Search results for: transformer neural networks

Authors: Mohamed Aymen Slim, Afef Abdelkrim, Mohamed Benrejeb

Abstract:

The handwriting is a physical demonstration of a complex cognitive process learnt by man since his childhood. People with disabilities or suffering from various neurological diseases are facing so many difficulties resulting from problems located at the muscle stimuli (EMG) or signals from the brain (EEG) and which arise at the stage of writing. The handwriting velocity of the same writer or different writers varies according to different criteria: age, attitude, mood, writing surface, etc. Therefore, it is interesting to reconstruct an experimental basis records taking, as primary reference, the writing speed for different writers which would allow studying the global system during handwriting process. This paper deals with a new approach of the handwriting system modeling based on the velocity criterion through the concepts of artificial neural networks, precisely the Radial Basis Functions (RBF) neural networks. The obtained simulation results show a satisfactory agreement between responses of the developed neural model and the experimental data for various letters and forms then the efficiency of the proposed approaches.

Keywords: Electro Myo Graphic (EMG) signals, experimental approach, handwriting process, Radial Basis Functions (RBF) neural networks, velocity modeling

Procedia PDF Downloads 440

Authors: Tharini N. de Silva, Xiao Zhibo, Zhao Rui, Mao Kezhi

Abstract:

Causal relation identification is a crucial task in information extraction and knowledge discovery. In this work, we present two approaches to causal relation identification. The first is a classification model trained on a set of knowledge-based features. The second is a deep learning based approach training a model using convolutional neural networks to classify causal relations. We experiment with several different convolutional neural networks (CNN) models based on previous work on relation extraction as well as our own research. Our models are able to identify both explicit and implicit causal relations as well as the direction of the causal relation. The results of our experiments show a higher accuracy than previously achieved for causal relation identification tasks.

Keywords: causal realtion extraction, relation extracton, convolutional neural network, text representation

Procedia PDF Downloads 732

Authors: Konstantinos Perifanos, Eirini Florou, Dionysis Goutsos

Abstract:

This paper presents and benchmarks a number of end-to-end Deep Learning based models for metaphor detection in Greek. We combine Convolutional Neural Networks and Recurrent Neural Networks with representation learning to bear on the metaphor detection problem for the Greek language. The models presented achieve exceptional accuracy scores, significantly improving the previous state-of-the-art results, which had already achieved accuracy 0.82. Furthermore, no special preprocessing, feature engineering or linguistic knowledge is used in this work. The methods presented achieve accuracy of 0.92 and F-score 0.92 with Convolutional Neural Networks (CNNs) and bidirectional Long Short Term Memory networks (LSTMs). Comparable results of 0.91 accuracy and 0.91 F-score are also achieved with bidirectional Gated Recurrent Units (GRUs) and Convolutional Recurrent Neural Nets (CRNNs). The models are trained and evaluated only on the basis of training tuples, the related sentences and their labels. The outcome is a state-of-the-art collection of metaphor detection models, trained on limited labelled resources, which can be extended to other languages and similar tasks.

Keywords: metaphor detection, deep learning, representation learning, embeddings

Procedia PDF Downloads 153

Authors: Ghofrane Rehaiem, Hamza Gharsellaoui, Samir Benahmed

Abstract:

In this study, Artificial Neural Networks (ANNs) were used for modeling the parameters that allow the real-time scheduling of embedded systems under resources constraints designed for real-time applications running. The objective of this work is to implement a neural networks based approach for real-time scheduling of embedded systems in order to handle real-time constraints in execution scenarios. In our proposed approach, many techniques have been proposed for both the planning of tasks and reducing energy consumption. In fact, a combination of Dynamic Voltage Scaling (DVS) and time feedback can be used to scale the frequency dynamically adjusting the operating voltage. Indeed, we present in this paper a hybrid contribution that handles the real-time scheduling of embedded systems, low power consumption depending on the combination of DVS and Neural Feedback Scheduling (NFS) with the energy Priority Earlier Deadline First (PEDF) algorithm. Experimental results illustrate the efficiency of our original proposed approach.

