This paper presents a neural network simulator based on anonymized patient motions that measures, categorizes, and infers human gestures based on a library of anonymized patient motions. There is a need for a sufficient training set for deep learning applications (DL). Our proposal is to extend a database that includes a limited number of videos of human physiotherapy activities with synthetic data. As a result of our posture generator, we are able to generate skeletal vectors that depict human movement. A human skeletal model is generated by using OpenPose (OP) from multiple-person videos and photographs. In every video frame, OP represents each human skeletal position as a vector in Euclidean space. The GAN is used to generate new samples and control the parameters of the motion. The joints in our skeletal model have been restructured to emphasize their linkages using depth-first search (DFS), a method for searching tree structures. Additionally, this work explores solutions to common problems associated with the acquisition of human gesture data, such as synchronizing activities and linking them to time and space. A new simulator is proposed that generates a sequence of virtual coordinated human movements based upon a script.

• Klíčová slova
• Generative Adversarial Network (GAN), Human body movements, OpenPose, Rehabilitation, Siamese twins Neural Network, Simulator,
• MeSH
• databáze faktografické MeSH
• lidé MeSH
• neuronové sítě * MeSH
• pohyb * MeSH
• Check Tag
• lidé MeSH
• Publikační typ
• časopisecké články MeSH

This paper deals with the vulnerability of machine learning models to adversarial examples and its implication for robustness and generalization properties. We propose an evolutionary algorithm that can generate adversarial examples for any machine learning model in the black-box attack scenario. This way, we can find adversarial examples without access to model's parameters, only by querying the model at hand. We have tested a range of machine learning models including deep and shallow neural networks. Our experiments have shown that the vulnerability to adversarial examples is not only the problem of deep networks, but it spreads through various machine learning architectures. Rather, it depends on the type of computational units. Local units, such as Gaussian kernels, are less vulnerable to adversarial examples.

• Klíčová slova
• Adversarial examples, Genetic algorithms, Kernel methods, Neural networks, Supervised learning,
• MeSH
• algoritmy MeSH
• lidé MeSH
• neuronové sítě * MeSH
• řízené strojové učení * trendy   MeSH
• rozpoznávání automatizované metody   trendy   MeSH
• strojové učení trendy   MeSH
• Check Tag
• lidé MeSH
• Publikační typ
• časopisecké články MeSH

A novel methodology for dataset augmentation in the semantic segmentation of coil-coated surface degradation is presented in this study. Deep convolutional generative adversarial networks (DCGAN) are employed to generate synthetic input-target pairs, which closely resemble real-world data, with the goal of expanding an existing dataset. These augmented datasets are used to train two state-of-the-art models, U-net, and DeepLabV3, for the precise detection of degradation areas around scribes. In a series of experiments, it was demonstrated that the introduction of synthetic data improves the models' performance in detecting degradation, especially when the ratio of synthetic to real data is carefully managed. Results indicate that optimal improvements in accuracy and F1-score are achieved when the ratio of synthetic to original data is between 0.2 and 0.5. Moreover, the advantages and limitations of different GAN architectures for dataset expansion are explored, with specific attention to their ability to produce realistic and diverse samples. This work offers a scalable solution to the challenges associated with creating large and diverse annotated datasets for industrial applications of coil coating degradation assessment. The proposed approach provides a significant contribution by improving model generalization and segmentation accuracy while reducing the burden of manual data annotation. These findings have important implications for industries relying on coil coatings, as more efficient and accurate degradation detection methods are enabled.

• Klíčová slova
• coil coating, deep learning, degradation, delamination, generative adversarial network, semantic segmentation,
• Publikační typ
• časopisecké články MeSH

Designing a cranial implant to restore the protective and aesthetic function of the patient's skull is a challenging process that requires a substantial amount of manual work, even for an experienced clinician. While computer-assisted approaches with various levels of required user interaction exist to aid this process, they are usually only validated on either a single type of simple synthetic defect or a very limited sample of real defects. The work presented in this paper aims to address two challenges: (i) design a fully automatic 3D shape reconstruction method that can address diverse shapes of real skull defects in various stages of healing and (ii) to provide an open dataset for optimization and validation of anatomical reconstruction methods on a set of synthetically broken skull shapes. We propose an application of the multi-scale cascade architecture of convolutional neural networks to the reconstruction task. Such an architecture is able to tackle the issue of trade-off between the output resolution and the receptive field of the model imposed by GPU memory limitations. Furthermore, we experiment with both generative and discriminative models and study their behavior during the task of anatomical reconstruction. The proposed method achieves an average surface error of 0.59mm for our synthetic test dataset with as low as 0.48mm for unilateral defects of parietal and temporal bone, matching state-of-the-art performance while being completely automatic. We also show that the model trained on our synthetic dataset is able to reconstruct real patient defects.

