The data is in the form of CT-Scan images of lung cancer and normal lungs. The results of several experiments from the proposed model produce an accuracy value of 95% using three layers, 128 filters on the first layer, 256 on the second layer, and 512 filters on the third layer, then with 32 batch sizes, 0.5 dropout.</span></p>
32
Энгель, Е. А., and Н. Е. Энгель Энгель. "INTELLIGENT MODEL FOR MAXIMIZING THE GENERATED POWER OF A RECONFIGURABLE SOLAR POWER PLANT." Proceedings in Cybernetics 22, no. 1 (2023): 52–58. http://dx.doi.org/10.35266/1999-7604-2023-1-52-58.
Full textAbstract:
The global maximum power point tracking of a solar power plant in partial shading demands a global optimization. Standard algorithms for tracking of maximum power point do not provide for a maximum global power of a solar power plant during real time mode due to low convergence. A model of aximizing the generated power of a reconfigurable solar power plant was developed as a modified fuzzy deep neural network based on the modified quantum-behaved particle swarm optimizer. This neural network consists of the following: convolutional units, recurrent neural networks, and fuzzy units. By processing the sensor signals and images of the solar array, the set modified fuzzy deep neural network generates a reference voltage and an electrical interconnection matrix of the parallel-serial solar array, maximizing its power under non-uniform insolation. The neural network demonstrates such advantages as robustness, better efficiency, and tracking speed in comparison with the model of a reconfigurable solar power plant based on the particle swarm optimization.
33
Ma, Liyong, Chengkuan Ma, Yuejun Liu, and Xuguang Wang. "Thyroid Diagnosis from SPECT Images Using Convolutional Neural Network with Optimization." Computational Intelligence and Neuroscience 2019 (January 15, 2019): 1–11. http://dx.doi.org/10.1155/2019/6212759.
Full textAbstract:
Thyroid disease has now become the second largest disease in the endocrine field; SPECT imaging is particularly important for the clinical diagnosis of thyroid diseases. However, there is little research on the application of SPECT images in the computer-aided diagnosis of thyroid diseases based on machine learning methods. A convolutional neural network with optimization-based computer-aided diagnosis of thyroid diseases using SPECT images is developed. Three categories of diseases are considered, and they are Graves’ disease, Hashimoto disease, and subacute thyroiditis. A modified DenseNet architecture of convolutional neural network is employed, and the training method is improved. The architecture is modified by adding the trainable weight parameters to each skip connection in DenseNet. And the training method is improved by optimizing the learning rate with flower pollination algorithm for network training. Experimental results demonstrate that the proposed method of convolutional neural network is efficient for the diagnosis of thyroid diseases with SPECT images, and it has superior performance than other CNN methods.
34
Gaskarov, Rodion Dmitrievich, Alexey Mikhailovich Biryukov, Alexey Fedorovich Nikonov, Daniil Vladislavovich Agniashvili, and Danil Aydarovich Khayrislamov. "Steel Defects Analysis Using CNN (Convolutional Neural Networks)." Russian Digital Libraries Journal 23, no. 6 (2020): 1155–71. http://dx.doi.org/10.26907/1562-5419-2020-23-6-1155-1171.
Full textAbstract:
Steel is one of the most important bulk materials these days. It is used almost everywhere - from medicine to industry. Detecting this material's defects is one of the most challenging problems for industries worldwide. This process is also manual and time-consuming. Through this study we tried to automate this process. A convolutional neural network model UNet was used for this task for more accurate segmentation with less training image data set for our model. The essence of this NN (neural network) is in step-by-step convolution of every image (encoding) and then stretching them to initial resolution, consequently getting a mask of an image with various classes on it. The foremost modification is changing an input image's size to 128x800 px resolution (original images in dataset are 256x1600 px) because of GPU memory size's limitation. Secondly, we used ResNet34 CNN (convolutional neural network) as encoder, which was pre-trained on ImageNet1000 dataset with modified output layer - it shows 4 layers instead of 34. After running tests of this model, we obtained 92.7% accuracy using images of hot-rolled steel sheets.
35
Yang, Jin. "Urban Traffic Flow Prediction with Deep Neural Network." Security and Communication Networks 2022 (June 1, 2022): 1–10. http://dx.doi.org/10.1155/2022/8711873.