Keywords: optimization, neural networks, real-time scheduling, low-power consumption

Procedia PDF Downloads 371

Authors: Mohammad Namazi, Mohammad Sadeghzadeh Maharluie

Abstract:

Predicting earnings management is vital for the capital market participants, financial analysts and managers. The aim of this research is attempting to respond to this query: Is there a significant difference between the regression model and neural networks’ models in predicting earnings management, and which one leads to a superior prediction of it? In approaching this question, a Linear Regression (LR) model was compared with two neural networks including Multi-Layer Perceptron (MLP), and Generalized Regression Neural Network (GRNN). The population of this study includes 94 listed companies in Tehran Stock Exchange (TSE) market from 2003 to 2011. After the results of all models were acquired, ANOVA was exerted to test the hypotheses. In general, the summary of statistical results showed that the precision of GRNN did not exhibit a significant difference in comparison with MLP. In addition, the mean square error of the MLP and GRNN showed a significant difference with the multi variable LR model. These findings support the notion of nonlinear behavior of the earnings management. Therefore, it is more appropriate for capital market participants to analyze earnings management based upon neural networks techniques, and not to adopt linear regression models.

Keywords: earnings management, generalized linear regression, neural networks multi-layer perceptron, Tehran stock exchange

Procedia PDF Downloads 421

Authors: Masoud Safarishaal

Abstract:

Detecting the location of pole-to-earth faults is essential for the safe operation of the electrical system of the railroad. This paper aims to use a combination of evolutionary algorithms and neural networks to increase the accuracy of single pole-to-earth fault detection and location on the Tehran railroad power supply system. As a result, the Imperialist Competitive Algorithm (ICA) and Particle Swarm Optimization (PSO) are used to train the neural network to improve the accuracy and convergence of the learning process. Due to the system's nonlinearity, fault detection is an ideal application for the proposed method, where the 600 Hz harmonic ripple method is used in this paper for fault detection. The substations were simulated by considering various situations in feeding the circuit, the transformer, and typical Tehran metro parameters that have developed the silicon rectifier. Required data for the network learning process has been gathered from simulation results. The 600Hz component value will change with the change of the location of a single pole to the earth's fault. Therefore, 600Hz components are used as inputs of the neural network when fault location is the output of the network system. The simulation results show that the proposed methods can accurately predict the fault location.

Keywords: single pole-to-pole fault, Tehran railway, ICA, PSO, artificial neural network

Procedia PDF Downloads 123

Authors: Jie Zhao, Meng Su

Abstract:

Image recognition, as one of the most critical technologies in computer vision, works to help machine-like robotics understand a scene, that is, if deployed appropriately, will trigger the revolution in remote sensing and industry automation. With the developments of AI technologies, there are many prevailing and sophisticated neural networks as technologies developed for image recognition. However, computer vision platforms as hardware, supporting neural networks for image recognition, as crucial as the neural network technologies, need to be more congruently addressed as the research subjects. In contrast, different computer vision platforms are deterministic to leverage the performance of different neural networks for recognition. In this paper, three different computer vision platforms – Jetson Nano(with 4GB), a standalone laptop(with RTX 3000s, using CUDA), and Google Colab (web-based, using GPU) are explored and four prominent neural network architectures (including AlexNet, VGG(16/19), GoogleNet, and ResNet(18/34/50)), are investigated. In the context of pairwise usage between different computer vision platforms and distinctive neural networks, with the merits of recognition accuracy and time efficiency, the performances are evaluated. In the case study using public imageNets, our findings provide a nuanced perspective on optimizing image recognition tasks across Edge-AI platforms, offering guidance on selecting appropriate neural network structures to maximize performance under hardware constraints.