• Klíčová slova
• 3D shape completion, Anatomical reconstruction, Convolutional neural networks, Cranial implant design, Generative adversarial networks,
• MeSH
• lebka diagnostické zobrazování   MeSH
• lidé MeSH
• neuronové sítě * MeSH
• počítačové zpracování obrazu * MeSH
• protézy a implantáty MeSH
• Check Tag
• lidé MeSH
• Publikační typ
• časopisecké články MeSH
• práce podpořená grantem MeSH

Reinforcement learning algorithms are increasingly utilized across diverse domains within power systems. One notable challenge in training and deploying these algorithms is the acquisition of large, realistic datasets. It is imperative that these algorithms are trained on extensive, realistic datasets over numerous iterations to ensure optimal performance in real-world scenarios. In pursuit of this goal, we curated a comprehensive dataset capturing electric vehicle (EV) charging details over a span of 29,600 days within a designated parking facility. This dataset encompasses necessary information such as connection times, charging durations, and energy consumption of individual EVs. The methodology involved employing conditional tabular generative adversarial networks (CTGAN) to craft a pool of synthetic dataset from a smaller initial dataset collected from an EV charging facility located on the Caltech campus. Subsequently, multiple post-processing techniques were implemented to extract data from this pool, ensuring compliance with the charging station's capacity constraint while maintaining a realistic daily EV demand profile derived from historical data. Using kernel density estimation (KDE), the distributional characteristics of the historical data, especially concerning the timing of EV connections, were faithfully replicated. The developed dataset is specifically useful in training offline reinforcement learning algorithms.

• Klíčová slova
• ACN-data, Adaptive charging networks, Charging station, Generative adversarial networks, Kernel density estimation, conditional tabular GAN,
• Publikační typ
• časopisecké články MeSH

The cost of generating electricity in developing countries surpasses the government's ability to sustain it, necessitating the involvement of the private sector in this service provision through public-private partnerships (PPPs) contracts. In Syria, the electricity system has been highly susceptible to damage as a result of the ongoing crisis, leading to frequent and prolonged blackouts. This research focuses on addressing the need for a comprehensive system that aids decision-making for PPPs contracts in the country. By employing a combination of studies, reports, and interviews with domain experts, significant general and exclusive factors that guide decision-makers in PPPs contracts are identified and organized into questionnaires. These questionnaires are then filled out by professionals engaged in PPPs contracts. The collected data is analyzed and validated using SPSS software. However, due to insufficient data collected, generative adversarial neural networks (GAN) are utilized to enhance the research data. Additionally, Expert Choice and the analytic hierarchy process are employed to calculate weights for each factor. Remarkably, the calculated weights for both general and exclusive factors align with real-life strategies. General factors primarily address the financial and commercial considerations associated with PPPs, while exclusive factors primarily focus on the operational aspects of the electrical power system. These factors are arranged in descending order of effectiveness, enabling stakeholders to determine whether the private sector should be engaged in the project or if it should remain within the public sector's purview. The proposed system has demonstrated its reliability and can serve as a promising starting point for PPPs contracts.

• Klíčová slova
• Effective criteria, Electrical system, Generative adversarial neural networks, Private-public partnership, Sustainable development goals, Sustainable energy,
• Publikační typ
• časopisecké články MeSH