Full textAbstract:
It is critical to realize accurate collecting, visualization, rule mining, and prediction analysis of the traffic flow operating state in order for the intelligent transportation system to achieve exact management and control of traffic flow. Traffic flow prediction is primarily concerned with traffic data on roadways, which has both temporal and spatial correlations. Aiming at the spatiotemporal characteristics, this paper studies two aspects and designs a traffic flow prediction model with a deep neural network. First, this work proposes a traffic flow spatial feature learning algorithm with the combination of graph convolutional neural network and attention mechanism. Distinct weights are assigned to the degree of mutual impact between different nodes, and node adaptive learning is implemented at the same time, which modifies the standard parameter sharing mode, allowing for improved expressive ability and spatial feature extraction. Secondly, a learning algorithm for temporal characteristics of traffic flow based on the temporal convolutional network is proposed, which ensures that the dimensions of input and output data are consistent through causal convolution. The dilated convolution can flexibly control the receptive field by setting the sampling interval and can also extract temporal features well for long-length spatiotemporal sequence data. Finally, a spatiotemporal graph attention-based traffic flow prediction approach is constructed. To learn features, learn parameters for multiple modes and improve the model effect, this model employs a combination of graph convolutional neural networks and an attention mechanism. It uses a temporal convolutional network to expand the receptive field, better capture temporal features, and finally add residual connections to prevent problems such as overfitting caused by too deep network layers.
36
Anees, Fatima Khan, P. Bhavya, and Ravinder Reddy R. "Land Classification using Convolutional Neural Networks." International Journal of Recent Technology and Engineering (IJRTE) 9, no. 2 (2020): 79–83. https://doi.org/10.35940/ijrte.A3030.079220.
Full textAbstract:
Identifying the physical aspect of the earth’s surface (Land cover) and also how we exploit the land (Land use) is a challenging problem in environment monitoring and much of other subdomains. One of the most efficient ways to do this is through Remote Sensing (analyzing satellite images). For such classification using satellite images, there exist many algorithms and methods, but they have several problems associated with them, such as improper feature extraction, poor efficiency, etc. Problems associated with established land-use classification methods can be solved by using various optimization techniques with the Convolutional neural networks(CNN). The structure of the Convolutional neural network model is modified to improve the classification performance, and the overfitting phenomenon that may occur during training is avoided by optimizing the training algorithm. This work mainly focuses on classifying land types such as forest lands, bare lands, residential buildings, Rivers, Highways, cultivated lands, etc. The outcome of this work can be further processed for monitoring in various domains.
37
Kavitha Rajalakshmi D and P. Bharathisindhu. "A Modified Deep Convolutional Network for Detection of Covid19 from Chest X-Rays Based on Concatenation of Image Preprocessing Techniques and RESnCOV." Metallurgical and Materials Engineering 31, no. 4 (2025): 331–40. https://doi.org/10.63278/1441.
Full textAbstract:
The fast-spreading coronavirus disease called COVID-19 has impacted millions of people worldwide. It becomes difficult for medical experts to rapidly detect the illness and stop its spread because of its rapid growth and rising numbers. One of the newer areas of study where this issue can be more carefully addressed is medical image analysis. In this study, we implemented an image processing system utilizing deep learning and neural networks to previse the 2019-nCoV using chest roentgen ray images. In order to recognize COVID-19 positive and healthy patients using chest roentgen ray images, this paper suggests employing convolutional neural networks, deep learning, and machine learning. We proposed a neural network composed of various features taken from two convolutional neural networks, ResNet50 and ResNet152V2, in order to successfully manage the intricate structural complexity of an image. We tested our network on 7940 images to see how well it performs in real-world situations. The proposed network detects normal and COVID-19 cases with an average accuracy of 95% and can be used as an aid in the radiology department.
38
Dawud, Awwal Muhammad, Kamil Yurtkan, and Huseyin Oztoprak. "Application of Deep Learning in Neuroradiology: Brain Haemorrhage Classification Using Transfer Learning." Computational Intelligence and Neuroscience 2019 (June 3, 2019): 1–12. http://dx.doi.org/10.1155/2019/4629859.