Keywords: alexNet, VGG, googleNet, resNet, Jetson nano, CUDA, COCO-NET, cifar10, imageNet large scale visual recognition challenge (ILSVRC), google colab

Procedia PDF Downloads 90

Authors: Andika Bagaskara, Andhika Rizki Pratama, Lalu Arya Repatmaja, Septhian Ditaputra Raharja

Abstract:

The power transformer is one of the critical things in system transmission. Regular testing of the power transformer is very important to maintain the reliability of the power. One of the causes of the failure of the transformer is the breakdown of insulation caused by the presence of voids in the equipment that is electrified. As a result of the voids that occur in this power transformer equipment, it can cause partial discharge. Several methods were used to determine the occurrence of damage to the power transformer equipment, such as Sweep Frequency Response Analysis (SFRA) and Tan Delta. In Inter Bus Transformer (IBT) 500/150 kV Cirata Extra High Voltage (EHV) Substation, a breakdown occurred in the T-phase tertiary bushing. From the lessons learned in this case, a complete electrical test was carried out. From the results of the complete electrical test, there was a suspicion of deterioration in the post-breakdown SFRA results. After overhaul and inspection, traces of voids were found on the tertiary bushing, which indicated a breakdown in the tertiary bushing of the IBT 500/150kV Cirata Substation transformer.

Keywords: void, bushing, SFRA, Tan Delta

Procedia PDF Downloads 141

Authors: Suk-Hyun Yu, Heeyong Kwon

Abstract:

Recently PM-10 has become a social and global issue. It is one of major air pollutants which affect human health. Therefore, it needs to be forecasted rapidly and precisely. However, PM-10 comes from various emission sources, and its level of concentration is largely dependent on meteorological and geographical factors of local and global region, so the forecasting of PM-10 concentration is very difficult. Neural network model can be used in the case. But, there are few cases of high concentration PM-10. It makes the learning of the neural network model difficult. In this paper, we suggest a simple input balancing method when the data distribution is uneven. It is based on the probability of appearance of the data. Experimental results show that the input balancing makes the neural networks’ learning easy and improves the forecasting rates.

Keywords: artificial intelligence, air quality prediction, neural networks, pattern recognition, PM-10

Procedia PDF Downloads 232

Authors: Alexander Goncharenko, Andrey Denisov, Sergey Alyamkin, Evgeny Terentev

Abstract:

The neural network quantization is highly desired procedure to perform before running neural networks on mobile devices. Quantization without fine-tuning leads to accuracy drop of the model, whereas commonly used training with quantization is done on the full set of the labeled data and therefore is both time- and resource-consuming. Real life applications require simplification and acceleration of quantization procedure that will maintain accuracy of full-precision neural network, especially for modern mobile neural network architectures like Mobilenet-v1, MobileNet-v2 and MNAS. Here we present a method to significantly optimize training with quantization procedure by introducing the trained scale factors for discretization thresholds that are separate for each filter. Using the proposed technique, we quantize the modern mobile architectures of neural networks with the set of train data of only ∼ 10% of the total ImageNet 2012 sample. Such reduction of train dataset size and small number of trainable parameters allow to fine-tune the network for several hours while maintaining the high accuracy of quantized model (accuracy drop was less than 0.5%). Ready-for-use models and code are available in the GitHub repository.

Keywords: distillation, machine learning, neural networks, quantization

Procedia PDF Downloads 325

Authors: Afroze Ibrahim Baqapuri, Ilya Trofimov

Abstract:

Sponsored search is a multi-billion dollar industry and makes up a major source of revenue for search engines (SE). Click-through-rate (CTR) estimation plays a crucial role for ads selection, and greatly affects the SE revenue, advertiser traffic and user experience. We propose a novel architecture of solving CTR prediction problem by combining artificial neural networks (ANN) with decision trees. First, we compare ANN with respect to other popular machine learning models being used for this task. Then we go on to combine ANN with MatrixNet (proprietary implementation of boosted trees) and evaluate the performance of the system as a whole. The results show that our approach provides a significant improvement over existing models.

Keywords: neural networks, sponsored search, web advertisement, click prediction, click-through rate

Procedia PDF Downloads 572

Authors: Hongda Guo, Wenxia Sima

Abstract:

Transformer oil is widely used in power systems because of its excellent insulation properties. The accurate measurement of electric field and space charge distribution in transformer oil under high voltage impulse has important theoretical and practical significance, but still remains challenging to date because of its low Kerr constant. In this study, the continuous electric field and space charge distribution over time between parallel-plate electrodes in high-voltage pulsed transformer oil based on the Kerr effect is directly measured using a linear array photoelectrical detector. Experimental results demonstrate the applicability and reliability of this method. This study provides a feasible approach to further study the space charge effects and breakdown mechanisms in transformer oil.

