Journal articles on the topic 'Classification based on generative models'
To see the other types of publications on this topic, follow the link: Classification based on generative models.
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 'Classification based on generative models.'
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
Cazzanti, Luca, Maya R. Gupta, and Anjali J. Koppal. "Generative models for similarity-based classification." Pattern Recognition 41, no. 7 (July 2008): 2289–97. http://dx.doi.org/10.1016/j.patcog.2008.01.005.
2
Wei, Wei, Jun Fang, Ning Yang, Qi Li, Lin Hu, Lanbo Zhao, and Jie Han. "AC-ModNet: Molecular Reverse Design Network Based on Attribute Classification." International Journal of Molecular Sciences 25, no. 13 (June 25, 2024): 6940. http://dx.doi.org/10.3390/ijms25136940.
Abstract:
Deep generative models are becoming a tool of choice for exploring the molecular space. One important application area of deep generative models is the reverse design of drug compounds for given attributes (solubility, ease of synthesis, etc.). Although there are many generative models, these models cannot generate specific intervals of attributes. This paper proposes a AC-ModNet model that effectively combines VAE with AC-GAN to generate molecular structures in specific attribute intervals. The AC-ModNet is trained and evaluated using the open 250K ZINC dataset. In comparison with related models, our method performs best in the FCD and Frag model evaluation indicators. Moreover, we prove the AC-ModNet created molecules have potential application value in drug design by comparing and analyzing them with medical records in the PubChem database. The results of this paper will provide a new method for machine learning drug reverse design.
3
Gopal, Narendra, and Sivakumar D. "DIMENSIONALITY REDUCTION BASED CLASSIFICATION USING GENERATIVE ADVERSARIAL NETWORKS DATASET GENERATION." ICTACT Journal on Image and Video Processing 13, no. 01 (August 1, 2022): 2786–90. http://dx.doi.org/10.21917/ijivp.2022.0396.
Abstract:
The term data augmentation refers to an approach that can be used to prevent overfitting in the training dataset, which is where the issue first manifests itself. This is based on the assumption that extra datasets can be improved by include new information that is of use. It is feasible to create an artificially larger training dataset by utilizing methods such as data warping and oversampling. This will allow for the creation of more accurate models. This idea is demonstrated through the application of a variety of different methods, some of which include neural style transfer, adversarial training, and erasure by random erasure, amongst others. By utilizing oversampling augmentations, it is feasible to create synthetic instances that can be incorporated into the training data. This is made possible by the generation of synthetic instances. There are numerous illustrations of this, including image merging, feature space enhancements, and generative adversarial networks, to name a few (GANs). In this paper, we aim to provide evidence that a Generative Adversarial Network can be used to convert regular images into Hyper Spectral Images (HSI). The purpose of the model is to generate data by including a certain amount of unpredictable noise.
4
Shastry, K. Aditya, B. A. Manjunatha, T. G. Mohan Kumar, and D. U. Karthik. "Generative Adversarial Networks Based Scene Generation on Indian Driving Dataset." Journal of ICT Research and Applications 17, no. 2 (August 31, 2023): 181–200. http://dx.doi.org/10.5614/itbj.ict.res.appl.2023.17.2.4.
Abstract:
The rate of advancement in the field of artificial intelligence (AI) has drastically increased over the past twenty years or so. From AI models that can classify every object in an image to realistic chatbots, the signs of progress can be found in all fields. This work focused on tackling a relatively new problem in the current scenario-generative capabilities of AI. While the classification and prediction models have matured and entered the mass market across the globe, generation through AI is still in its initial stages. Generative tasks consist of an AI model learning the features of a given input and using these learned values to generate completely new output values that were not originally part of the input dataset. The most common input type given to generative models are images. The most popular architectures for generative models are autoencoders and generative adversarial networks (GANs). Our study aimed to use GANs to generate realistic images from a purely semantic representation of a scene. While our model can be used on any kind of scene, we used the Indian Driving Dataset to train our model. Through this work, we could arrive at answers to the following questions: (1) the scope of GANs in interpreting and understanding textures and variables in complex scenes; (2) the application of such a model in the field of gaming and virtual reality; (3) the possible impact of generating realistic deep fakes on society.
5
Ekolle, Zie Eya, and Ryuji Kohno. "GenCo: A Generative Learning Model for Heterogeneous Text Classification Based on Collaborative Partial Classifications." Applied Sciences 13, no. 14 (July 14, 2023): 8211. http://dx.doi.org/10.3390/app13148211.
Abstract:
The use of generative learning models in natural language processing (NLP) has significantly contributed to the advancement of natural language applications, such as sentimental analysis, topic modeling, text classification, chatbots, and spam filtering. With a large amount of text generated each day from different sources, such as web-pages, blogs, emails, social media, and articles, one of the most common tasks in NLP is the classification of a text corpus. This is important in many institutions for planning, decision-making, and creating archives of their projects. Many algorithms exist to automate text classification tasks but the most intriguing of them is that which also learns these tasks automatically. In this study, we present a new model to infer and learn from data using probabilistic logic and apply it to text classification. This model, called GenCo, is a multi-input single-output (MISO) learning model that uses a collaboration of partial classifications to generate the desired output. It provides a heterogeneity measure to explain its classification results and enables a reduction in the curse of dimensionality in text classification. Experiments with the model were carried out on the Twitter US Airline dataset, the Conference Paper dataset, and the SMS Spam dataset, outperforming baseline models with 98.40%, 89.90%, and 99.26% accuracy, respectively.
6
Zhai, Junhai, Jiaxing Qi, and Chu Shen. "Binary imbalanced data classification based on diversity oversampling by generative models." Information Sciences 585 (March 2022): 313–43. http://dx.doi.org/10.1016/j.ins.2021.11.058.
7
Kim, Eunbeen, Jaeuk Moon, Jonghwa Shim, and Eenjun Hwang. "DualDiscWaveGAN-Based Data Augmentation Scheme for Animal Sound Classification." Sensors 23, no. 4 (February 10, 2023): 2024. http://dx.doi.org/10.3390/s23042024.
Abstract:
Animal sound classification (ASC) refers to the automatic identification of animal categories by sound, and is useful for monitoring rare or elusive wildlife. Thus far, deep-learning-based models have shown good performance in ASC when training data is sufficient, but suffer from severe performance degradation if not. Recently, generative adversarial networks (GANs) have shown the potential to solve this problem by generating virtual data. However, in a multi-class environment, existing GAN-based methods need to construct separate generative models for each class. Additionally, they only consider the waveform or spectrogram of sound, resulting in poor quality of the generated sound. To overcome these shortcomings, we propose a two-step sound augmentation scheme using a class-conditional GAN. First, common features are learned from all classes of animal sounds, and multiple classes of animal sounds are generated based on the features that consider both waveforms and spectrograms using class-conditional GAN. Second, we select data from the generated data based on the confidence of the pretrained ASC model to improve classification performance. Through experiments, we show that the proposed method improves the accuracy of the basic ASC model by up to 18.3%, which corresponds to a performance improvement of 13.4% compared to the second-best augmentation method.
8
Kannan, K. Gokul, and T. R. Ganesh Babu. "Semi Supervised Generative Adversarial Network for Automated Glaucoma Diagnosis with Stacked Discriminator Models." Journal of Medical Imaging and Health Informatics 11, no. 5 (May 1, 2021): 1334–40. http://dx.doi.org/10.1166/jmihi.2021.3787.
Abstract:
Generative Adversarial Network (GAN) is neural network architecture, widely used in many computer vision applications such as super-resolution image generation, art creation and image to image translation. A conventional GAN model consists of two sub-models; generative model and discriminative model. The former one generates new samples based on an unsupervised learning task, and the later one classifies them into real or fake. Though GAN is most commonly used for training generative models, it can be used for developing a classifier model. The main objective is to extend the effectiveness of GAN into semi-supervised learning, i.e., for the classification of fundus images to diagnose glaucoma. The discriminator model in the conventional GAN is improved via transfer learning to predict n + 1 classes by training the model for both supervised classification (n classes) and unsupervised classification (fake or real). Both models share all feature extraction layers and differ in the output layers. Thus any update in one of the model will impact both models. Results show that the semi-supervised GAN performs well than a standalone Convolution Neural Networks (CNNs) model.
