Search results for: transformer neural networks

Authors: Deepika Bhalla, Raj Kumar Bansal, Hari Om Gupta

Abstract:

Dissolved Gas Analysis (DGA) has been widely used for fault diagnosis in a transformer. Artificial neural networks (ANN) have high accuracy but are regarded as black boxes that are difficult to interpret. For many problems it is desired to extract knowledge from trained neural networks (NN) so that the user can gain a better understanding of the solution arrived by the NN. This paper applies a pedagogical approach for rule extraction from function approximating neural networks (REFANN) with application to incipient fault diagnosis using the concentrations of the dissolved gases within the transformer oil, as the input to the NN. The input space is split into subregions and for each subregion there is a linear equation that is used to predict the type of fault developing within a transformer. The experiments on real data indicate that the approach used can extract simple and useful rules and give fault predictions that match the actual fault and are at times also better than those predicted by the IEC method.

Keywords: artificial neural networks, dissolved gas analysis, rules extraction, transformer

Procedia PDF Downloads 536

Authors: Cheng-yu Hsieh, Bo Zhang, Ahmed Hambaba

Abstract:

Stock market prediction has long been an area of interest for both expert analysts and investors, driven by its complexity and the noisy, volatile conditions it operates under. This research examines the efficacy of combining the Patch Time Series Transformer (PatchTST) with wavelet transforms, specifically focusing on Haar and Daubechies wavelets, in forecasting the adjusted closing price of the S&P 500 index for the following day. By comparing the performance of the augmented PatchTST models with traditional predictive models such as Recurrent Neural Networks (RNNs), Convolutional Neural Networks (CNNs), Long Short-Term Memory (LSTM) networks, and Transformers, this study highlights significant enhancements in prediction accuracy. The integration of the Daubechies wavelet with PatchTST notably excels, surpassing other configurations and conventional models in terms of Mean Absolute Error (MAE) and Mean Squared Error (MSE). The success of the PatchTST model paired with Daubechies wavelet is attributed to its superior capability in extracting detailed signal information and eliminating irrelevant noise, thus proving to be an effective approach for financial time series forecasting.

Keywords: deep learning, financial forecasting, stock market prediction, patch time series transformer, wavelet transform

Procedia PDF Downloads 50

Authors: H. Y. Jung, Jing Wang, J. H. Park, Hao Shen

Abstract:

This brief addresses the passivity problem for neural networks with time-varying delays. The aim is focus on establishing the passivity condition of the considered neural networks.

Keywords: neural networks, passivity analysis, time-varying delays, linear matrix inequality

Procedia PDF Downloads 570

Authors: Diego De Almeida Pereira, Diana Borchenko

Abstract:

Artificial neural networks are used for many applications as they are able to learn complex nonlinear relationships between input and output data. As the number of neurons and layers in a neural network increases, it is possible to represent more complex behaviors. The present study proposes that artificial neural networks are a valuable tool for architecture and engineering professionals concerned with understanding how buildings influence human and social well-being based on theories of environmental psychology.

Keywords: environmental psychology, architecture, neural networks, human and social well-being

Procedia PDF Downloads 496

Authors: Shweta Singh, Sudaman Katti

Abstract:

The most well-known sequence models make use of complex recurrent neural networks in an encoder-decoder configuration. The model used in this research makes use of a transformer, which is based purely on a self-attention mechanism, without relying on recurrence at all. More specifically, encoders and decoders which make use of self-attention and operate based on a memory, are used. In this research work, results for various 3D visual and non-visual reinforcement learning tasks designed in Unity software were obtained. Convolutional neural networks, more specifically, nature CNN architecture, are used for input processing in visual tasks, and comparison with standard long short-term memory (LSTM) architecture is performed for both visual tasks based on CNNs and non-visual tasks based on coordinate inputs. This research work combines the transformer architecture with the proximal policy optimization technique used popularly in reinforcement learning for stability and better policy updates while training, especially for continuous action spaces, which are used in this research work. Certain tasks in this paper are long horizon tasks that carry on for a longer duration and require extensive use of memory-based functionalities like storage of experiences and choosing appropriate actions based on recall. The transformer, which makes use of memory and self-attention mechanism in an encoder-decoder configuration proved to have better performance when compared to LSTM in terms of exploration and rewards achieved. Such memory based architectures can be used extensively in the field of cognitive robotics and reinforcement learning.