Keywords: electric field, Kerr, space charge, transformer oil

Procedia PDF Downloads 363

Authors: Koray U. Erbas

Abstract:

Neural networks are appealing for many applications since they are able to learn complex non-linear relationships between input and output data. As the number of neurons and layers in a neural network increase, it is possible to represent more complex relationships with automatically extracted features. Nowadays Deep Neural Networks (DNNs) are widely used in Computer Vision problems such as; classification, object detection, segmentation image editing etc. In this work, Facial Emotion Recognition task is performed by proposed Convolutional Neural Network (CNN)-based DNN architecture using FER2013 Dataset. Moreover, the effects of different hyperparameters (activation function, kernel size, initializer, batch size and network size) are investigated and ablation study results for Pooling Layer, Dropout and Batch Normalization are presented.

Keywords: convolutional neural network, deep learning, deep learning based FER, facial emotion recognition

Procedia PDF Downloads 274

Authors: Reza Dinarvand, Mahdi Sadeghian, Somaye Sadeghian

Abstract:

Prediction of the ultimate bearing capacity of piles (Qu) is one of the basic issues in geotechnical engineering. So far, several methods have been used to estimate Qu, including the recently developed artificial intelligence methods. In recent years, optimization algorithms have been used to minimize artificial network errors, such as colony algorithms, genetic algorithms, imperialist competitive algorithms, and so on. In the present research, artificial neural networks based on colonial competition algorithm (ANN-ICA) were used, and their results were compared with other methods. The results of laboratory tests of short piles in clayey soils with parameters such as pile diameter, pile buried length, eccentricity of load and undrained shear resistance of soil were used for modeling and evaluation. The results showed that ICA-based artificial neural networks predicted lateral bearing capacity of short piles with a correlation coefficient of 0.9865 for training data and 0.975 for test data. Furthermore, the results of the model indicated the superiority of ICA-based artificial neural networks compared to back-propagation artificial neural networks as well as the Broms and Hansen methods.

Keywords: artificial neural network, clayey soil, imperialist competition algorithm, lateral bearing capacity, short pile

Procedia PDF Downloads 152

Authors: Pavan K. Rallabandi, Kailash C. Patidar

Abstract:

In this paper, we present an optimization technique or a learning algorithm using the hybrid architecture by combining the most popular sequence recognition models such as Recurrent Neural Networks (RNNs) and Hidden Markov models (HMMs). In order to improve the sequence or pattern recognition/ classification performance by applying a hybrid/neural symbolic approach, a gradient descent learning algorithm is developed using the Real Time Recurrent Learning of Recurrent Neural Network for processing the knowledge represented in trained Hidden Markov Models. The developed hybrid algorithm is implemented on automata theory as a sample test beds and the performance of the designed algorithm is demonstrated and evaluated on learning the deterministic finite state automata.

Keywords: hybrid systems, hidden markov models, recurrent neural networks, deterministic finite state automata

Procedia PDF Downloads 388

Authors: Yog Raj Sood, Rajnish Shrivastava, Anchal Wadhwa

Abstract:

Power transformer is one of the electrical equipment that has a central and critical role in the power system. In order to avoid power transformer failure, information system that provides the transformer condition is needed. This paper presents an information system to know the exact situations prevailing within the transformer by declaring its health index. Health index of a transformer is decided by considering several diagnostic tools. The current work deals with UV-Vis, IFT, FP, BDV and Water Content. UV/VIS results have been pre-accessed using separate FL controller for concluding with the Furan contents. It is broadly accepted that the life of a power transformer is the life of the oil/ paper insulating system. The method relies on the use of furan analysis (insulation paper), and other oil analysis results as a means to declare health index. Fuzzy logic system is used to develop the information system. The testing is done on 5 samples of oil of transformers of rating 132/66 KV to obtain the results and results are analyzed using fuzzy logic model.

