Search results for: bidirectional LSTM

Authors: Fazıl Gökgöz, Fahrettin Filiz

Abstract:

Load forecasting has become crucial in recent years and become popular in forecasting area. Many different power forecasting models have been tried out for this purpose. Electricity load forecasting is necessary for energy policies, healthy and reliable grid systems. Effective power forecasting of renewable energy load leads the decision makers to minimize the costs of electric utilities and power plants. Forecasting tools are required that can be used to predict how much renewable energy can be utilized. The purpose of this study is to explore the effectiveness of LSTM-based neural networks for estimating renewable energy loads. In this study, we present models for predicting renewable energy loads based on deep neural networks, especially the Long Term Memory (LSTM) algorithms. Deep learning allows multiple layers of models to learn representation of data. LSTM algorithms are able to store information for long periods of time. Deep learning models have recently been used to forecast the renewable energy sources such as predicting wind and solar energy power. Historical load and weather information represent the most important variables for the inputs within the power forecasting models. The dataset contained power consumption measurements are gathered between January 2016 and December 2017 with one-hour resolution. Models use publicly available data from the Turkish Renewable Energy Resources Support Mechanism. Forecasting studies have been carried out with these data via deep neural networks approach including LSTM technique for Turkish electricity markets. 432 different models are created by changing layers cell count and dropout. The adaptive moment estimation (ADAM) algorithm is used for training as a gradient-based optimizer instead of SGD (stochastic gradient). ADAM performed better than SGD in terms of faster convergence and lower error rates. Models performance is compared according to MAE (Mean Absolute Error) and MSE (Mean Squared Error). Best five MAE results out of 432 tested models are 0.66, 0.74, 0.85 and 1.09. The forecasting performance of the proposed LSTM models gives successful results compared to literature searches.

Keywords: deep learning, long short term memory, energy, renewable energy load forecasting

Procedia PDF Downloads 232

Authors: Arnab Adhikari, Arnab Bisi

Abstract:

Since the inception, the fashion apparel supply chain is facing the problem of high demand uncertainty. Often the demand volatility compels the corresponding supply chain member to incur substantial holding cost and opportunity cost in case of the overproduction and the underproduction scenario, respectively. It leads to an uncoordinated fashion apparel supply chain. There exist several scholarly works to achieve coordination in the fashion apparel supply chain by employing the different contracts such as the buyback contract, the revenue sharing contract, the option contract, and so on. Specially, the application of option contract in the apparel industry becomes prevalent with the changing global scenario. Exploration of existing literature related to the option contract reveals that most of the research works concentrate on the one direction demand adjustment i.e. either to match the demand upwards or downwards. Here, we present a holistic approach to coordinate a dyadic fashion apparel supply chain comprising one manufacturer and one retailer with the help of bidirectional option contract. We show a combination of wholesale price contract and bidirectional option contract can coordinate the under expanded supply chain. We also propose a framework that captures the variation of the apparel retailer’s order quantity and the apparel manufacturer’s production quantity with the changing exercise price for the different ranges of the option price. We analytically explore that corresponding cost parameters of the supply chain members along with the nature of demand distribution play an instrumental role in the coordination as well as the retailer’s ordering decision.

Keywords: fashion apparel supply chain, supply chain coordination, wholesale price contract, bidirectional option contract

Procedia PDF Downloads 418

Authors: Swati Tyagi, Syed Abbas

Abstract:

Fractional-order Hopfield neural networks are generally used to model the information processing among the interacting neurons. To show the constancy of the processed information, it is required to analyze the stability of these systems. In this work, we perform Mittag-Leffler stability for the corresponding Caputo fractional-order bidirectional associative memory (BAM) neural networks with various time-delays. We derive sufficient conditions to ensure the existence and uniqueness of the equilibrium point by using the theory of topological degree theory. By applying the fractional Lyapunov method and Mittag-Leffler functions, we derive sufficient conditions for the global Mittag-Leffler stability, which further imply the global asymptotic stability of the network equilibrium. Finally, we present two suitable examples to show the effectiveness of the obtained results.