Keywords: convolutional neural networks, reinforcement learning, self-attention, transformers, unity

Procedia PDF Downloads 136

Authors: Sanaa Rashed Abdallah, Yasser F. Hassan

Abstract:

The paper will introduce an approach where a rough sets, gene expression programming and rough neural networks are used cooperatively for learning and classification support. The Objective of gene expression programming rough neural networks (GEP-RNN) approach is to obtain new classified data with minimum error in training and testing process. Starting point of gene expression programming rough neural networks (GEP-RNN) approach is an information system and the output from this approach is a structure of rough neural networks which is including the weights and thresholds with minimum classification error.

Keywords: rough sets, gene expression programming, rough neural networks, classification

Procedia PDF Downloads 383

Authors: Kaoutar Abbahaddou, Mohammed Salah Chiadmi

Abstract:

The need to find a relevant way to predict the next-day price of a stock index is a real concern for many financial stakeholders and researchers. We have known across years the proliferation of several methods. Nevertheless, among all these methods, the most controversial one is a machine learning algorithm that claims to be reliable, namely neural networks. Thus, the purpose of this article is to study the prediction power of neural networks in the particular case of Islamic finance as it is an under-looked area. In this article, we will first briefly present a review of the literature regarding neural networks and Islamic finance. Next, we present the architecture and principles of artificial neural networks most commonly used in finance. Then, we will show its empirical application on two Islamic stock indexes. The accuracy rate would be used to measure the performance of the algorithm in predicting the right price the next day. As a result, we can conclude that artificial neural networks are a reliable method to predict the next-day price for Islamic indices as it is claimed for conventional ones.

Keywords: Islamic finance, stock price prediction, artificial neural networks, machine learning

Procedia PDF Downloads 237

Authors: Pranav Gunhal., Krish Jhurani

Abstract:

This study tackles the significant computational challenge of predicting excited state dynamics in organic photovoltaic (OPV) materials—a pivotal factor in the performance of solar energy solutions. Time-dependent density functional theory (TDDFT), though effective, is computationally prohibitive for larger and more complex molecules. As a solution, the research explores the application of transformer neural networks, a type of artificial intelligence (AI) model known for its superior performance in natural language processing, to predict excited state dynamics in OPV materials. The methodology involves a two-fold process. First, the transformer model is trained on an extensive dataset comprising over 10,000 TDDFT calculations of excited state dynamics from a diverse set of OPV materials. Each training example includes a molecular structure and the corresponding TDDFT-calculated excited state lifetimes and key electronic transitions. Second, the trained model is tested on a separate set of molecules, and its predictions are rigorously compared to independent TDDFT calculations. The results indicate a remarkable degree of predictive accuracy. Specifically, for a test set of 1,000 OPV materials, the transformer model predicted excited state lifetimes with a mean absolute error of 0.15 picoseconds, a negligible deviation from TDDFT-calculated values. The model also correctly identified key electronic transitions contributing to the excited state dynamics in 92% of the test cases, signifying a substantial concordance with the results obtained via conventional quantum chemistry calculations. The practical integration of the transformer model with existing quantum chemistry software was also realized, demonstrating its potential as a powerful tool in the arsenal of materials scientists and chemists. The implementation of this AI model is estimated to reduce the computational cost of predicting excited state dynamics by two orders of magnitude compared to conventional TDDFT calculations. The successful utilization of transformer neural networks to accurately predict excited state dynamics provides an efficient computational pathway for the accelerated discovery and design of new OPV materials, potentially catalyzing advancements in the realm of sustainable energy solutions.