9
Chen, Zirui. "Diffusion Models-based Data Augmentation for the Cell Cycle Phase Classification." Journal of Physics: Conference Series 2580, no. 1 (September 1, 2023): 012001. http://dx.doi.org/10.1088/1742-6596/2580/1/012001.
Abstract:
Abstract For biological research, sample size imbalance is common due to the nature of the research subjects. For example, in the study of the cell cycle phase, the sample size of dividing cells is also much smaller due to the extremely short duration of the mitotic phase compared to the interphase. Data augmentation using image generative models is an excellent way to address insufficient sample size and imbalanced distribution. In addition to the GAN-like models that have been extensively applied, the diffusion model, as an emerging model, has shown extraordinary performance in the field of image generation. This experiment uses the diffusion model as a means of image data enhancement. The experimental results expose that the performance of the classifier with data augmentation is significantly improved compared with the original dataset, and the positive predictive value is increased from about 0.7 to more than 0.9. The results reveal that the diffusion model has a good application prospect in the area of data enhancement and can effectively solve the problem of insufficient data or unbalanced sample size.
10
Bhavani, N. Sree, G. Narendra Babu Reddy, Y. Sravani Devi, M. Bhavani, P. Chandana Reddy, and V. Abhignya Reddy. "Generative Data Augmentation and ARMD Classification." International Journal for Research in Applied Science and Engineering Technology 11, no. 6 (June 30, 2023): 3662–67. http://dx.doi.org/10.22214/ijraset.2023.54178.
Abstract:
Abstract: Age Related Macular Degeneration (ARMD) is a type of eye disease which normally have an effect on the central vision of a person. This Disease might sometimes lead to permanent vision loss for some people. It affects the people over the age of 50. So, basically there are 2 different types of ARMD i.e., Dry and Wet. Dry ARMD will generate a tiny amount of protein deposits called drusen, whereas Wet ARMD occurs whenever any abnormal blood vessel is developed under the retina, so sometimes this blood vessels might leak blood fluid, this type of ARMD is very severe and can even lead to permanent central vision loss. Therefore, it is necessary for early detection of the disease. Generative Data Augmentation for ARMD Classification is deep learning based which uses Convolutional Neural Network (CNN) model for generating images to accurately identify the disease. Deep Learning Diagnostic models require expertly graded images from extensive data sets obtained in large scale clinical trials which may not exist. Therefore, (Generative Adversarial Networks) GAN-based generative data augmentation method called Style GAN is used for generating the images. Generative deep learning techniques is used to synthesize new large datasets of artificial retinal images from different stages of ARMD using the images from the already existing datasets. The performance of ARMD diagnostic DCNNs will be trained on the combination of both real and synthetic datasets. Images obtained by using GAN appear to be realistic, and increase the accuracy of the model. It then continues with classifying the retinal images into one of the three classes i.e., dry, wet or normal using CNN model. It also compares the accuracy against the model with traditional augmentation techniques, towards improving the performance of real-world ARMD classification tasks.
11
Wang, Chuantao, Xuexin Yang, and Linkai Ding. "Imbalanced sentiment classification based on sequence generative adversarial nets." Journal of Intelligent & Fuzzy Systems 39, no. 5 (November 19, 2020): 7909–19. http://dx.doi.org/10.3233/jifs-201370.
Abstract:
The purpose of sentiment classification is to solve the problem of automatic judgment of sentiment tendency. In the sentiment classification task of text data (such as online reviews), the traditional deep learning model focuses on algorithm optimization, but ignores the characteristics of the imbalanced distribution of the number of samples in each classification, which will cause the classification performance of the model to decrease in practical applications. In this paper, the experiment is divided into two stages. In the first stage, samples of minority class in the sample distribution are used to train a sequence generative adversarial nets, so that the sequence generative adversarial nets can learn the features of the samples of minority class in depth. In the second stage, the trained generator of sequence generative adversarial nets is used to generate false samples of minority class and mix them with the original samples to balance the sample distribution. After that, the mixed samples are input into the sentiment classification deep model to complete the model training. Experimental results show that the model has excellent classification performance in comparing a variety of deep learning models based on classic imbalanced learning methods in the sentiment classification task of hotel reviews.
12
Hassani, Hossein, Roozbeh Razavi-Far, Mehrdad Saif, and Vasile Palade. "Generative Adversarial Network-Based Scheme for Diagnosing Faults in Cyber-Physical Power Systems." Sensors 21, no. 15 (July 30, 2021): 5173. http://dx.doi.org/10.3390/s21155173.
Abstract:
This paper presents a novel diagnostic framework for distributed power systems that is based on using generative adversarial networks for generating artificial knockoffs in the power grid. The proposed framework makes use of the raw data measurements including voltage, frequency, and phase-angle that are collected from each bus in the cyber-physical power systems. The collected measurements are firstly fed into a feature selection module, where multiple state-of-the-art techniques have been used to extract the most informative features from the initial set of available features. The selected features are inputs to a knockoff generation module, where the generative adversarial networks are employed to generate the corresponding knockoffs of the selected features. The generated knockoffs are then fed into a classification module, in which two different classification models are used for the sake of fault diagnosis. Multiple experiments have been designed to investigate the effect of noise, fault resistance value, and sampling rate on the performance of the proposed framework. The effectiveness of the proposed framework is validated through a comprehensive study on the IEEE 118-bus system.
13
Cao, Zhiyi, Lei Shi, Wei Wang, and Shaozhang Niu. "Facial Pose and Expression Transfer Based on Classification Features." Electronics 12, no. 8 (April 7, 2023): 1756. http://dx.doi.org/10.3390/electronics12081756.
Abstract:
Transferring facial pose and expression features from one face to another is a challenging problem and an interesting topic in pattern recognition, but is one of great importance with many applications. However, existing models usually learn to transfer pose and expression features with classification labels, which cannot hold all the differences in shape and size between conditional faces and source faces. To solve this problem, we propose a generative adversarial network model based on classification features for facial pose and facial expression transfer. We constructed a two-stage classifier to capture the high-dimensional classification features for each face first. Then, the proposed generation model attempts to transfer pose and expression features with classification features. In addition, we successfully combined two cost functions with different convergence speeds to learn pose and expression features. Compared to state-of-the-art models, the proposed model achieved leading scores for facial pose and expression transfer on two datasets.
14
Won, K. J., C. Saunders, and A. Prügel-Bennett. "Evolving Fisher Kernels for Biological Sequence Classification." Evolutionary Computation 21, no. 1 (March 2013): 83–105. http://dx.doi.org/10.1162/evco_a_00065.
Abstract:
Fisher kernels have been successfully applied to many problems in bioinformatics. However, their success depends on the quality of the generative model upon which they are built. For Fisher kernel techniques to be used on novel problems, a mechanism for creating accurate generative models is required. A novel framework is presented for automatically creating domain-specific generative models that can be used to produce Fisher kernels for support vector machines (SVMs) and other kernel methods. The framework enables the capture of prior knowledge and addresses the issue of domain-specific kernels, both of which are current areas that are lacking in many kernel-based methods. To obtain the generative model, genetic algorithms are used to evolve the structure of hidden Markov models (HMMs). A Fisher kernel is subsequently created from the HMM, and used in conjunction with an SVM, to improve the discriminative power. This paper investigates the effectiveness of the proposed method, named GA-SVM. We show that its performance is comparable if not better than other state of the art methods in classifying secretory protein sequences of malaria. More interestingly, it showed better results than the sequence-similarity-based approach, without the need for additional homologous sequence information in protein enzyme family classification. The experiments clearly demonstrate that the GA-SVM is a novel way to find features with good performance from biological sequences, that does not require extensive tuning of a complex model.