Keywords: interfacial tension analyzer (ift), flash point (fp), furfuraldehyde (fal), health index

Procedia PDF Downloads 634

Authors: S. Neelima, P. S. Subramanyam

Abstract:

The major tool for distribution planning is load forecasting, which is the anticipation of the load in advance. Artificial neural networks have found wide applications in load forecasting to obtain an efficient strategy for planning and management. In this paper, the application of neural networks to study the design of short term load forecasting (STLF) Systems was explored. Our work presents a pragmatic methodology for short term load forecasting (STLF) using proposed two-stage model of wavelet transform (WT) and artificial neural network (ANN). It is a two-stage prediction system which involves wavelet decomposition of input data at the first stage and the decomposed data with another input is trained using a separate neural network to forecast the load. The forecasted load is obtained by reconstruction of the decomposed data. The hybrid model has been trained and validated using load data from Telangana State Electricity Board.

Keywords: electrical distribution systems, wavelet transform (WT), short term load forecasting (STLF), artificial neural network (ANN)

Procedia PDF Downloads 436

Authors: Piush Verma, Y. R. Sood

Abstract:

This paper provides the information on the diagnostics techniques for condition monitoring of power transformer (PT). This paper deals with the practical importance of the transformer diagnostic in the Electrical Engineering field. The life of the transformer depends upon its insulation i.e paper and oil. The major testing techniques applies on transformer oil and paper i.e dissolved gas analysis, furfural analysis, radio interface, acoustic emission, infra-red emission, frequency response analysis, power factor, polarization spectrum, magnetizing currents, turn and winding ratio. A review has been made on the modern development of this practical technology.

Keywords: temperature, condition monitoring, diagnostics methods, paper analysis techniques, oil analysis techniques

Procedia PDF Downloads 433

Authors: Rami El-Hajj Mohamad, Mahmoud Skafi, Ali Massoud Haidar

Abstract:

Several meteorological parameters were used for the prediction of monthly average daily global solar radiation on horizontal using recurrent neural networks (RNNs). Climatological data and measures, mainly air temperature, humidity, sunshine duration, and wind speed between 1995 and 2007 were used to design and validate a feed forward and recurrent neural network based prediction systems. In this paper we present our reference system based on a feed-forward multilayer perceptron (MLP) as well as the proposed approach based on an RNN model. The obtained results were promising and comparable to those obtained by other existing empirical and neural models. The experimental results showed the advantage of RNNs over simple MLPs when we deal with time series solar radiation predictions based on daily climatological data.

Keywords: recurrent neural networks, global solar radiation, multi-layer perceptron, gradient, root mean square error

Procedia PDF Downloads 444

Authors: Christoph Linse, Thomas Martinetz

Abstract:

Recent findings have shown that Neural Networks generalize also in over-parametrized regimes with zero training error. This is surprising, since it is completely against traditional machine learning wisdom. In our empirical study we fortify these findings in the domain of fine-grained image classification. We show that very large Convolutional Neural Networks with millions of weights do learn with only a handful of training samples and without image augmentation, explicit regularization or pretraining. We train the architectures ResNet018, ResNet101 and VGG19 on subsets of the difficult benchmark datasets Caltech101, CUB_200_2011, FGVCAircraft, Flowers102 and StanfordCars with 100 classes and more, perform a comprehensive comparative study and draw implications for the practical application of CNNs. Finally, we show that VGG19 with 140 million weights learns to distinguish airplanes and motorbikes with up to 95% accuracy using only 20 training samples per class.

Keywords: convolutional neural networks, fine-grained image classification, generalization, image recognition, over-parameterized, small data sets

Procedia PDF Downloads 88

Authors: H. Kiani, S. Moradi, B. Soltani Soulgani, S. Mousavian

Abstract:

Desalting/dehydration plants (DDP) are often installed in crude oil production units in order to remove water-soluble salts from an oil stream. In order to optimize this process, desalting unit should be modeled. In this research, artificial neural network is used to model efficiency of desalting unit as a function of input parameter. The result of this research shows that the mentioned model has good agreement with experimental data.