Keywords: transformer neural networks, organic photovoltaic materials, excited state dynamics, time-dependent density functional theory, predictive modeling

Procedia PDF Downloads 118

Authors: Mohammad Hossein Mohammadi Sanjani, Ashknaz Oraee, Arian Amirnia, Atena Taheri, Mohammadreza Arabi, Mahmud Fotuhi-Firuzabad

Abstract:

Ferroresonance effects cause overvoltage in medium voltage transformers and isolators used in electrical networks. Ferroresonance effects are nonlinear and occur between the network capacitor and the nonlinear inductance of the voltage transformer during saturation. This phenomenon is unwanted for transformers since it causes overheating, introduction of high dynamic forces in primary coils, and rise of voltage in primary coils for the voltage transformer. Furthermore, it results in electrical and thermal failure of the transformer. Expansion of distribution lines, design of the transformer in smaller sizes, and the increase of harmonics in distribution networks result in an increase of ferroresonance. There is limited literature available to improve the effects of ferroresonance; therefore, optimizing its effects for voltage transformers is of great importance. In this study, comprehensive modeling of a medium voltage block-type voltage transformer is performed. In addition, a recent model is proposed to improve the performance of voltage transformers during the occurrence of ferroresonance using damping oscillations. Also, transformer design optimization is presented in this study to show further improvements in the performance of the voltage transformer. The recently proposed model is experimentally tested and verified on a medium voltage transformer in the laboratory, and simulation results show a large reduction of the effects of ferroresonance.

Keywords: optimization, voltage transformer, ferroresonance, modeling, damper

Procedia PDF Downloads 101

Authors: N. K. Mohd Affendi, T. A. R. Tuan Abdullah, S. A. Syed Mustaffa

Abstract:

In power industry transformer is an important component and most of us familiar by the functioning principle of a transformer electrically. There are many losses occur during the operation of a transformer that causes heat generation. This heat, if not dissipated properly will reduce the lifetime and effectiveness of the transformer. Transformer cooling helps in maintaining the temperature rise of various paths. This paper proposed to minimize the ambient temperature of the transformer room in order to lower down the temperature of the transformer. A simulation has been made using finite element methods programs called FEMM (Finite Elements Method Magnetics) to create a virtual model based on actual measurement of a transformer. The generalization of the two-dimensional (2D) FEMM results proves that by minimizing the ambient temperature, the heat of the transformer is decreased. The modeling process and of the transformer heat flow has been presented.

Keywords: heat generation, temperature rise, ambient temperature, FEMM

Procedia PDF Downloads 400

Authors: Cheikh Bamba Dione, Alla Lo, Elhadji Mamadou Nguer, Siley O. Ba

Abstract:

In this paper, we propose two neural machine translation (NMT) systems (French-to-Wolof and Wolof-to-French) based on sequence-to-sequence with attention and transformer architectures. We trained our models on a parallel French-Wolof corpus of about 83k sentence pairs. Because of the low-resource setting, we experimented with advanced methods for handling data sparsity, including subword segmentation, back translation, and the copied corpus method. We evaluate the models using the BLEU score and find that transformer outperforms the classic seq2seq model in all settings, in addition to being less sensitive to noise. In general, the best scores are achieved when training the models on word-level-based units. For subword-level models, using back translation proves to be slightly beneficial in low-resource (WO) to high-resource (FR) language translation for the transformer (but not for the seq2seq) models. A slight improvement can also be observed when injecting copied monolingual text in the target language. Moreover, combining the copied method data with back translation leads to a substantial improvement of the translation quality.