15
Miller, David J., Jayaram Raghuram, George Kesidis, and Christopher M. Collins. "Improved Generative Semisupervised Learning Based on Finely Grained Component-Conditional Class Labeling." Neural Computation 24, no. 7 (July 2012): 1926–66. http://dx.doi.org/10.1162/neco_a_00284.
Abstract:
We introduce new inductive, generative semisupervised mixtures with more finely grained class label generation mechanisms than in previous work. Our models combine advantages of semisupervised mixtures, which achieve label extrapolation over a component, and nearest-neighbor (NN)/nearest-prototype (NP) classification, which achieve accurate classification in the vicinity of labeled samples or prototypes. For our NN-based method, we propose a novel two-stage stochastic data generation, with all samples first generated using a standard finite mixture and then all class labels generated, conditioned on the samples and their components of origin. This mechanism entails an underlying Markov random field, specific to each mixture component or cluster. We invoke the pseudo-likelihood formulation, which forms the basis for an approximate generalized expectation-maximization model learning algorithm. Our NP-based model overcomes a problem with the NN-based model that manifests at very low labeled fractions. Both models are advantageous when within-component class proportions are not constant over the feature space region “owned by” a component. The practicality of this scenario is borne out by experiments on UC Irvine data sets, which demonstrate significant gains in classification accuracy over previous semisupervised mixtures and also overall gains, over KNN classification. Moreover, for very small labeled fractions, our methods overall outperform supervised linear and nonlinear kernel support vector machines.
16
Bandi, Ajay, Pydi Venkata Satya Ramesh Adapa, and Yudu Eswar Vinay Pratap Kumar Kuchi. "The Power of Generative AI: A Review of Requirements, Models, Input–Output Formats, Evaluation Metrics, and Challenges." Future Internet 15, no. 8 (July 31, 2023): 260. http://dx.doi.org/10.3390/fi15080260.
Abstract:
Generative artificial intelligence (AI) has emerged as a powerful technology with numerous applications in various domains. There is a need to identify the requirements and evaluation metrics for generative AI models designed for specific tasks. The purpose of the research aims to investigate the fundamental aspects of generative AI systems, including their requirements, models, input–output formats, and evaluation metrics. The study addresses key research questions and presents comprehensive insights to guide researchers, developers, and practitioners in the field. Firstly, the requirements necessary for implementing generative AI systems are examined and categorized into three distinct categories: hardware, software, and user experience. Furthermore, the study explores the different types of generative AI models described in the literature by presenting a taxonomy based on architectural characteristics, such as variational autoencoders (VAEs), generative adversarial networks (GANs), diffusion models, transformers, language models, normalizing flow models, and hybrid models. A comprehensive classification of input and output formats used in generative AI systems is also provided. Moreover, the research proposes a classification system based on output types and discusses commonly used evaluation metrics in generative AI. The findings contribute to advancements in the field, enabling researchers, developers, and practitioners to effectively implement and evaluate generative AI models for various applications. The significance of the research lies in understanding that generative AI system requirements are crucial for effective planning, design, and optimal performance. A taxonomy of models aids in selecting suitable options and driving advancements. Classifying input–output formats enables leveraging diverse formats for customized systems, while evaluation metrics establish standardized methods to assess model quality and performance.
17
Zhou, Kun, Wenyong Wang, Teng Hu, and Kai Deng. "Time Series Forecasting and Classification Models Based on Recurrent with Attention Mechanism and Generative Adversarial Networks." Sensors 20, no. 24 (December 16, 2020): 7211. http://dx.doi.org/10.3390/s20247211.
Abstract:
Time series classification and forecasting have long been studied with the traditional statistical methods. Recently, deep learning achieved remarkable successes in areas such as image, text, video, audio processing, etc. However, research studies conducted with deep neural networks in these fields are not abundant. Therefore, in this paper, we aim to propose and evaluate several state-of-the-art neural network models in these fields. We first review the basics of representative models, namely long short-term memory and its variants, the temporal convolutional network and the generative adversarial network. Then, long short-term memory with autoencoder and attention-based models, the temporal convolutional network and the generative adversarial model are proposed and applied to time series classification and forecasting. Gaussian sliding window weights are proposed to speed the training process up. Finally, the performances of the proposed methods are assessed using five optimizers and loss functions with the public benchmark datasets, and comparisons between the proposed temporal convolutional network and several classical models are conducted. Experiments show the proposed models’ effectiveness and confirm that the temporal convolutional network is superior to long short-term memory models in sequence modeling. We conclude that the proposed temporal convolutional network reduces time consumption to around 80% compared to others while retaining the same accuracy. The unstable training process for generative adversarial network is circumvented by tuning hyperparameters and carefully choosing the appropriate optimizer of “Adam”. The proposed generative adversarial network also achieves comparable forecasting accuracy with traditional methods.
18
Lv, Yancheng, Lin Lin, Jie Liu, Hao Guo, and Changsheng Tong. "Research on Imbalanced Data Classification Based on Classroom-Like Generative Adversarial Networks." Neural Computation 34, no. 4 (March 23, 2022): 1045–73. http://dx.doi.org/10.1162/neco_a_01470.
Abstract:
Abstract Most of the research on machine learning classification methods is based on balanced data; the research on imbalanced data classification needs improvement. Generative adversarial networks (GANs) are able to learn high-dimensional complex data distribution without relying on a prior hypothesis, which has become a hot technology in artificial intelligence. In this letter, we propose a new structure, classroom-like generative adversarial networks (CLGANs), to construct a model with multiple generators. Taking inspiration from the fact that teachers arrange teaching activities according to students' learning situation, we propose a weight allocation function to adaptively adjust the influence weight of generator loss function on discriminator loss function. All the generators work together to improve the degree of discriminator and training sample space, so that a discriminator with excellent performance is trained and applied to the tasks of imbalanced data classification. Experimental results on the Case Western Reserve University data set and 2.4 GHz Indoor Channel Measurements data set show that the data classification ability of the discriminator trained by CLGANs with multiple generators is superior to that of other imbalanced data classification models, and the optimal discriminator can be obtained by selecting the right matching scheme of the generator models.
19
Zhang, Xia, and Mingyu Ma. "Research on sEMG Feature Generation and Classification Performance Based on EBGAN." Electronics 12, no. 4 (February 20, 2023): 1040. http://dx.doi.org/10.3390/electronics12041040.
Abstract:
Surface electromyography signal (sEMG) recognition technology requires a large number of samples to ensure the accuracy of the training results. However, sEMG signals generally have the problems of a small amount of data, complicated acquisition process and large environmental influence, which hinders the improvement of the accuracy of sEMG classification. In order to improve the accuracy of sEMG classification, an sEMG feature generation method based on an energy generative adversarial network (EBGAN) is proposed in this paper for the first time. The energy concept is introduced into the discriminant network instead of the traditional binary judgment, and the distribution of the real EMG dataset is learned and captured by multiple fully connected layers, with similar sEMG data being generated. The experimental results show that, compared with other types of GAN networks, this method achieves a small maximum mean discrepancy in comparison with that of the original data. The experimental results using different typical classification models show that the data augmentation method proposed can effectively improve the classification accuracy of typical classification models, and the accuracy increase range is 1~5%.
20
Li, Bohan, Xiao Xu, Xinghao Wang, Yutai Hou, Yunlong Feng, Feng Wang, Xuanliang Zhang, Qingfu Zhu, and Wanxiang Che. "Semantic-Guided Generative Image Augmentation Method with Diffusion Models for Image Classification." Proceedings of the AAAI Conference on Artificial Intelligence 38, no. 4 (March 24, 2024): 3018–27. http://dx.doi.org/10.1609/aaai.v38i4.28084.