Keywords: desalting unit, crude oil, neural networks, simulation, recovery, separation

Procedia PDF Downloads 450

Authors: M. Salih Taci, N. Tayebi, I. Bozkır

Abstract:

In this paper, the equivalent circuit of the ideal single-phase power transformer with its appropriate voltage current measurement was presented. The calculated values of the voltages and currents of the different connections single phase normal transformer and the results of the simulation process are compared. As it can be seen, the calculated results are the same as the simulated results. This paper includes eight possible different transformer connections. Depending on the desired voltage level, step-down and step-up application transformer is considered. Modelling and analysis of a system consisting of an equivalent source, transformer (primary and secondary), and loads are performed to investigate the combinations. The obtained values are simulated in PSpice environment and then how the currents, voltages and phase angle are distributed between them is explained based on calculation.

Keywords: transformer, simulation, equivalent model, parallel series combinations

Procedia PDF Downloads 361

Authors: Xuewen Yu, Danhui Dan

Abstract:

The identification of impact load and some hard-to-obtain system parameters is crucial for the activities of analysis, validation, and evaluation in the engineering field. This paper proposes a method that utilizes neural networks based on 1D-CNN to identify the impact load and partial system parameters from measured responses. To this end, forward computations are conducted to provide datasets consisting of the triples (parameter θ, input u, output y). Then neural networks are trained to learn the mapping from input to output, fu|{θ} : y → u, as well as from input and output to parameter, fθ : (u, y) → θ. Afterward, feeding the trained neural networks the measured output response, the input impact load and system parameter can be calculated, respectively. The method is tested on two simulated examples and shows sound accuracy in estimating the impact load (waveform and location) and system parameters.

Keywords: convolutional neural network, impact load identification, system parameter identification, inverse problem

Procedia PDF Downloads 123

Authors: Chad Brown

Abstract:

This paper establishes general conditions for the convergence rates of nonparametric sieve estimators with dependent data. We present two key results: one for nonstationary data and another for stationary mixing data. Previous theoretical results often lack practical applicability to deep neural networks (DNNs). Using these conditions, we derive convergence rates for DNN sieve estimators in nonparametric regression settings with both nonstationary and stationary mixing data. The DNN architectures considered adhere to current industry standards, featuring fully connected feedforward networks with rectified linear unit activation functions, unbounded weights, and a width and depth that grows with sample size.

Keywords: sieve extremum estimates, nonparametric estimation, deep learning, neural networks, rectified linear unit, nonstationary processes

Procedia PDF Downloads 41

Authors: Elabed Saud

Abstract:

This paper introduces the new ability of Artificial Neural Networks (ANNs) in estimating speed and controlling the separately excited DC motor. The neural control scheme consists of two parts. One is the neural estimator which is used to estimate the motor speed. The other is the neural controller which is used to generate a control signal for a converter. These two neutrals are training by Levenberg-Marquardt back-propagation algorithm. ANNs are the standard three layers feed-forward neural network with sigmoid activation functions in the input and hidden layers and purelin in the output layer. Simulation results are presented to demonstrate the effectiveness of this neural and advantage of the control system DC motor with ANNs in comparison with the conventional scheme without ANNs.

Keywords: Artificial Neural Network (ANNs), excited DC motor, convenional controller, speed Controller

Procedia PDF Downloads 726

Authors: Kyu Chul Lee, Sung Hyun Yoo, Choon Ki Ahn, Myo Taeg Lim

Abstract:

Recent experimental evidences have shown that because of a fast convergence and a nice accuracy, neural networks training via extended Kalman filter (EKF) method is widely applied. However, as to an uncertainty of the system dynamics or modeling error, the performance of the method is unreliable. In order to overcome this problem in this paper, a new finite impulse response (FIR) filter based learning algorithm is proposed to train radial basis function neural networks (RBFN) for nonlinear function approximation. Compared to the EKF training method, the proposed FIR filter training method is more robust to those environmental conditions. Furthermore, the number of centers will be considered since it affects the performance of approximation.