Keywords: bidirectional associative memory neural network, existence and uniqueness, fractional-order, Lyapunov function, Mittag-Leffler stability

Procedia PDF Downloads 337

Authors: Abdulaziz Afandi

Abstract:

Minimizing the inventory cost, optimizing the inventory quantities, and increasing system operational availability are the main motivations to enhance forecasting demand of spare parts in a major power utility company in Medina. This paper reports in an effort made to optimize the orders quantities of spare parts by improving the method of forecasting the demand. The study focuses on equipment that has frequent spare parts purchase orders with uncertain demand. The pattern of the demand considers a lumpy pattern which makes conventional forecasting methods less effective. A comparison was made by benchmarking various methods of forecasting based on experts’ criteria to select the most suitable method for the case study. Three actual data sets were used to make the forecast in this case study. Two neural networks (NN) approaches were utilized and compared, namely long short-term memory (LSTM) and multilayer perceptron (MLP). The results as expected, showed that the NN models gave better results than traditional forecasting method (judgmental method). In addition, the LSTM model had a higher predictive accuracy than the MLP model.

Keywords: neural network, LSTM, MLP, forecasting demand, inventory management

Procedia PDF Downloads 98

Authors: Zhe Li, Aihua Cai

Abstract:

Aiming at the problem of high-density clutter and interference affecting radar detection target track initiation in ECM and complex radar mission, the traditional radar target track initiation method has been difficult to adapt. To this end, we propose a multi-algorithm fusion learning track initiation algorithm, which transforms the track initiation problem into a true-false track discrimination problem, and designs an algorithm based on 1DCNN(One-Dimensional CNN)combined with Bi-LSTM (Bi-Directional Long Short-Term Memory )for fusion classification. The experimental dataset consists of real trajectories obtained from a certain type of three-coordinate radar measurements, and the experiments are compared with traditional trajectory initiation methods such as rule-based method, logical-based method and Hough-transform-based method. The simulation results show that the overall performance of the multi-algorithm fusion learning track initiation algorithm is significantly better than that of the traditional method, and the real track initiation rate can be effectively improved under high clutter density with the average initiation time similar to the logical method.

Keywords: track initiation, multi-algorithm fusion, 1DCNN, Bi-LSTM

Procedia PDF Downloads 46

Authors: Shervin Alaei, Reza Moradi

Abstract:

Trading in financial markets is subject to risks due to their high volatilities. Here, using an LSTM neural network, and by doing some risk-based feature engineering tasks, we developed a method that can accurately predict trends of the Tehran stock exchange market index from a few days ago. Our test results have shown that the proposed method with an average prediction accuracy of more than 94% is superior to the other common machine learning algorithms. To the best of our knowledge, this is the first work incorporating deep learning and risk factors to accurately predict market trends.

Keywords: deep learning, LSTM, trend prediction, risk management, artificial neural networks

Procedia PDF Downloads 113

Authors: Amartya Hatua, Trung Nguyen, Andrew Sung

Abstract:

In this paper, we study the information diffusion process on Twitter as a multivariate time series problem. Our model concerns three measures (volume, network influence, and sentiment of tweets) based on 10 features, and we collected 27 million tweets to build our information diffusion time series dataset for analysis. Then, different time series clustering techniques with Dynamic Time Warping (DTW) distance were used to identify different patterns of information diffusion. Finally, we built the information diffusion prediction models for new hashtags which comprise two phrases: The first phrase is recognizing the pattern using k-NN with DTW distance; the second phrase is building the forecasting model using the traditional Autoregressive Integrated Moving Average (ARIMA) model and the non-linear recurrent neural network of Long Short-Term Memory (LSTM). Preliminary results of performance evaluation between different forecasting models show that LSTM with clustering information notably outperforms other models. Therefore, our approach can be applied in real-world applications to analyze and predict the information diffusion characteristics of selected topics or memes (hashtags) in Twitter.

Keywords: ARIMA, DTW, information diffusion, LSTM, RNN, time series clustering, time series forecasting, Twitter

Procedia PDF Downloads 361

Authors: Amir Andria Gad Shehata

Abstract:

Minimizing the inventory cost, optimizing the inventory quantities, and increasing system operational availability are the main motivations to enhance forecasting demand of spare parts in a major power utility company in Medina. This paper reports in an effort made to optimize the orders quantities of spare parts by improving the method of forecasting the demand. The study focuses on equipment that has frequent spare parts purchase orders with uncertain demand. The pattern of the demand considers a lumpy pattern which makes conventional forecasting methods less effective. A comparison was made by benchmarking various methods of forecasting based on experts’ criteria to select the most suitable method for the case study. Three actual data sets were used to make the forecast in this case study. Two neural networks (NN) approaches were utilized and compared, namely long short-term memory (LSTM) and multilayer perceptron (MLP). The results as expected, showed that the NN models gave better results than traditional forecasting method (judgmental method). In addition, the LSTM model had a higher predictive accuracy than the MLP model.