Abstract:
Existing image augmentation methods consist of two categories: perturbation-based methods and generative methods. Perturbation-based methods apply pre-defined perturbations to augment an original image, but only locally vary the image, thus lacking image diversity. In contrast, generative methods bring more image diversity in the augmented images but may not preserve semantic consistency, thus may incorrectly change the essential semantics of the original image. To balance image diversity and semantic consistency in augmented images, we propose SGID, a Semantic-guided Generative Image augmentation method with Diffusion models for image classification. Specifically, SGID employs diffusion models to generate augmented images with good image diversity. More importantly, SGID takes image labels and captions as guidance to maintain semantic consistency between the augmented and original images. Experimental results show that SGID outperforms the best augmentation baseline by 1.72% on ResNet-50 (from scratch), 0.33% on ViT (ImageNet-21k), and 0.14% on CLIP-ViT (LAION-2B). Moreover, SGID can be combined with other image augmentation baselines and further improves the overall performance. We demonstrate the semantic consistency and image diversity of SGID through quantitative human and automated evaluations, as well as qualitative case studies.
21
Zhang, Zhaohui, Lijun Yang, Ligong Chen, Qiuwen Liu, Ying Meng, Pengwei Wang, and Maozhen Li. "A generative adversarial network–based method for generating negative financial samples." International Journal of Distributed Sensor Networks 16, no. 2 (February 2020): 155014772090705. http://dx.doi.org/10.1177/1550147720907053.
Abstract:
In financial anti-fraud field, negative samples are small and sparse with serious sample imbalanced problem. Generating negative samples consistent with original data to naturally solve imbalanced problem is a serious problem. This article proposes a new method to solve this problem. We introduce a new generation model, combined Generative Adversarial Network with Long Short-Term Memory network for one-dimensional negative financial samples. The characteristic association between transaction sequences can be learned by long short-term memory layer, and the generator covers real data distribution by the adversarial discriminator with time-sequence. Mapping data distribution to feature space is a common evaluation method of synthetic data; however, relationships between data attributes have been ignored in online transactions. We define a comprehensive evaluation method to evaluate the validity of generated samples from data distribution and attribute characteristics. Experimental results on real bank B2B transaction data show that the proposed model has higher overall ratings, which is 10% higher than traditional generation models. Finally, well-trained model is used to generate negative samples and form new dataset. The classification results on new datasets show that precision and recall are all higher than baseline models. Our work has a certain practical value and provides a new idea to solve imbalanced problem in whatever fields.
22
Sheeny, Marcel, Andrew Wallace, and Sen Wang. "RADIO: Parameterized Generative Radar Data Augmentation for Small Datasets." Applied Sciences 10, no. 11 (June 2, 2020): 3861. http://dx.doi.org/10.3390/app10113861.
Abstract:
We present a novel, parameterised radar data augmentation (RADIO) technique to generate realistic radar samples from small datasets for the development of radar-related deep learning models. RADIO leverages the physical properties of radar signals, such as attenuation, azimuthal beam divergence and speckle noise, for data generation and augmentation. Exemplary applications on radar-based classification and detection demonstrate that RADIO can generate meaningful radar samples that effectively boost the accuracy of classification and generalisability of deep models trained with a small dataset.
23
Gao, Dan, Xiaofang Wu, Zhijin Wen, Yue Xu, and Zhengchao Chen. "Few-shot SAR vehicle target augmentation based on generative adversarial networks." ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences X-1-2024 (May 9, 2024): 83–90. http://dx.doi.org/10.5194/isprs-annals-x-1-2024-83-2024.
Abstract:
Abstract. The study of few-shot SAR image generation is an effective way to expand the SAR dataset, which not only provides diversified data support for SAR target classification, but also provides a high-fidelity false image template for SAR deceptive jamming. In this paper, we have constructed a multi-frequency and multi-target type SAR vehicle imagery dataset that encompasses frequencies such as X, Ka, P, and S bands. The vehicle types are coaster, suv and cabin. Subsequently, we utilized various Generative Adversarial Networks for image generation from the SAR vehicle dataset. The experimental result indicates that the images generated by the DCGAN and the LSGAN models are of superior quality. Furthermore, we employed different recognition networks to evaluate the classification accuracy of the generated images. Of all the frequency bands, the Ka band generated images achieved the highest recognition rate, with an accuracy of up to 99%. Under conditions of a limited number of samples, the LSGAN model performed the best, reaching a classification recognition rate of 71.48% with a dataset of only 20 samples. Finally, we use a conditional network generation model to generate conditions based on target categories and frequency bands, providing high fidelity samples for SAR deception jamming.
24
Lee, Donghoun. "Driving Safety Area Classification for Automated Vehicles Based on Data Augmentation Using Generative Models." Sustainability 16, no. 11 (May 21, 2024): 4337. http://dx.doi.org/10.3390/su16114337.
Abstract:
The integration of automated vehicles (AVs) into existing road networks for mobility services presents unique challenges, particularly in discerning the driving safety areas associated with the automation mode of AVs. The assessment of AV’s capability to safely operate in a specific road section is contingent upon the occurrence of disengagement events within that section, which are evaluated against a predefined operational design domain (ODD). However, the process of collecting comprehensive data for all roadway areas is constrained by limited resources. Moreover, challenges are posed in accurately classifying whether a new roadway section can be safely operated by AVs when relying on restricted datasets. This research proposes a novel framework aimed at enhancing the discriminative capability of given classifiers in identifying safe driving areas for AVs, leveraging cutting-edge data augmentation algorithms using generative models, including generative adversarial networks (GANs) and diffusion-based models. The proposed framework is validated using a field test dataset containing disengagement events from expressways in South Korea. Performance evaluations are conducted across various metrics to demonstrate the effectiveness of the data augmentation models. The evaluation study concludes that the proposed framework significantly enhances the discriminative performance of the classifiers, contributing valuable insights into safer AV deployment in diverse road conditions.
25
Wu, Jheng-Long, and Shuoyen Huang. "Application of Generative Adversarial Networks and Shapley Algorithm Based on Easy Data Augmentation for Imbalanced Text Data." Applied Sciences 12, no. 21 (October 29, 2022): 10964. http://dx.doi.org/10.3390/app122110964.
Abstract:
Imbalanced data constitute an extensively studied problem in the field of machine learning classification because they result in poor training outcomes. Data augmentation is a method for increasing minority class diversity. In the field of text data augmentation, easy data augmentation (EDA) is used to generate additional data that would otherwise lack diversity and exhibit monotonic sentence patterns. Generative adversarial network (GAN) models can generate diverse sentence patterns by using the probability corresponding to each word in a language model. Therefore, hybrid EDA and GAN models can generate highly diverse and appropriate sentence patterns. This study proposes a hybrid framework that employs a generative adversarial network and Shapley algorithm based on easy data augmentation (HEGS) to improve classification performance. The experimental results reveal that the HEGS framework can generate highly diverse training sentences to form balanced text data and improve text classification performance for minority classes.
26
Škorić, Mihailo, Miloš Utvić, and Ranka Stanković. "Transformer-Based Composite Language Models for Text Evaluation and Classification." Mathematics 11, no. 22 (November 16, 2023): 4660. http://dx.doi.org/10.3390/math11224660.
Abstract:
Parallel natural language processing systems were previously successfully tested on the tasks of part-of-speech tagging and authorship attribution through mini-language modeling, for which they achieved significantly better results than independent methods in the cases of seven European languages. The aim of this paper is to present the advantages of using composite language models in the processing and evaluation of texts written in arbitrary highly inflective and morphology-rich natural language, particularly Serbian. A perplexity-based dataset, the main asset for the methodology assessment, was created using a series of generative pre-trained transformers trained on different representations of the Serbian language corpus and a set of sentences classified into three groups (expert translations, corrupted translations, and machine translations). The paper describes a comparative analysis of calculated perplexities in order to measure the classification capability of different models on two binary classification tasks. In the course of the experiment, we tested three standalone language models (baseline) and two composite language models (which are based on perplexities outputted by all three standalone models). The presented results single out a complex stacked classifier using a multitude of features extracted from perplexity vectors as the optimal architecture of composite language models for both tasks.