Full textAbstract:
In this paper, we address the problem of identifying brain haemorrhage which is considered as a tedious task for radiologists, especially in the early stages of the haemorrhage. The problem is solved using a deep learning approach where a convolutional neural network (CNN), the well-known AlexNet neural network, and also a modified novel version of AlexNet with support vector machine (AlexNet-SVM) classifier are trained to classify the brain computer tomography (CT) images into haemorrhage or nonhaemorrhage images. The aim of employing the deep learning model is to address the primary question in medical image analysis and classification: can a sufficient fine-tuning of a pretrained model (transfer learning) eliminate the need of building a CNN from scratch? Moreover, this study also aims to investigate the advantages of using SVM as a classifier instead of a three-layer neural network. We apply the same classification task to three deep networks; one is created from scratch, another is a pretrained model that was fine-tuned to the brain CT haemorrhage classification task, and our modified novel AlexNet model which uses the SVM classifier. The three networks were trained using the same number of brain CT images available. The experiments show that the transfer of knowledge from natural images to medical images classification is possible. In addition, our results proved that the proposed modified pretrained model “AlexNet-SVM” can outperform a convolutional neural network created from scratch and the original AlexNet in identifying the brain haemorrhage.
39
Wagh, Jagruti. "Geographical Area Classification on Satellite Images Using CNN Architecture." INTERANTIONAL JOURNAL OF SCIENTIFIC RESEARCH IN ENGINEERING AND MANAGEMENT 08, no. 05 (2024): 1–5. http://dx.doi.org/10.55041/ijsrem34144.
Full textAbstract:
This paper presents a novel approach for classi- fying geographical areas in satellite imagery using a modified Convolutional Neural Network (CNN) architecture.The archi- tecture enhances feature extraction and classification accuracy by combining specialized layers like fully connected, pooling, and conventional layers. Our modified CNN performs better at accurately classifying a variety of geographic locations, according to our testing results. By efficiently capturing and analyzing complex spatial patterns, the use of customized layers enhances classification results in satellite-based geographical area classifi- cation. Index Terms—Geographical area classification, Convolutional Neural Network (CNN), Satellite imagery, Image classification, Fully connected layers, Pooling layers, Conventional layers
40
Et. al., Siji George C. G,. "Genetic Algorithm Based Hybrid Model Of convolutional Neural Network And Random Forest Classifier For Sentiment Classification." Turkish Journal of Computer and Mathematics Education (TURCOMAT) 12, no. 2 (2021): 3216–23. http://dx.doi.org/10.17762/turcomat.v12i2.2379.
Full textAbstract:
Sentiment analysis is one of the active research areas in the field of datamining. Machine learning algorithms are capable to implement sentiment analysis. Due to the capacity of self-learning and massive data handling, most of the researchers are using deep learning neural networks for solving sentiment classification tasks. So, in this paper, a new model is designed under a hybrid framework of machine learning and deep learning which couples Convolutional Neural Network and Random Forest classifier for fine-grained sentiment analysis. The Continuous Bag-of-Word (CBOW) model is used to vectorize the text input. The most important features are extracted by the Convolutional Neural Network (CNN). The extracted features are used by the Random Forest(RF) classifier for sentiment classification. The performance of the proposed hybrid CNNRF model is comparedwith the base model such as Convolutional Neural Network (CNN) and Random Forest (RF) classifier. The experimental result shows that the proposed model far beat the existing base models in terms of classification accuracy and effectively integrated genetically-modified CNN with Random Forest classifier.
41
Firsov, Nikita, Evgeny Myasnikov, Valeriy Lobanov, et al. "HyperKAN: Kolmogorov–Arnold Networks Make Hyperspectral Image Classifiers Smarter." Sensors 24, no. 23 (2024): 7683. https://doi.org/10.3390/s24237683.
Full textAbstract:
In traditional neural network designs, a multilayer perceptron (MLP) is typically employed as a classification block following the feature extraction stage. However, the Kolmogorov–Arnold Network (KAN) presents a promising alternative to MLP, offering the potential to enhance prediction accuracy. In this paper, we studied KAN-based networks for pixel-wise classification of hyperspectral images. Initially, we compared baseline MLP and KAN networks with varying numbers of neurons in their hidden layers. Subsequently, we replaced the linear, convolutional, and attention layers of traditional neural networks with their KAN-based counterparts. Specifically, six cutting-edge neural networks were modified, including 1D (1DCNN), 2D (2DCNN), and 3D convolutional networks (two different 3DCNNs, NM3DCNN), as well as transformer (SSFTT). Experiments conducted using seven publicly available hyperspectral datasets demonstrated a substantial improvement in classification accuracy across all the networks. The best classification quality was achieved using a KAN-based transformer architecture.