Keywords: extended Kalman filter, classification problem, radial basis function networks (RBFN), finite impulse response (FIR) filter

Procedia PDF Downloads 456

Authors: C. N. Vanitha, M. Usha

Abstract:

In a real world scenario, the viability of the sensor networks has been proved by standardizing the technologies. Wireless sensor networks are vulnerable to both electronic and physical security breaches because of their deployment in remote, distributed, and inaccessible locations. The compromised sensor nodes send malicious data to the base station, and thus, the total network effectiveness will possibly be compromised. To detect and seclude the Route modifiers, a neural network based Pattern Learning predictor (PLP) is presented. This algorithm senses data at any node on present and previous patterns obtained from the en-route nodes. The eminence of any node is upgraded by their predicted and reported patterns. This paper propounds a solution not only to detect the route modifiers, but also to seclude the malevolent nodes from the network. The simulation result proves the effective performance of the network by the presented methodology in terms of energy level, routing and various network conditions.

Keywords: neural networks, pattern learning, security, wireless sensor networks

Procedia PDF Downloads 404

Authors: Andrey Khalov

Abstract:

The rapid proliferation of unstructured data in IT infrastructure management demands innovative approaches for extracting actionable knowledge. This paper presents a framework for ontology-based knowledge extraction that combines relational graph neural networks (R-GNN) with large language models (LLMs). The proposed method leverages the DOLCE framework as the foundational ontology, extending it with concepts from ITSMO for domain-specific applications in IT service management and outsourcing. A key component of this research is the use of transformer-based models, such as DeBERTa-v3-large, for automatic entity and relationship extraction from unstructured texts. Furthermore, the paper explores how transfer learning techniques can be applied to fine-tune large language models (LLaMA) for using to generate synthetic datasets to improve precision in BERT-based entity recognition and ontology alignment. The resulting IT Ontology (ITO) serves as a comprehensive knowledge base that integrates domain-specific insights from ITIL processes, enabling more efficient decision-making. Experimental results demonstrate significant improvements in knowledge extraction and relationship mapping, offering a cutting-edge solution for enhancing cognitive computing in IT service environments.

Keywords: ontology expansion, synthetic dataset, transformer fine-tuning, concept extraction, DOLCE, BERT, taxonomy, LLM, NER

Procedia PDF Downloads 14

Authors: Tea Poklepović, Zdravka Aljinović, Branka Marasović

Abstract:

Due to the importance of yield curve and its estimation it is inevitable to have valid methods for yield curve forecasting in cases when there are scarce issues of securities and/or week trade on a secondary market. Therefore in this paper, after the estimation of weekly yield curves on Croatian financial market from October 2011 to August 2012 using Nelson-Siegel and Svensson models, yield curves are forecasted using Vector auto-regressive model and Neural networks. In general, it can be concluded that both forecasting methods have good prediction abilities where forecasting of yield curves based on Nelson Siegel estimation model give better results in sense of lower Mean Squared Error than forecasting based on Svensson model Also, in this case Neural networks provide slightly better results. Finally, it can be concluded that most appropriate way of yield curve prediction is neural networks using Nelson-Siegel estimation of yield curves.

Keywords: Nelson-Siegel Model, neural networks, Svensson Model, vector autoregressive model, yield curve

Procedia PDF Downloads 334

Authors: Ghorab Sara, Meziani Lila, Rubin Harvey Stuart

Abstract:

The rapid growth of deep learning has led to intricate and resource-intensive deep neural networks widely used in computer vision tasks. However, their complexity results in high computational demands and memory usage, hindering real-time application. To address this, research focuses on model compression techniques. The paper provides an overview of recent advancements in compressing neural networks and categorizes the various methods into four main approaches: network pruning, quantization, network decomposition, and knowledge distillation. This paper aims to provide a comprehensive outline of both the advantages and limitations of each method.

Keywords: model compression, deep neural network, pruning, knowledge distillation, quantization, low-rank decomposition

Procedia PDF Downloads 43