Keywords: spare part, spare part inventory, inventory model, optimization, maintenanceneural network, LSTM, MLP, forecasting demand, inventory management

Procedia PDF Downloads 19

Authors: Sonia Perez-Gamboa, Qingquan Sun, Yan Zhang

Abstract:

Non-intrusive sensor-based human activity recognition (HAR) is utilized in a spectrum of applications, including fitness tracking devices, gaming, health care monitoring, and smartphone applications. Deep learning models such as convolutional neural networks (CNNs) and long short term memory (LSTM) recurrent neural networks (RNNs) provide a way to achieve HAR accurately and effectively. In this paper, we design a multi-layer hybrid architecture with CNN and LSTM and explore a variety of multi-layer combinations. Based on the exploration, we present a lightweight, hybrid, and multi-layer model, which can improve the recognition performance by integrating local features and scale-invariant with dependencies of activities. The experimental results demonstrate the efficacy of the proposed model, which can achieve a 94.7% activity recognition rate on a benchmark human activity dataset. This model outperforms traditional machine learning and other deep learning methods. Additionally, our implementation achieves a balance between recognition rate and training time consumption.

Keywords: deep learning, LSTM, CNN, human activity recognition, inertial sensor

Procedia PDF Downloads 117

Authors: Grienggrai Rajchakit

Abstract:

As we all know that coronavirus is announced as a pandemic in the world by WHO. It is speeded all over the world with few days of time. To control this spreading, every citizen maintains social distance and self-preventive measures are the best strategies. As of now, many researchers and scientists are continuing their research in finding out the exact vaccine. The machine learning model finds that the coronavirus disease behaves in an exponential manner. To abolish the consequence of this pandemic, an efficient step should be taken to analyze this disease. In this paper, a recurrent neural network model is chosen to predict the number of active cases in a particular state. To make this prediction of active cases, we need a database. The database of COVID-19 is downloaded from the KAGGLE website and is analyzed by applying a recurrent LSTM neural network with univariant features to predict the number of active cases of patients suffering from the corona virus. The downloaded database is divided into training and testing the chosen neural network model. The model is trained with the training data set and tested with a testing dataset to predict the number of active cases in a particular state; here, we have concentrated on Andhra Pradesh state.

Keywords: COVID-19, coronavirus, KAGGLE, LSTM neural network, machine learning

Procedia PDF Downloads 136

Authors: Babak Forouraghi

Abstract:

A genetic circuit is a collection of interacting genes and proteins that enable individual cells to implement and perform vital biological functions such as cell division, growth, death, and signaling. In cell engineering, synthetic gene circuits are engineered networks of genes specifically designed to implement functionalities that are not evolved by nature. These engineered networks enable scientists to tackle complex problems such as engineering cells to produce therapeutics within the patient's body, altering T cells to target cancer-related antigens for treatment, improving antibody production using engineered cells, tissue engineering, and production of genetically modified plants and livestock. Construction of computational models to realize genetic circuits is an especially challenging task since it requires the discovery of the flow of genetic information in complex biological systems. Building synthetic biological models is also a time-consuming process with relatively low prediction accuracy for highly complex genetic circuits. The primary goal of this study was to investigate the utility of a pre-trained bidirectional encoder transformer that can accurately predict gene expressions in genetic circuit designs. The main reason behind using transformers is their innate ability (attention mechanism) to take account of the semantic context present in long DNA chains that are heavily dependent on the spatial representation of their constituent genes. Previous approaches to gene circuit design, such as CNN and RNN architectures, are unable to capture semantic dependencies in long contexts, as required in most real-world applications of synthetic biology. For instance, RNN models (LSTM, GRU), although able to learn long-term dependencies, greatly suffer from vanishing gradient and low-efficiency problem when they sequentially process past states and compresses contextual information into a bottleneck with long input sequences. In other words, these architectures are not equipped with the necessary attention mechanisms to follow a long chain of genes with thousands of tokens. To address the above-mentioned limitations, a transformer model was built in this work as a variation to the existing DNA Bidirectional Encoder Representations from Transformers (DNABERT) model. It is shown that the proposed transformer is capable of capturing contextual information from long input sequences with an attention mechanism. In previous works on genetic circuit design, the traditional approaches to classification and regression, such as Random Forrest, Support Vector Machine, and Artificial Neural Networks, were able to achieve reasonably high R2 accuracy levels of 0.95 to 0.97. However, the transformer model utilized in this work, with its attention-based mechanism, was able to achieve a perfect accuracy level of 100%. Further, it is demonstrated that the efficiency of the transformer-based gene expression classifier is not dependent on the presence of large amounts of training examples, which may be difficult to compile in many real-world gene circuit designs.