42
Lin, Chaojun, Ying Shi, Jian Zhang, Changjun Xie, Wei Chen, and Yue Chen. "An anchor-free detector and R-CNN integrated neural network architecture for environmental perception of urban roads." Proceedings of the Institution of Mechanical Engineers, Part D: Journal of Automobile Engineering 235, no. 12 (2021): 2964–73. http://dx.doi.org/10.1177/09544070211004466.
Full textAbstract:
Environmental perception of urban roads is a critical research goal in intelligent transportation technology and autonomous vehicles, and pedestrian location is key to many relevant algorithms. Because anchor-free detectors are faster and region-based convolutional neural networks have a higher accuracy in object detection and classification, we propose an integrated convolutional networking architecture combining an anchor-free detector with a region-based convolutional neural network in the environmental perception task. The proposed network achieves higher precision and increases inference speed by up to 30%. To acquire more accurate region boundaries than a coarse bounding box method, a semantic segmentation sub-network is adopted to predict an instance segmentation mask for each object, and more accurate segmentation results are obtained by using the Dice loss. Moreover, we present an assignment strategy using a modified feature pyramid structure and show that it improves mean average precision of pedestrian detection by 2% on average. Finally, we verify that the pretrained neural network is beneficial for small datasets. Overall, the results show that our model achieves higher precision than the approaches used for comparison.
43
Andini, Silfia, Erni Rouza, Luth Fimawahib, et al. "Convolutional Neural Network for object Identification and Detection." Journal of Physics: Conference Series 2394, no. 1 (2022): 012018. http://dx.doi.org/10.1088/1742-6596/2394/1/012018.
Full textAbstract:
Abstract The goal of this study is to use a Convolutional Neural Network to find the optimum architectural model for classifying cloud images. Cirrus Cumulus Stratus Nimbus uses a source dataset that includes 11 cloud classifications and 2545 cloud photos (CCSN). In this study, the best Convolutional Neural Network is retrained almost fast by transferring education from Google’s basic design. Based on the modified Googlenet architecture, the training and testing phases of the classification process are divided into two. The dataset is separated into three sections during the training phase: 70% of the training data, 15% of the validation data, and 15% of the test data. There are two trials to categorize cloud photographs during the test phase, one of which has ten cloud kinds that can be randomly chosen. The precision achieved throughout the training was 44.5%, according to the findings. The results of the two tests are 75%, with an average error of 0.2. In the testing phase, the percentage is 75%.
44
Fouad, Zainab, Marco Alfonse, Mohamed Roushdy, and Abdel-Badeeh M. Salem. "Hyper-parameter optimization of convolutional neural network based on particle swarm optimization algorithm." Bulletin of Electrical Engineering and Informatics 10, no. 6 (2021): 3377–84. http://dx.doi.org/10.11591/eei.v10i6.3257.
Full textAbstract:
Deep neural networks have accomplished enormous progress in tackling many problems. More specifically, convolutional neural network (CNN) is a category of deep networks that have been a dominant technique in computer vision tasks. Despite that these deep neural networks are highly effective; the ideal structure is still an issue that needs a lot of investigation. Deep Convolutional Neural Network model is usually designed manually by trials and repeated tests which enormously constrain its application. Many hyper-parameters of the CNN can affect the model performance. These parameters are depth of the network, numbers of convolutional layers, and numbers of kernels with their sizes. Therefore, it may be a huge challenge to design an appropriate CNN model that uses optimized hyper-parameters and reduces the reliance on manual involvement and domain expertise. In this paper, a design architecture method for CNNs is proposed by utilization of particle swarm optimization (PSO) algorithm to learn the optimal CNN hyper-parameters values. In the experiment, we used Modified National Institute of Standards and Technology (MNIST) database of handwritten digit recognition. The experiments showed that our proposed approach can find an architecture that is competitive to the state-of-the-art models with a testing error of 0.87%.
45
K, Jeyalakshmi, and Rangaraj R. "Accurate liver disease prediction system using convolutional neural network." Indian Journal of Science and Technology 14, no. 17 (2021): 1406–21. https://doi.org/10.17485/IJST/v14i17.451.