Keywords: backtranslation, low-resource language, neural machine translation, sequence-to-sequence, transformer, Wolof

Procedia PDF Downloads 147

Authors: Najmeh Mohsenifar, Narjes Mohsenifar, Abbas Kargar

Abstract:

In this paper, has been presented a stable method for predicting the ECG signals through the RBF neural networks, by the PSO algorithm. In spite of quasi-periodic ECG signal from a healthy person, there are distortions in electro cardiographic data for a patient. Therefore, there is no precise mathematical model for prediction. Here, we have exploited neural networks that are capable of complicated nonlinear mapping. Although the architecture and spread of RBF networks are usually selected through trial and error, the PSO algorithm has been used for choosing the best neural network. In this way, 2 second of a recorded ECG signal is employed to predict duration of 20 second in advance. Our simulations show that PSO algorithm can find the RBF neural network with minimum MSE and the accuracy of the predicted ECG signal is 97 %.

Keywords: electrocardiogram, RBF artificial neural network, PSO algorithm, predict, accuracy

Procedia PDF Downloads 626

Authors: K. A. Laptinskiy, S. A. Burikov, A. M. Vervald, S. A. Dolenko, T. A. Dolenko

Abstract:

The article presents the results of the application of artificial neural networks to separate the fluorescent contribution of nanodiamonds used as biomarkers, adsorbents and carriers of drugs in biomedicine, from a fluorescent background of own biological fluorophores. The principal possibility of solving this problem is shown. Use of neural network architecture let to detect fluorescence of nanodiamonds against the background autofluorescence of egg white with high accuracy - better than 3 ug/ml.

Keywords: artificial neural networks, fluorescence, data aggregation, biomarkers

Procedia PDF Downloads 710

Authors: José Luis Carrillo-Medina, Roberto Latorre

Abstract:

Experimental evidence has revealed that different living neural systems can sign their output signals with some specific neural signature. Although experimental and modeling results suggest that neural signatures can have an important role in the activity of neural networks in order to identify the source of the information or to contextualize a message, the functional meaning of these neural fingerprints is still unclear. The existence of cellular mechanisms to identify the origin of individual neural signals can be a powerful information processing strategy for the nervous system. We have recently built different models to study the ability of a neural network to process information based on the emission and recognition of specific neural fingerprints. In this paper we further analyze the features that can influence on the information processing ability of this kind of networks. In particular, we focus on the role that the duration of a refractory period in each neuron after emitting a signed message can play in the network collective dynamics.

Keywords: neural signature, neural fingerprint, processing based on signal identification, self-organizing neural network

Procedia PDF Downloads 492

Authors: B. Afsharipoor, E. Nazemi

Abstract:

Artificial neural networks (ANNs) are powerful tool for prediction which can be trained based on a set of examples and thus, it would be useful for nonlinear image processing. The present paper reviews several paper regarding applications of ANN in image processing to shed the light on advantage and disadvantage of ANNs in this field. Different steps in the image processing chain including pre-processing, enhancement, segmentation, object recognition, image understanding and optimization by using ANN are summarized. Furthermore, results on using multi artificial neural networks are presented.

Keywords: neural networks, image processing, segmentation, object recognition, image understanding, optimization, MANN

Procedia PDF Downloads 406

Authors: Naci Büyükkaracığan

Abstract:

Artificial neural networks (ANN) is an electrical model based on the human brain nervous system and working principle. Artificial neural networks have been the subject of an active field of research that has matured greatly over the past 55 years. ANN now is used in many fields. But, it has been viewed that artificial neural networks give better results in particular optimization and control systems. There are requirements of optimization and control system in many of the area forming the subject of civil engineering applications. In this study, the first artificial intelligence systems are widely used in the solution of civil engineering systems were examined with the basic principles and technical aspects. Finally, the literature reviews for applications in the field of civil engineering were conducted and also artificial intelligence techniques were informed about the study and its results.

Keywords: artificial neural networks, civil engineering, Fuzzy logic, statistics

Procedia PDF Downloads 412

Authors: Daham Owaid Matrood, Naqaa Hussein Raheem

Abstract:

Evolutionary algorithms and Artificial neural networks (ANN) are two relatively young research areas that were subject to a steadily growing interest during the past years. This paper examines the use of Particle Swarm Optimization (PSO) to train a multi-layer feed forward neural network for demand forecasting. We use in this paper weekly demand data for packed cement and towels, which have been outfitted by the Northern General Company for Cement and General Company of prepared clothes respectively. The results showed superiority of trained neural networks using particle swarm optimization on neural networks trained using error back propagation because their ability to escape from local optima.