Keywords: machine learning, classification and regression, gene circuit design, bidirectional transformers

Procedia PDF Downloads 33

Authors: Marco Furinghetti, Alberto Pavese, Michele Rinaldi

Abstract:

Concave Surface Slider devices have been more and more used in real applications for seismic protection of both bridge and building structures. Several research activities have been carried out, in order to investigate the lateral response of such a typology of devices, and a reasonably high level of knowledge has been reached. If radial analysis is performed, the frictional force is always aligned with respect to the restoring force, whereas under bidirectional seismic events, a bi-axial interaction of the directions of motion occurs, due to the step-wise projection of the main frictional force, which is assumed to be aligned to the trajectory of the isolator. Nonetheless, if non-linear time history analyses have to be performed, standard codes provide precise rules for the definition of an averagely spectrum-compatible set of accelerograms in radial conditions, whereas for bidirectional motions different combinations of the single components spectra can be found. Moreover, nowadays software for the adjustment of natural accelerograms are available, which lead to a higher quality of spectrum-compatibility and to a smaller dispersion of results for radial motions. In this endeavor a simplified design procedure is defined, for building structures, base-isolated by means of Concave Surface Slider devices. Different case study structures have been analyzed. In a first stage, the capacity curve has been computed, by means of non-linear static analyses on the fixed-base structures: inelastic fiber elements have been adopted and different direction angles of lateral forces have been studied. Thanks to these results, a linear elastic Finite Element Model has been defined, characterized by the same global stiffness of the linear elastic branch of the non-linear capacity curve. Then, non-linear time history analyses have been performed on the base-isolated structures, by applying seven bidirectional seismic events. The spectrum-compatibility of bidirectional earthquakes has been studied, by considering different combinations of single components and adjusting single records: thanks to the proposed procedure, results have shown a small dispersion and a good agreement in comparison to the assumed design values.

Keywords: concave surface slider, spectrum-compatibility, bidirectional earthquake, base isolation

Procedia PDF Downloads 263

Authors: Sharun Akter Khushbu

Abstract:

‘SOS’ addresses text summary such as feasibility study and allows more comprehensive methods on text of language resources. Resources language has been exploited by the importance of text documental procedure. Throughout this key idea will come out a machine interpreter called an SOS that has built an argumentative as an employed model is LSTM-CNN(long short-term memory- recurrent neural network). Summarization of Bengali text formulated by the information of latent structure instead of brief input string counting as text. Text summarization is the proper utilization of optimal solutions being time reduction, and easy interpretation whenever human-generated summary and machine targeted summary remain similar and without degrading the semantic summarization quality. According to the problem affirmation key idea has advanced an algorithm with the method of encoder and decoder describing a sequential structure that is rigorously connected with actual predicted and meaningful output. Regarding the seq2seq approach aimed in the future with high semantic summarization similarity on behalf of the large data samples that are also enlisted by the method. Thus, the SOS method assigns a discriminator over Bengali text documents where encoded input sequences such as summary and decoded the targeted summary of gist will be an error-free machine.

Keywords: LSTM-CNN, NN, SOS, text summarization

Procedia PDF Downloads 42

Authors: Danilo López, Nelson Vera, Luis Pedraza

Abstract:

This paper analyzes fundamental ideas and concepts related to neural networks, which provide the reader a theoretical explanation of Long Short-Term Memory (LSTM) networks operation classified as Deep Learning Systems, and to explicitly present the mathematical development of Backward Pass equations of the LSTM network model. This mathematical modeling associated with software development will provide the necessary tools to develop an intelligent system capable of predicting the behavior of licensed users in wireless cognitive radio networks.