Full textAbstract:
Abstract <strong>Objectives:</strong> To introduce the technique which can ensure the accurate and reliable prediction of liver disease by adapting the deep learning technique. <strong>Methods:</strong> In this work Modified Convolutional Neural Network based Liver Disease Prediction System (MCNN-LDPS) is introduced for the accurate liver disease prediction outcome. In the proposed research work, Dimensionality reduction is carried out using Modified Principal Component Analysis. Optimal feature selection is carried out using Score based Artificial Fish Swarm Algorithm (SAFSA). In SAFSA algorithm, information gain and entropy values are taken as input values which proved accurate outcome. This research method has been analysed over Indian Liver patient dataset. <strong>Findings:</strong> The analysis of the research work proves that the proposed method MCNN-LDPS obtains better outcome in terms of increased accuracy, precision. Here comparison analysis proved that MCNN-LDPS obtains 4.05% increased accuracy, 21.23% F-measure, 4.22% precision and 34.26% recall. This research method has been compared with the existing Multi layer Perceptron Neural Network (MLPNN) for the performance analysis. <strong>Novelty:</strong> The major limitation of CNN is its inability to encode Orientational and relative spatial relationships, view angle. CNN do not encode the position and orientation of data. Lack of ability to be spatially invariant to the input data sample. This is resolved in this research work by combining the genetic algorithm with the CNN method. <strong>Keywords:</strong> Liver Disease Prediction; Feature Selection; Information Gain; Entropy; Convolutional neural network; Dimensionality Reduction
46
Alsawalqah, Ahmad, and Bakhtiar Rosdi. "Robust Finger Vein Presentation Attack Detection Using XceptionNet-based Modified Depthwise Separable Convolutional Neural Network." Jordan Journal of Electrical Engineering 11, no. 1 (2025): 1. http://dx.doi.org/10.5455/jjee.204-1717325207.
Full textAbstract:
Finger vein presentation attack detection (FVPAD) biometric systems have seen substantial enhancements through the application of deep learning convolutional neural networks (DCNN). This advancement led to increased complexity, parameters and resource requirements. To address these challenges, a novel modification to the first entry flow of the XceptionNet architecture based on customized depthwise separable convolution (DSC) CNN-based for extracting robust features from FV images to detect spoofing attacks is proposed in this paper. The proposed approach stands out for its simplicity in design, fewer parameters, reduced computational load, minimal resource and equipment needs, and minimum data overflow while maintaining high accuracy in verification and classification tasks. The developed FVPAD system includes FV image data preprocessing and augmentation, a modified XceptionNet architecture based on DSC to deeply extract robust features. Finally, the fully connected (FC) layers exclusively use the SoftMax activation function to normalize, predict and classify output classes. The model was evaluated on cropped FV images from the IDIAP and SCUT-SFVD datasets, achieving high accuracy rates of 100% and 99.499%, respectively. It also has the lowest number of trainable parameters at 131,106 acquired from fifteen convolutional and depth-separable convolution layers.
47
Ghafar, Abdul, and Usman Sattar. "Convolutional Autoencoder for Image Denoising." UMT Artificial Intelligence Review 1, no. 2 (2021): 1–11. http://dx.doi.org/10.32350/air.0102.01.
Full textAbstract:
Image denoising is a process used to remove noise from the image to create a sharp and clear image. It is mainly used in medical imaging, where due to the malfunctioning of machines or due to the precautions taken to protect patients from radiation, medical imaging machines create a lot of noise in the final image. Several techniques can be used in order to avoid such distortions in the image before their final printing. Autoencoders are the most notable software used to denoise images before their final printing. These software are not intelligent so the resultant image is not of good quality. In this paper, we introduced a modified autoencoder having a deep convolutional neural network. It creates better quality images as compared to traditional autoencoders. After training with a test dataset on the tensor board, the modified autoencoder is tested on a different dataset having various shapes. The results were satisfactory but not desirable due to several reasons. Nevertheless, our proposed system still performed better than traditional autoencoders.
 KEYWORDS: image denoising, deep learning, convolutional neural network, image autoencoder, image convolutional autoencoder
48
Dofitas, Cyreneo, Joon-Min Gil, and Yung-Cheol Byun. "Multi-Directional Long-Term Recurrent Convolutional Network for Road Situation Recognition." Sensors 24, no. 14 (2024): 4618. http://dx.doi.org/10.3390/s24144618.