27
Jie, Zhideng, Hong Zhang, Kaixuan Li, Xiao Xie, and Aopu Shi. "Image Enhancement of Steel Plate Defects Based on Generative Adversarial Networks." Electronics 13, no. 11 (May 22, 2024): 2013. http://dx.doi.org/10.3390/electronics13112013.
Abstract:
In this study, the problem of a limited number of data samples, which affects the detection accuracy, arises for the image classification task of steel plate surface defects under conditions of small sample sizes. A data enhancement method based on generative adversarial networks is proposed. The method introduces a two-way attention mechanism, which is specifically designed to improve the model’s ability to identify weak defects and optimize the model structure of the network discriminator, which augments the model’s capacity to perceive the overall details of the image and effectively improves the intricacy and authenticity of the generated images. By enhancing the two original datasets, the experimental results show that the proposed method improves the average accuracy by 8.5% across the four convolutional classification models. The results demonstrate the superior detection accuracy of the proposed method, improving the classification of steel plate surface defects.
28
Chen, Yushi, Lingbo Huang, Lin Zhu, Naoto Yokoya, and Xiuping Jia. "Fine-Grained Classification of Hyperspectral Imagery Based on Deep Learning." Remote Sensing 11, no. 22 (November 18, 2019): 2690. http://dx.doi.org/10.3390/rs11222690.
Abstract:
Hyperspectral remote sensing obtains abundant spectral and spatial information of the observed object simultaneously. It is an opportunity to classify hyperspectral imagery (HSI) with a fine-grained manner. In this study, the fine-grained classification of HSI, which contains a large number of classes, is investigated. On one hand, traditional classification methods cannot handle fine-grained classification of HSI well; on the other hand, deep learning methods have shown their powerfulness in fine-grained classification. So, in this paper, deep learning is explored for HSI supervised and semi-supervised fine-grained classification. For supervised HSI fine-grained classification, densely connected convolutional neural network (DenseNet) is explored for accurate classification. Moreover, DenseNet is combined with pre-processing technique (i.e., principal component analysis or auto-encoder) or post-processing technique (i.e., conditional random field) to further improve classification performance. For semi-supervised HSI fine-grained classification, a generative adversarial network (GAN), which includes a discriminative CNN and a generative CNN, is carefully designed. The GAN fully uses the labeled and unlabeled samples to improve classification accuracy. The proposed methods were tested on the Indian Pines data set, which contains 33,3951 samples with 52 classes. The experimental results show that the deep learning-based methods provide great improvements compared with other traditional methods, which demonstrate that deep models have huge potential for HSI fine-grained classification.
29
Chatterjee, Kalyan, M. Raju, N. Selvamuthukumaran, M. Pramod, B. Krishna Kumar, Anjan Bandyopadhyay, and Saurav Mallik. "HaCk: Hand Gesture Classification Using a Convolutional Neural Network and Generative Adversarial Network-Based Data Generation Model." Information 15, no. 2 (February 4, 2024): 85. http://dx.doi.org/10.3390/info15020085.
Abstract:
According to global data on visual impairment from the World Health Organization in 2010, an estimated 285 million individuals, including 39 million who are blind, face visual impairments. These individuals use non-contact methods such as voice commands and hand gestures to interact with user interfaces. Recognizing the significance of hand gesture recognition for this vulnerable population and aiming to improve user usability, this study employs a Generative Adversarial Network (GAN) coupled with Convolutional Neural Network (CNN) techniques to generate a diverse set of hand gestures. Recognizing hand gestures using HaCk typically involves a two-step approach. First, the GAN is trained to generate synthetic hand gesture images, and then a separate CNN is employed to classify gestures in real-world data. The evaluation of HaCk is demonstrated through a comparative analysis using Leave-One-Out Cross-Validation (LOO CV) and Holdout Cross-Validation (Holdout CV) tests. These tests are crucial for assessing the model’s generalization, robustness, and suitability for practical applications. The experimental results reveal that the performance of HaCk surpasses that of other compared ML/DL models, including CNN, FTCNN, CDCGAN, GestureGAN, GGAN, MHG-CAN, and ASL models. Specifically, the improvement percentages for the LOO CV Test are 17.03%, 20.27%, 15.76%, 13.76%, 10.16%, 5.90%, and 15.90%, respectively. Similarly, for the Holdout CV Test, HaCk outperforms HU, ZM, GB, GB-ZM, GB-HU, CDCGAN, GestureGAN, GGAN, MHG-CAN, and ASL models, with improvement percentages of 56.87%, 15.91%, 13.97%, 24.81%, 23.52%, 17.72%, 15.72%, 12.12%, 7.94%, and 17.94%, respectively.
30
Li, Yuanming, Bonhwa Ku, Shou Zhang, Jae-Kwang Ahn, and Hanseok Ko. "Seismic Data Augmentation Based on Conditional Generative Adversarial Networks." Sensors 20, no. 23 (November 30, 2020): 6850. http://dx.doi.org/10.3390/s20236850.
Abstract:
Realistic synthetic data can be useful for data augmentation when training deep learning models to improve seismological detection and classification performance. In recent years, various deep learning techniques have been successfully applied in modern seismology. Due to the performance of deep learning depends on a sufficient volume of data, the data augmentation technique as a data-space solution is widely utilized. In this paper, we propose a Generative Adversarial Networks (GANs) based model that uses conditional knowledge to generate high-quality seismic waveforms. Unlike the existing method of generating samples directly from noise, the proposed method generates synthetic samples based on the statistical characteristics of real seismic waveforms in embedding space. Moreover, a content loss is added to relate high-level features extracted by a pre-trained model to the objective function to enhance the quality of the synthetic data. The classification accuracy is increased from 96.84% to 97.92% after mixing a certain amount of synthetic seismic waveforms, and results of the quality of seismic characteristics derived from the representative experiment show that the proposed model provides an effective structure for generating high-quality synthetic seismic waveforms. Thus, the proposed model is experimentally validated as a promising approach to realistic high-quality seismic waveform data augmentation.
31
Liu, Kun, Xiaolin Ning, and Sidong Liu. "Medical Image Classification Based on Semi-Supervised Generative Adversarial Network and Pseudo-Labelling." Sensors 22, no. 24 (December 17, 2022): 9967. http://dx.doi.org/10.3390/s22249967.
Abstract:
Deep learning has substantially improved the state-of-the-art in object detection and image classification. Deep learning usually requires large-scale labelled datasets to train the models; however, due to the restrictions in medical data sharing and accessibility and the expensive labelling cost, the application of deep learning in medical image classification has been dramatically hindered. In this study, we propose a novel method that leverages semi-supervised adversarial learning and pseudo-labelling to incorporate the unlabelled images in model learning. We validate the proposed method on two public databases, including ChestX-ray14 for lung disease classification and BreakHis for breast cancer histopathological image diagnosis. The results show that our method achieved highly effective performance with an accuracy of 93.15% while using only 30% of the labelled samples, which is comparable to the state-of-the-art accuracy for chest X-ray classification; it also outperformed the current methods in multi-class breast cancer histopathological image classification with a high accuracy of 96.87%.
32
Shaik, Abdul Lateef Haroon Phulara, Monica Komala Manoharan, Alok Kumar Pani, Raji Reddy Avala, and Chien-Ming Chen. "Gaussian Mutation–Spider Monkey Optimization (GM-SMO) Model for Remote Sensing Scene Classification." Remote Sensing 14, no. 24 (December 11, 2022): 6279. http://dx.doi.org/10.3390/rs14246279.