Keywords: artificial neural network, demand forecasting, particle swarm optimization, weight optimization

Procedia PDF Downloads 452

Authors: S. Adjiri-Bailiche, S. M. Boudia, H. Daaou, S. Hadouche, A. Benzaoui

Abstract:

In this work the study of changes in the wind speed depending on the altitude is calculated and described by the model of the neural networks, the use of measured data, the speed and direction of wind, temperature and the humidity at 10 m are used as input data and as data targets at 50m above sea level. Comparing predict wind speeds and extrapolated at 50 m above sea level is performed. The results show that the prediction by the method of artificial neural networks is very accurate.

Keywords: MATLAB, neural network, power low, vertical extrapolation, wind energy, wind speed

Procedia PDF Downloads 692

Authors: A. A. Behroozpoor, M. M. Mazarei

Abstract:

In this paper, a fuzzy recurrent neural network is proposed for solving the classical quadratic control problem subject to linear equality and bound constraints. The convergence of the state variables of the proposed neural network to achieve solution optimality is guaranteed.

Keywords: REFERENCES [1] Xia, Y, A new neural network for solving linear and quadratic programming problems. IEEE Transactions on Neural Networks, 7(6), 1996, pp.1544–1548. [2] Xia, Y., & Wang, J, A recurrent neural network for solving nonlinear convex programs subject to linear constraints. IEEE Transactions on Neural Networks, 16(2), 2005, pp. 379–386. [3] Xia, Y., H, Leung, & J, Wang, A projection neural network and its application to constrained optimization problems. IEEE Transactions Circuits and Systems-I, 49(4), 2002, pp.447–458.B. [4] Q. Liu, Z. Guo, J. Wang, A one-layer recurrent neural network for constrained seudoconvex optimization and its application for dynamic portfolio optimization. Neural Networks, 26, 2012, pp. 99-109.

Procedia PDF Downloads 644

Authors: Kitti Leangkrua

Abstract:

This paper presents a risk-based maintenance strategy of a power transformer in order to optimize operating and maintenance costs. The methodology involves the study and preparation of a database for the collection the technical data and test data of a power transformer. An evaluation of the overall condition of each transformer is performed by a program developed as a result of the measured results; in addition, the calculation of the main equipment separation to the overall condition of the transformer (% HI) and the criteria for evaluating the importance (% ImI) of each location where the transformer is installed. The condition assessment is performed by analysis test data such as electrical test, insulating oil test and visual inspection. The condition of the power transformer will be classified from very poor to very good condition. The importance is evaluated from load criticality, importance of load and failure consequence. The risk matrix is developed for evaluating the risk of each power transformer. The high risk power transformer will be focused firstly. The computerized program is developed for practical use, and the maintenance strategy of a power transformer can be effectively managed.

Keywords: asset management, risk-based maintenance, power transformer, health index

Procedia PDF Downloads 306

Authors: Sorin Valcan, Mihail Gaianu

Abstract:

Labeling is a very costly and time consuming process which aims to generate datasets for training neural networks in several functionalities and projects. For driver monitoring system projects, the need for labeled images has a significant impact on the budget and distribution of effort. This paper presents the modifications done to an algorithm used for the generation of ground truth data for 2D eyes location on infrared images with drivers in order to improve the quality of the data and performance of the trained neural networks. The algorithm restrictions become tougher, which makes it more accurate but also less constant. The resulting dataset becomes smaller and shall not be altered by any kind of manual label adjustment before being used in the neural networks training process. These changes resulted in a much better performance of the trained neural networks.