Deepfake (DF) is a kind of forged image or video that is developed to spread misinformation and facilitate vulnerabilities to privacy hacking and truth masking with advanced technologies, including deep learning and artificial intelligence with trained algorithms. This kind of multimedia manipulation, such as changing facial expressions or speech, can be used for a variety of purposes to spread misinformation or exploitation. This kind of multimedia manipulation, such as changing facial expressions or speech, can be used for a variety of purposes to spread misinformation or exploitation. With the recent advancement of generative adversarial networks (GANs) in deep learning models, DF has become an essential part of social media. To detect forged video and images, numerous methods have been developed, and those methods are focused on a particular domain and obsolete in the case of new attacks/threats. Hence, a novel method needs to be developed to tackle new attacks. The method introduced in this article can detect various types of spoofs of images and videos that are computationally generated using deep learning models, such as variants of long short-term memory and convolutional neural networks. The first phase of this proposed work extracts the feature frames from the forged video/image using a sparse autoencoder with a graph long short-term memory (SAE-GLSTM) method at training time. The first phase of this proposed work extracts the feature frames from the forged video/image using a sparse autoencoder with a graph long short-term memory (SAE-GLSTM) method at training time. The proposed DF detection model is tested using the FFHQ database, 100K-Faces, Celeb-DF (V2) and WildDeepfake. The evaluated results show the effectiveness of the proposed method.

• Klíčová slova
• Capsule convolution neural network, Deep learning, DeepFake, Generative adversarial networks, Graph LSTM, Long short term memory (LSTM),
• Publikační typ
• časopisecké články MeSH

We introduce a new approach towards generative quantum machine learning significantly reducing the number of hyperparameters and report on a proof-of-principle experiment demonstrating our approach. Our proposal depends on collaboration between the generators and discriminator, thus, we call it quantum synergic generative learning. We present numerical evidence that the synergic approach, in some cases, compares favorably to recently proposed quantum generative adversarial learning. In addition to the results obtained with quantum simulators, we also present experimental results obtained with an actual programmable quantum computer. We investigate how a quantum computer implementing generative learning algorithm could learn the concept of a maximally-entangled state. After completing the learning process, the network is able both to recognize and to generate an entangled state. Our approach can be treated as one possible preliminary step to understanding how the concept of quantum entanglement can be learned and demonstrated by a quantum computer.

• Publikační typ
• časopisecké články MeSH

• Klíčová slova
• cell image synthesis, deep learning, generative adversarial networks, style transfer,
• MeSH
• deep learning * MeSH
• neuronové sítě MeSH
• počítačové zpracování obrazu * MeSH
• Publikační typ
• časopisecké články MeSH
• komentáře MeSH

OBJECTIVES: Class imbalance in datasets is one of the challenges of machine learning (ML) in medical image analysis. We employed synthetic data to overcome class imbalance when segmenting bitewing radiographs as an exemplary task for using ML. METHODS: After segmenting bitewings into classes, i.e. dental structures, restorations, and background, the pixel-level representation of implants in the training set (1543 bitewings) and testing set (177 bitewings) was 0.03 % and 0.07 %, respectively. A diffusion model and a generative adversarial network (pix2pix) were used to generate a dataset synthetically enriched in implants. A U-Net segmentation model was trained on (1) the original dataset, (2) the synthetic dataset, (3) on the synthetic dataset and fine-tuned on the original dataset, or (4) on a dataset which was naïvely oversampled with images containing implants. RESULTS: U-Net trained on the original dataset was unable to segment implants in the testing set. Model performance was significantly improved by naïve over-sampling, achieving the highest precision. The model trained only on synthetic data performed worse than naïve over-sampling in all metrics, but with fine-tuning on original data, it resulted in the highest Dice score, recall, F1 score and ROC AUC, respectively. The performance on other classes than implants was similar for all strategies except training only on synthetic data, which tended to perform worse. CONCLUSIONS: The use of synthetic data alone may deteriorate the performance of segmentation models. However, fine-tuning on original data could significantly enhance model performance, especially for heavily underrepresented classes. CLINICAL SIGNIFICANCE: This study explored the use of synthetic data to enhance segmentation of bitewing radiographs, focusing on underrepresented classes like implants. Pre-training on synthetic data followed by fine-tuning on original data yielded the best results, highlighting the potential of synthetic data to advance AI-driven dental imaging and ultimately support clinical decision-making.

• Klíčová slova
• Artificial intelligence, Dataset imbalance, Dentistry, Diffusion model, Generative adversarial network, Synthetic medical data,
• MeSH
• lidé MeSH
• počítačové zpracování obrazu * metody   MeSH
• strojové učení * MeSH
• zubní implantáty MeSH
• Check Tag
• lidé MeSH
• Publikační typ
• časopisecké články MeSH
• Názvy látek
• zubní implantáty MeSH