Abstract:
Scene classification aims to classify various objects and land use classes such as farms, highways, rivers, and airplanes in the remote sensing images. In recent times, the Convolutional Neural Network (CNN) based models have been widely applied in scene classification, due to their efficiency in feature representation. The CNN based models have the limitation of overfitting problems, due to the generation of more features in the convolutional layer and imbalanced data problems. This study proposed Gaussian Mutation–Spider Monkey Optimization (GM-SMO) model for feature selection to solve overfitting and imbalanced data problems in scene classification. The Gaussian mutation changes the position of the solution after exploration to increase the exploitation in feature selection. The GM-SMO model maintains better tradeoff between exploration and exploitation to select relevant features for superior classification. The GM-SMO model selects unique features to overcome overfitting and imbalanced data problems. In this manuscript, the Generative Adversarial Network (GAN) is used for generating the augmented images, and the AlexNet and Visual Geometry Group (VGG) 19 models are applied to extract the features from the augmented images. Then, the GM-SMO model selects unique features, which are given to the Long Short-Term Memory (LSTM) network for classification. In the resulting phase, the GM-SMO model achieves 99.46% of accuracy, where the existing transformer-CNN has achieved only 98.76% on the UCM dataset.
33
Mounica, Mrs K. V. S. "GAN Based Multi-Class Skin Disease Classification: Deep Learning Approach." International Journal for Research in Applied Science and Engineering Technology 12, no. 5 (May 31, 2024): 137–42. http://dx.doi.org/10.22214/ijraset.2024.61366.
Abstract:
Abstract: Skin diseases pose significant diagnostic and treatment challenges due to their diverse and complex manifestations. Convolutional neural networks (CNNs) have demonstrated superior capabilities in image classification tasks, including skin disease identification. However, the performance of CNN models depends heavily on the quality and quantity of training data, which often suffers from limitations such as imbalance and sparsity. This project proposes an approach new approach to address these challenges by integrating generative adversarial networks (GANs). ) with CNN for multi-class skin disease classification. The GAN-based system aims to improve the diversity and quantity of the training dataset by generating synthetic images of various skin conditions. Through an adversarial training process, the generator network learns to generate realistic images of skin diseases, while the discriminator network distinguishes between real and synthetic data. Figures The synthetic images generated by the GAN are then combined with the real dataset to train the model CNN. specially designed to classify skin diseases.
34
Alhumaid, Mohammad, and Ayman G. Fayoumi. "Transfer Learning-Based Classification of Maxillary Sinus Using Generative Adversarial Networks." Applied Sciences 14, no. 7 (April 6, 2024): 3083. http://dx.doi.org/10.3390/app14073083.
Abstract:
Paranasal sinus pathologies, particularly those affecting the maxillary sinuses, pose significant challenges in diagnosis and treatment due to the complex anatomical structures and diverse disease manifestations. The aim of this study is to investigate the use of deep learning techniques, particularly generative adversarial networks (GANs), in combination with convolutional neural networks (CNNs), for the classification of sinus pathologies in medical imaging data. The dataset is composed of images obtained through computed tomography (CT) scans, covering cases classified into “Moderate”, “Severe”, and “Normal” classes. The lightweight GAN is applied to augment a dataset by creating synthetic images, which are then used to train and test the ResNet-50 and ResNeXt-50 models. The model performance is optimized using random search to perform hyperparameter tuning, and the evaluation is conducted extensively for various metrics like accuracy, precision, recall, and the F1-score. The results demonstrate the effectiveness of the proposed approach in accurately classifying sinus pathologies, with the ResNeXt-50 model achieving superior performance with accuracy: 91.154, precision: 0.917, recall: 0.912, and F1-score: 0.913 compared to ResNet-50. This study highlights the potential of GAN-based data augmentation and deep learning techniques in enhancing the diagnosis of maxillary sinus diseases.
35
Schaudt, Daniel, Christian Späte, Reinhold von Schwerin, Manfred Reichert, Marianne von Schwerin, Meinrad Beer, and Christopher Kloth. "A Critical Assessment of Generative Models for Synthetic Data Augmentation on Limited Pneumonia X-ray Data." Bioengineering 10, no. 12 (December 14, 2023): 1421. http://dx.doi.org/10.3390/bioengineering10121421.
Abstract:
In medical imaging, deep learning models serve as invaluable tools for expediting diagnoses and aiding specialized medical professionals in making clinical decisions. However, effectively training deep learning models typically necessitates substantial quantities of high-quality data, a resource often lacking in numerous medical imaging scenarios. One way to overcome this deficiency is to artificially generate such images. Therefore, in this comparative study we train five generative models to artificially increase the amount of available data in such a scenario. This synthetic data approach is evaluated on a a downstream classification task, predicting four causes for pneumonia as well as healthy cases on 1082 chest X-ray images. Quantitative and medical assessments show that a Generative Adversarial Network (GAN)-based approach significantly outperforms more recent diffusion-based approaches on this limited dataset with better image quality and pathological plausibility. We show that better image quality surprisingly does not translate to improved classification performance by evaluating five different classification models and varying the amount of additional training data. Class-specific metrics like precision, recall, and F1-score show a substantial improvement by using synthetic images, emphasizing the data rebalancing effect of less frequent classes. However, overall performance does not improve for most models and configurations, except for a DreamBooth approach which shows a +0.52 improvement in overall accuracy. The large variance of performance impact in this study suggests a careful consideration of utilizing generative models for limited data scenarios, especially with an unexpected negative correlation between image quality and downstream classification improvement.
36
Elzobi, Moftah, and Ayoub Al-Hamadi. "Generative vs. Discriminative Recognition Models for Off-Line Arabic Handwriting." Sensors 18, no. 9 (August 24, 2018): 2786. http://dx.doi.org/10.3390/s18092786.
Abstract:
The majority of handwritten word recognition strategies are constructed on learning-based generative frameworks from letter or word training samples. Theoretically, constructing recognition models through discriminative learning should be the more effective alternative. The primary goal of this research is to compare the performances of discriminative and generative recognition strategies, which are described by generatively-trained hidden Markov modeling (HMM), discriminatively-trained conditional random fields (CRF) and discriminatively-trained hidden-state CRF (HCRF). With learning samples obtained from two dissimilar databases, we initially trained and applied an HMM classification scheme. To enable HMM classifiers to effectively reject incorrect and out-of-vocabulary segmentation, we enhance the models with adaptive threshold schemes. Aside from proposing such schemes for HMM classifiers, this research introduces CRF and HCRF classifiers in the recognition of offline Arabic handwritten words. Furthermore, the efficiencies of all three strategies are fully assessed using two dissimilar databases. Recognition outcomes for both words and letters are presented, with the pros and cons of each strategy emphasized.
37
Lee, Junghyuk, Jun-Hyuk Kim, and Jong-Seok Lee. "Demystifying Randomly Initialized Networks for Evaluating Generative Models." Proceedings of the AAAI Conference on Artificial Intelligence 37, no. 7 (June 26, 2023): 8482–90. http://dx.doi.org/10.1609/aaai.v37i7.26022.
Abstract:
Evaluation of generative models is mostly based on the comparison between the estimated distribution and the ground truth distribution in a certain feature space. To embed samples into informative features, previous works often use convolutional neural networks optimized for classification, which is criticized by recent studies. Therefore, various feature spaces have been explored to discover alternatives. Among them, a surprising approach is to use a randomly initialized neural network for feature embedding. However, the fundamental basis to employ the random features has not been sufficiently justified. In this paper, we rigorously investigate the feature space of models with random weights in comparison to that of trained models. Furthermore, we provide an empirical evidence to choose networks for random features to obtain consistent and reliable results. Our results indicate that the features from random networks can evaluate generative models well similarly to those from trained networks, and furthermore, the two types of features can be used together in a complementary way.
38
Abedi, Masoud, Lars Hempel, Sina Sadeghi, and Toralf Kirsten. "GAN-Based Approaches for Generating Structured Data in the Medical Domain." Applied Sciences 12, no. 14 (July 13, 2022): 7075. http://dx.doi.org/10.3390/app12147075.