Keywords: labeling automation, infrared camera, driver monitoring, eye detection, convolutional neural networks

Procedia PDF Downloads 117

Authors: Jessica Lopez Espejel, Mahaman Sanoussi Yahaya Alassan, Walid Dahhane, El Hassane Ettifouri

Abstract:

Pretrained transformer-based models have shown high performance in natural language generation tasks. However, a new wave of interest has surged: automatic programming language code generation. This task consists of translating natural language instructions to a source code. Despite the fact that well-known pre-trained models on language generation have achieved good performance in learning programming languages, effort is still needed in automatic code generation. In this paper, we introduce JaCoText, a model based on Transformer neural network. It aims to generate java source code from natural language text. JaCoText leverages the advantages of both natural language and code generation models. More specifically, we study some findings from state of the art and use them to (1) initialize our model from powerful pre-trained models, (2) explore additional pretraining on our java dataset, (3) lead experiments combining the unimodal and bimodal data in training, and (4) scale the input and output length during the fine-tuning of the model. Conducted experiments on CONCODE dataset show that JaCoText achieves new state-of-the-art results.

Keywords: java code generation, natural language processing, sequence-to-sequence models, transformer neural networks

Procedia PDF Downloads 284

Authors: Ali Isapour, Ramin Nateghi

Abstract:

— Markov parameters are unique parameters of the system and remain unchanged under similarity transformations. Markov parameters from a power series that is convergent only if the system matrix’s eigenvalues are inside the unity circle. Therefore, Markov parameters of a stable discrete-time system are convergent. In this study, we aim to realize the system based on Markov parameters by using Artificial Neural Networks (ANN), and this end, we use Flexible Neural Networks. Realization means determining the elements of matrices A, B, C, and D.

Keywords: Markov parameters, realization, activation function, flexible neural network

Procedia PDF Downloads 194

Authors: Arbnor Pajaziti, Hasan Cana

Abstract:

In this paper, the structural genetic algorithm is used to optimize the neural network to control the joint movements of robotic arm. The robotic arm has also been modeled in 3D and simulated in real-time in MATLAB. It is found that Neural Networks provide a simple and effective way to control the robot tasks. Computer simulation examples are given to illustrate the significance of this method. By combining Genetic Algorithm optimization method and Neural Networks for the given robotic arm with 5 D.O.F. the obtained the results shown that the base joint movements overshooting time without controller was about 0.5 seconds, while with Neural Network controller (optimized with Genetic Algorithm) was about 0.2 seconds, and the population size of 150 gave best results.

Keywords: robotic arm, neural network, genetic algorithm, optimization

Procedia PDF Downloads 523

Authors: M. Brandt, A. Peniak, J. Makarovič, P. Rafajdus

Abstract:

This paper deals with a novel approach of power transformers diagnostics. This approach identifies the exact location and the range of a fault in the transformer and helps to reduce operation costs related to handling of the faulty transformer, its disassembly and repair. The advantage of the approach is a possibility to simulate healthy transformer and also all faults, which can occur in transformer during its operation without its disassembling, which is very expensive in practice. The approach is based on creating frequency dependent impedance of the transformer by sweep frequency response analysis measurements and by 3D FE parametrical modeling of the fault in the transformer. The parameters of the 3D FE model are the position and the range of the axial short circuit. Then, by comparing the frequency dependent impedances of the parametrical models with the measured ones, the location and the range of the fault is identified. The approach was tested on a real transformer and showed high coincidence between the real fault and the simulated one.

Keywords: transformer, parametrical model of transformer, fault, sweep frequency response analysis, finite element method

Procedia PDF Downloads 482

Authors: Salah Ghamari

Abstract:

In this study, the ability of self organizing map artificial (SOM) neural networks in clustering the wheat seeds varieties according to morphological properties of them was considered. The SOM is one type of unsupervised competitive learning. Experimentally, five morphological features of 300 seeds (including three varieties: gaskozhen, Md and sardari) were obtained using image processing technique. The results show that the artificial neural network has a good performance (90.33% accuracy) in classification of the wheat varieties despite of high similarity in them. The highest classification accuracy (100%) was achieved for sardari.