Full textAbstract:
Understanding road conditions is essential for implementing effective road safety measures and driving solutions. Road situations encompass the day-to-day conditions of roads, including the presence of vehicles and pedestrians. Surveillance cameras strategically placed along streets have been instrumental in monitoring road situations and providing valuable information on pedestrians, moving vehicles, and objects within road environments. However, these video data and information are stored in large volumes, making analysis tedious and time-consuming. Deep learning models are increasingly utilized to monitor vehicles and identify and evaluate road and driving comfort situations. However, the current neural network model requires the recognition of situations using time-series video data. In this paper, we introduced a multi-directional detection model for road situations to uphold high accuracy. Deep learning methods often integrate long short-term memory (LSTM) into long-term recurrent network architectures. This approach effectively combines recurrent neural networks to capture temporal dependencies and convolutional neural networks (CNNs) to extract features from extensive video data. In our proposed method, we form a multi-directional long-term recurrent convolutional network approach with two groups equipped with CNN and two layers of LSTM. Additionally, we compare road situation recognition using convolutional neural networks, long short-term networks, and long-term recurrent convolutional networks. The paper presents a method for detecting and recognizing multi-directional road contexts using a modified LRCN. After balancing the dataset through data augmentation, the number of video files increased, resulting in our model achieving 91% accuracy, a significant improvement from the original dataset.
49
V, Roseline, and Heren Chellam G. "A Novel Fusion Attention Algorithm for Sentimental Image Analysis." Indian Journal of Science and Technology 15, no. 9 (2022): 386–94. https://doi.org/10.17485/IJST/v15i9.2159.
Full textAbstract:
Abstract <strong>Objectives:</strong> To implement a novel and hybrid methodology for finding out the positive features when using convolutional neural networks (CNNs) for visual sentiment analysis. To achieve increased accuracy, precision and recall by using this proposed fusion attention methodology. <strong>Methods:</strong> This study proposes a modified methodology encompassing spatial attention, channel attention as well as squeeze excitation modules. An enhanced approach on the basis of convolutional neural networks was used here which utilizes convolution operators by combining both spatial and channel-based data. Moreover, we have incorporated three considerations like spatial, channel as well as squeeze and excitation at various levels for attaining optimal results. <strong>Findings:</strong> The accuracy of the existing approaches was 59.88%, 60.06%, 59.28% and 62.89%, but the proposed fusion attention method showed increased accuracy of 64.15%. Similarly, the F1 score of existing approaches are 0.464804, 0.250164, 0.474129 and 0.2574, but the proposed method revealed increased F1 score of 0.512933. Furthermore, the proposed algorithm showed precision and recall of 0.560896 and 0.472526 which were better when compared with the existing approaches like Res-Target, Resnet50, Alexnet and VGG16. <strong>Novelty:</strong> The novel feature of this proposed fusion attention algorithm was that it incorporates a hybrid approach in which the image together with convolution passes through channel attention, spatial attention as well as squeeze and excitation so as to attain increased accuracy, but most of the existing approaches have used only channel attention and spatial attention modules. In this proposed method, the algorithm performs convolution in 64-bit, 128-bit and 256-bit respectively together in which the three attentions were interchanged in each convolution, which were not prevalent in the existing approaches. <strong>Keywords:</strong> Fusion attention algorithm; Sentimental image analysis; Convolutional neural networks; Convolution and pooling; Deep neural network
50
Han, Shuzhen, Pingjuan Niu, Shijie Luo, et al. "A Novel Deep Convolutional Neural Network Combining Global Feature Extraction and Detailed Feature Extraction for Bearing Compound Fault Diagnosis." Sensors 23, no. 19 (2023): 8060. http://dx.doi.org/10.3390/s23198060.
Full textAbstract:
This study researched the application of a convolutional neural network (CNN) to a bearing compound fault diagnosis. The proposed idea lies in the ability of CNN to automatically extract fault features from complex raw signals. In our approach, to extract more effective features from a raw signal, a novel deep convolutional neural network combining global feature extraction with detailed feature extraction (GDDCNN) is proposed. First, wide and small kernel sizes are separately adopted in shallow and deep convolutional layers to extract global and detailed features. Then, the modified activation layer with a concatenated rectified linear unit (CReLU) is added following the shallow convolution layer to improve the utilization of shallow global features of the network. Finally, to acquire more robust features, another strategy involving the GMP layer is utilized, which replaces the traditional fully connected layer. The performance of the obtained diagnosis was validated on two bearing datasets. The results show that the accuracy of the compound fault diagnosis is over 98%. Compared with three other CNN-based methods, the proposed model demonstrates better stability.