Abstract:
Modern machine and deep learning methods require large datasets to achieve reliable and robust results. This requirement is often difficult to meet in the medical field, due to data sharing limitations imposed by privacy regulations or the presence of a small number of patients (e.g., rare diseases). To address this data scarcity and to improve the situation, novel generative models such as Generative Adversarial Networks (GANs) have been widely used to generate synthetic data that mimic real data by representing features that reflect health-related information without reference to real patients. In this paper, we consider several GAN models to generate synthetic data used for training binary (malignant/benign) classifiers, and compare their performances in terms of classification accuracy with cases where only real data are considered. We aim to investigate how synthetic data can improve classification accuracy, especially when a small amount of data is available. To this end, we have developed and implemented an evaluation framework where binary classifiers are trained on extended datasets containing both real and synthetic data. The results show improved accuracy for classifiers trained with generated data from more advanced GAN models, even when limited amounts of original data are available.
39
You, Yuyang, Xiaoyu Guo, Xuyang Zhong, and Zhihong Yang. "A Few-Shot Learning-Based EEG and Stage Transition Sequence Generator for Improving Sleep Staging Performance." Biomedicines 10, no. 12 (November 22, 2022): 3006. http://dx.doi.org/10.3390/biomedicines10123006.
Abstract:
In this study, generative adversarial networks named SleepGAN are proposed to expand the training set for automatic sleep stage classification tasks by generating both electroencephalogram (EEG) epochs and sequence relationships of sleep stages. In order to reach high accuracy, most existing classification methods require substantial amounts of training data, but obtaining such quantities of real EEG epochs is expensive and time-consuming. We introduce few-shot learning, which is a method of training a GAN using a very small set of training data. This paper presents progressive Wasserstein divergence generative adversarial networks (GANs) and a relational memory generator to generate EEG epochs and stage transition sequences, respectively. For the evaluation of our generated data, we use single-channel EEGs from the public dataset Sleep-EDF. The addition of our augmented data and sequence to the training set was shown to improve the performance of the classification model. The accuracy of the model increased by approximately 1% after incorporating generated EEG epochs. Adding both the augmented data and sequence to the training set resulted in a further increase of 3%, from the original accuracy of 79.40% to 83.06%. The result proves that SleepGAN is a set of GANs capable of generating realistic EEG epochs and transition sequences under the condition of insufficient training data and can be used to enlarge the training dataset and improve the performance of sleep stage classification models in clinical practice.
40
Cheng, Ruoxi. "Expansion of the CT-scans image set based on the pretrained DCGAN for improving the performance of the CNN." Journal of Physics: Conference Series 2646, no. 1 (December 1, 2023): 012015. http://dx.doi.org/10.1088/1742-6596/2646/1/012015.
Abstract:
Abstract Diagnosis of COVID-19 based on CT scans images using artificial intelligence can massively reduce medical manpower, time, and resources and reduce misdiagnosis rate. However, there are few relevant image sets publicly available at present, which is not conducive to the training of models such as classification. Transfer learning has been extensively considered in image classification, but less utilized in image generation. This work attempts to expand this dataset with discriminators using Deep Convolutional Generative Adversarial Network (DCGAN) models of Imagenet pre-training models and verify the significance of pre-training models for generating image veracity. A DCGAN model using the Imagenet pre-training model (i.e. resnet18) and a DCGAN network without the pre-train model generated 100 positive and 100 negative images to extend the original dataset, respectively. These images were classified using a Convolutional Neural Network (CNN) binary classifier, and the accuracy improved from 82.67% to 85.33% after adding the pre-training model. Furthermore, the comparison shown by the Gradcam visualization shows that the discriminator with the pre-training model can better capture the key details of the images. This experiment shows that even though Imagenet and lung images are totally uncorrelated, there are still some features that can be transferred. It also demonstrates that Imagenet pre-training models can improve the quality of GAN-generated images, extending the application of migration transfer learning.
41
Divyanth, L. G., D. S. Guru, Peeyush Soni, Rajendra Machavaram, Mohammad Nadimi, and Jitendra Paliwal. "Image-to-Image Translation-Based Data Augmentation for Improving Crop/Weed Classification Models for Precision Agriculture Applications." Algorithms 15, no. 11 (October 30, 2022): 401. http://dx.doi.org/10.3390/a15110401.
Abstract:
Applications of deep-learning models in machine visions for crop/weed identification have remarkably upgraded the authenticity of precise weed management. However, compelling data are required to obtain the desired result from this highly data-driven operation. This study aims to curtail the effort needed to prepare very large image datasets by creating artificial images of maize (Zea mays) and four common weeds (i.e., Charlock, Fat Hen, Shepherd’s Purse, and small-flowered Cranesbill) through conditional Generative Adversarial Networks (cGANs). The fidelity of these synthetic images was tested through t-distributed stochastic neighbor embedding (t-SNE) visualization plots of real and artificial images of each class. The reliability of this method as a data augmentation technique was validated through classification results based on the transfer learning of a pre-defined convolutional neural network (CNN) architecture—the AlexNet; the feature extraction method came from the deepest pooling layer of the same network. Machine learning models based on a support vector machine (SVM) and linear discriminant analysis (LDA) were trained using these feature vectors. The F1 scores of the transfer learning model increased from 0.97 to 0.99, when additionally supported by an artificial dataset. Similarly, in the case of the feature extraction technique, the classification F1-scores increased from 0.93 to 0.96 for SVM and from 0.94 to 0.96 for the LDA model. The results show that image augmentation using generative adversarial networks (GANs) can improve the performance of crop/weed classification models with the added advantage of reduced time and manpower. Furthermore, it has demonstrated that generative networks could be a great tool for deep-learning applications in agriculture.
42
Hsieh, Chen-Chiung, Ti-Yun Hsu, and Wei-Hsin Huang. "An Online Rail Track Fastener Classification System Based on YOLO Models." Sensors 22, no. 24 (December 17, 2022): 9970. http://dx.doi.org/10.3390/s22249970.
Abstract:
In order to save manpower on rail track inspection, computer vision-based methodologies are developed. We propose utilizing the YOLOv4-Tiny neural network to identify track defects in real time. There are ten defects covering fasteners, rail surfaces, and sleepers from the upward and six defects about the rail waist from the sideward. The proposed real-time inspection system includes a high-performance notebook, two sports cameras, and three parallel processes. The hardware is mounted on a flat cart running at 30 km/h. The inspection results about the abnormal track components could be queried by defective type, time, and the rail hectometer stake. In the experiments, data augmentation by a Cycle Generative Adversarial Network (GAN) is used to increase the dataset. The number of images is 3800 on the upward and 967 on the sideward. Five object detection neural network models—YOLOv4, YOLOv4-Tiny, YOLOX-Tiny, SSD512, and SSD300—were tested. The YOLOv4-Tiny model with 150 FPS is selected as the recognition kernel, as it achieved 91.7%, 92%, and 91% for the mAP, precision, and recall of the defective track components from the upward, respectively. The mAP, precision, and recall of the defective track components from the sideward are 99.16%, 96%, and 94%, respectively.
43
Wang, Ziyue, and Junjun Guo. "Self-adaptive attention fusion for multimodal aspect-based sentiment analysis." Mathematical Biosciences and Engineering 21, no. 1 (2023): 1305–20. http://dx.doi.org/10.3934/mbe.2024056.
Abstract:
<abstract><p>Multimodal aspect term extraction (MATE) and multimodal aspect-oriented sentiment classification (MASC) are two crucial subtasks in multimodal sentiment analysis. The use of pretrained generative models has attracted increasing attention in aspect-based sentiment analysis (ABSA). However, the inherent semantic gap between textual and visual modalities poses a challenge in transferring text-based generative pretraining models to image-text multimodal sentiment analysis tasks. To tackle this issue, this paper proposes a self-adaptive cross-modal attention fusion architecture for joint multimodal aspect-based sentiment analysis (JMABSA), which is a generative model based on an image-text selective fusion mechanism that aims to bridge the semantic gap between text and image representations and adaptively transfer a textual-based pretraining model to the multimodal JMASA task. We conducted extensive experiments on two benchmark datasets, and the experimental results show that our model significantly outperforms other state of the art approaches by a significant margin.</p></abstract>
44
Alrashedy, Halima Hamid N., Atheer Fahad Almansour, Dina M. Ibrahim, and Mohammad Ali A. Hammoudeh. "BrainGAN: Brain MRI Image Generation and Classification Framework Using GAN Architectures and CNN Models." Sensors 22, no. 11 (June 6, 2022): 4297. http://dx.doi.org/10.3390/s22114297.