Keywords: artificial neural networks, clustering, self organizing map, wheat variety

Procedia PDF Downloads 656

Authors: S. Mousavian, D. Ashouri, F. Mousavian, V. Nikkhah Rashidabad, N. Ghazinia

Abstract:

PH, temperature, and time of extraction of each stage, agitation speed, and delay time between stages effect on efficiency of zinc extraction from concentrate. In this research, efficiency of zinc extraction was predicted as a function of mentioned variable by artificial neural networks (ANN). ANN with different layer was employed and the result show that the networks with 8 neurons in hidden layer has good agreement with experimental data.

Keywords: zinc extraction, efficiency, neural networks, operating condition

Procedia PDF Downloads 545

Authors: Samuel Nii Tackie, Oyebade K. Oyedotun, Ebenezer O. Olaniyi, Adnan Khashman

Abstract:

Artificial neural networks have been used in different fields of artificial intelligence, and more specifically in machine learning. Although, other machine learning options are feasible in most situations, but the ease with which neural networks lend themselves to different problems which include pattern recognition, image compression, classification, computer vision, regression etc. has earned it a remarkable place in the machine learning field. This research exploits neural networks as a data mining tool in predicting the number of times a student repeats a course, considering some attributes relating to the course itself, the teacher, and the particular student. Neural networks were used in this work to map the relationship between some attributes related to students’ course assessment and the number of times a student will possibly repeat a course before he passes. It is the hope that the possibility to predict students’ performance from such complex relationships can help facilitate the fine-tuning of academic systems and policies implemented in learning environments. To validate the power of neural networks in data mining, Turkish students’ performance database has been used; feedforward and radial basis function networks were trained for this task; and the performances obtained from these networks evaluated in consideration of achieved recognition rates and training time.

Keywords: artificial neural network, data mining, classification, students’ evaluation

Procedia PDF Downloads 613

Authors: Lianzhong Zhang, Chao Huang

Abstract:

Sea-land segmentation is a basic step in many tasks such as sea surface monitoring and ship detection. The existing sea-land segmentation algorithms have poor segmentation accuracy, and the parameter adjustments are cumbersome and difficult to meet actual needs. Also, the current sea-land segmentation adopts traditional deep learning models that use Convolutional Neural Networks (CNN). At present, the transformer architecture has achieved great success in the field of natural images, but its application in the field of radar images is less studied. Therefore, this paper proposes a sea-land segmentation method based on the transformer architecture to strengthen edge supervision. It uses a self-attention mechanism with a gating strategy to better learn relative position bias. Meanwhile, an additional edge supervision branch is introduced. The decoder stage allows the feature information of the two branches to interact, thereby improving the edge precision of the sea-land segmentation. Based on the Gaofen-3 satellite image dataset, the experimental results show that the method proposed in this paper can effectively improve the accuracy of sea-land segmentation, especially the accuracy of sea-land edges. The mean IoU (Intersection over Union), edge precision, overall precision, and F1 scores respectively reach 96.36%, 84.54%, 99.74%, and 98.05%, which are superior to those of the mainstream segmentation models and have high practical application values.

Keywords: SAR, sea-land segmentation, deep learning, transformer

Procedia PDF Downloads 181

Authors: Tianle Yang

Abstract:

As a common mental disorder, depression is a leading cause of various diseases worldwide. Early detection and treatment of depression can dramatically promote remission and prevent relapse. However, conventional ways of depression diagnosis require considerable human effort and cause economic burden, while still being prone to misdiagnosis. On the other hand, recent studies report that physical characteristics are major contributors to the diagnosis of depression, which inspires us to mine the internal relationship by neural networks instead of relying on clinical experiences. In this paper, neural networks are constructed to predict depression from physical characteristics. Two initialization methods are examined - Xaiver and Kaiming initialization. Experimental results show that a 3-layers neural network with Kaiming initialization achieves 83% accuracy.

Keywords: depression, neural network, Xavier initialization, Kaiming initialization

Procedia PDF Downloads 128