Abstract:
Deep learning models have been used in several domains, however, adjusting is still required to be applied in sensitive areas such as medical imaging. As the use of technology in the medical domain is needed because of the time limit, the level of accuracy assures trustworthiness. Because of privacy concerns, machine learning applications in the medical field are unable to use medical data. For example, the lack of brain MRI images makes it difficult to classify brain tumors using image-based classification. The solution to this challenge was achieved through the application of Generative Adversarial Network (GAN)-based augmentation techniques. Deep Convolutional GAN (DCGAN) and Vanilla GAN are two examples of GAN architectures used for image generation. In this paper, a framework, denoted as BrainGAN, for generating and classifying brain MRI images using GAN architectures and deep learning models was proposed. Consequently, this study proposed an automatic way to check that generated images are satisfactory. It uses three models: CNN, MobileNetV2, and ResNet152V2. Training the deep transfer models with images made by Vanilla GAN and DCGAN, and then evaluating their performance on a test set composed of real brain MRI images. From the results of the experiment, it was found that the ResNet152V2 model outperformed the other two models. The ResNet152V2 achieved 99.09% accuracy, 99.12% precision, 99.08% recall, 99.51% area under the curve (AUC), and 0.196 loss based on the brain MRI images generated by DCGAN architecture.
45
Yan, Yang, Wen Bo Huang, Yun Ji Wang, and Na Li. "Image Labeling Model Based on Conditional Random Fields." Advanced Materials Research 756-759 (September 2013): 3869–73. http://dx.doi.org/10.4028/www.scientific.net/amr.756-759.3869.
Abstract:
We present conditional random fields (CRFs), a framework for building probabilistic models to segment and label sequence data, and use CRFs to label pixels in an image. CRFs provide a discriminative framework to incorporate spatial dependencies in an image, which is more appropriate for classification tasks as opposed to a generative framework. In this paper we apply CRF to an image classification tasks: an image labeling problem (manmade vs. natural regions in the MSRC 21-object class datasets). Parameter learning is performed using contrastive divergence (CD) algorithm to maximize an approximation to the conditional likelihood. We focus on two aspects of the classification task: feature extraction and classifiers design. We present classification results on sample images from MSRC 21-object class datasets.
46
Alhoraibi, Lamia, Daniyal Alghazzawi, and Reemah Alhebshi. "Generative Adversarial Network-Based Data Augmentation for Enhancing Wireless Physical Layer Authentication." Sensors 24, no. 2 (January 19, 2024): 641. http://dx.doi.org/10.3390/s24020641.
Abstract:
Wireless physical layer authentication has emerged as a promising approach to wireless security. The topic of wireless node classification and recognition has experienced significant advancements due to the rapid development of deep learning techniques. The potential of using deep learning to address wireless security issues should not be overlooked due to its considerable capabilities. Nevertheless, the utilization of this approach in the classification of wireless nodes is impeded by the lack of available datasets. In this study, we provide two models based on a data-driven approach. First, we used generative adversarial networks to design an automated model for data augmentation. Second, we applied a convolutional neural network to classify wireless nodes for a wireless physical layer authentication model. To verify the effectiveness of the proposed model, we assessed our results using an original dataset as a baseline and a generated synthetic dataset. The findings indicate an improvement of approximately 19% in classification accuracy rate.
47
Boone, Kyle. "ParSNIP: Generative Models of Transient Light Curves with Physics-enabled Deep Learning." Astronomical Journal 162, no. 6 (December 1, 2021): 275. http://dx.doi.org/10.3847/1538-3881/ac2a2d.
Abstract:
Abstract We present a novel method to produce empirical generative models of all kinds of astronomical transients from data sets of unlabeled light curves. Our hybrid model, which we call ParSNIP, uses a neural network to model the unknown intrinsic diversity of different transients and an explicit physics-based model of how light from the transient propagates through the universe and is observed. The ParSNIP model predicts the time-varying spectra of transients despite only being trained on photometric observations. With a three-dimensional intrinsic model, we are able to fit out-of-sample multiband light curves of many different kinds of transients with model uncertainties of 0.04–0.06 mag. The representation learned by the ParSNIP model is invariant to redshift, so it can be used to perform photometric classification of transients even with heavily biased training sets. Our classification techniques significantly outperform state-of-the-art methods on both simulated (PLAsTiCC) and real (PS1) data sets with 2.3× and 2× less contamination, respectively, for classification of Type Ia supernovae. We demonstrate how our model can identify previously unobserved kinds of transients and produce a sample that is 90% pure. The ParSNIP model can also estimate distances to Type Ia supernovae in the PS1 data set with an rms of 0.150 ± 0.007 mag compared to 0.155 ± 0.008 mag for the SALT2 model on the same sample. We discuss how our model could be used to produce distance estimates for supernova cosmology without the need for explicit classification.
48
Yang, Guan, Chao Li, Xiaojun Liu, and Guangyou Fang. "A THz Passive Image Generation Method Based on Generative Adversarial Networks." Applied Sciences 12, no. 4 (February 14, 2022): 1976. http://dx.doi.org/10.3390/app12041976.
Abstract:
A terahertz (THz) passive imager with automatic target detection is an effective solution in the field of security inspection. The high-quality training datasets always play a key role in the high-precision target detection applications. However, due to the difficulty of passive image data acquisition and the lack of public dataset resources, the high-quality training datasets are often insufficient. The generative adversarial network (GAN) is an effective method for data augmentation. To enrich the dataset with the generated images, it is necessary to ensure that the generated images have high quality, good diversity, and correct category information. In this paper, a GAN-based generation model is proposed to generate terahertz passive images. By applying different residual connection structures in the generator and discriminator, the models have strong feature extracting ability. Additionally, the Wasserstein loss function with gradient penalty is used to maintain training stability. The self-developed 0.2 THz band passive imager is used to carry out imaging experiments, and the imaging results are collected as a dataset to verify the proposed method. Finally, a quality evaluation method suitable for THz passive image generation task is proposed, and classification tests are performed on the generated images. The results show that the proposed method can provide high-quality images as supplementary.
49
Gaspar, Héléna A., Gilles Marcou, Dragos Horvath, Alban Arault, Sylvain Lozano, Philippe Vayer, and Alexandre Varnek. "Generative Topographic Mapping-Based Classification Models and Their Applicability Domain: Application to the Biopharmaceutics Drug Disposition Classification System (BDDCS)." Journal of Chemical Information and Modeling 53, no. 12 (December 9, 2013): 3318–25. http://dx.doi.org/10.1021/ci400423c.
50
Lu, Zhengdong, Todd K. Leen, and Jeffrey Kaye. "Kernels for Longitudinal Data with Variable Sequence Length and Sampling Intervals." Neural Computation 23, no. 9 (September 2011): 2390–420. http://dx.doi.org/10.1162/neco_a_00164.
Abstract:
We develop several kernel methods for classification of longitudinal data and apply them to detect cognitive decline in the elderly. We first develop mixed-effects models, a type of hierarchical empirical Bayes generative models, for the time series. After demonstrating their utility in likelihood ratio classifiers (and the improvement over standard regression models for such classifiers), we develop novel Fisher kernels based on mixture of mixed-effects models and use them in support vector machine classifiers. The hierarchical generative model allows us to handle variations in sequence length and sampling interval gracefully. We also give nonparametric kernels not based on generative models, but rather on the reproducing kernel Hilbert space. We apply the methods to detecting cognitive decline from longitudinal clinical data on motor and neuropsychological tests. The likelihood ratio classifiers based on the neuropsychological tests perform better than than classifiers based on the motor behavior. Discriminant classifiers performed better than likelihood ratio classifiers for the motor behavior tests.