Keywords: neural networks, multilayer perceptron, long short-term memory, recurrent neuronal network, mathematical analysis

Procedia PDF Downloads 384

Authors: Venkat S. Somayajula

Abstract:

Ground surface temperature history prediction model plays a vital role in determining standards for international nuclear waste management. International standards for borehole based nuclear waste disposal require paleoclimate cycle predictions on scale of a million forward years for the place of waste disposal. This research focuses on developing a paleoclimate cycle prediction model using Bayesian long-short term memory (LSTM) neural architecture operated on accumulated borehole temperature history data. Bayesian models have been previously used for paleoclimate cycle prediction based on Monte-Carlo weight method, but due to limitations pertaining model coupling with certain other prediction networks, Bayesian models in past couldn’t accommodate prediction cycle’s over 1000 years. LSTM has provided frontier to couple developed models with other prediction networks with ease. Paleoclimate cycle developed using this process will be trained on existing borehole data and then will be coupled to surface temperature history prediction networks which give endpoints for backpropagation of LSTM network and optimize the cycle of prediction for larger prediction time scales. Trained LSTM will be tested on past data for validation and then propagated for forward prediction of temperatures at borehole locations. This research will be beneficial for study pertaining to nuclear waste management, anthropological cycle predictions and geophysical features

Keywords: Bayesian long-short term memory neural network, borehole temperature, ground surface temperature history, paleoclimate cycle

Procedia PDF Downloads 101

Authors: Xiang-Yao Zheng, Jen-Cheng Wang, Joe-Air Jiang

Abstract:

Improving the line ampacity while using existing power grids is an important issue that electricity dispatchers are now facing. Using the information provided by the dynamic thermal rating (DTR) of transmission lines, an overhead power grid can operate safely. However, dispatchers usually lack real-time DTR information. Thus, this study proposes a long-short-term memory (LSTM)-based method, which is one of the neural network models. The LSTM-based method predicts the DTR of lines using the weather data provided by Central Weather Bureau (CWB) of Taiwan. The possible thermal bottlenecks at different locations along the line and the margin of line ampacity can be real-time determined by the proposed LSTM-based prediction method. A case study that targets the 345 kV power grid of TaiPower in Taiwan is utilized to examine the performance of the proposed method. The simulation results show that the proposed method is useful to provide the information for the smart grid application in the future.

Keywords: electricity dispatch, line ampacity prediction, dynamic thermal rating, long-short-term memory neural network, smart grid

Procedia PDF Downloads 258

Authors: Vikrant Gupta, Amrit Goswami

Abstract:

The fixed income market forms the basis of the modern financial market. All other assets in financial markets derive their value from the bond market. Owing to its over-the-counter nature, corporate bonds have relatively less data publicly available and thus is researched upon far less compared to Equities. Bond price prediction is a complex financial time series forecasting problem and is considered very crucial in the domain of finance. The bond prices are highly volatile and full of noise which makes it very difficult for traditional statistical time-series models to capture the complexity in series patterns which leads to inefficient forecasts. To overcome the inefficiencies of statistical models, various machine learning techniques were initially used in the literature for more accurate forecasting of time-series. However, simple machine learning methods such as linear regression, support vectors, random forests fail to provide efficient results when tested on highly complex sequences such as stock prices and bond prices. hence to capture these intricate sequence patterns, various deep learning-based methodologies have been discussed in the literature. In this study, a recurrent neural network-based deep learning model using long short term networks for prediction of corporate bond prices has been discussed. Long Short Term networks (LSTM) have been widely used in the literature for various sequence learning tasks in various domains such as machine translation, speech recognition, etc. In recent years, various studies have discussed the effectiveness of LSTMs in forecasting complex time-series sequences and have shown promising results when compared to other methodologies. LSTMs are a special kind of recurrent neural networks which are capable of learning long term dependencies due to its memory function which traditional neural networks fail to capture. In this study, a simple LSTM, Stacked LSTM and a Masked LSTM based model has been discussed with respect to varying input sequences (three days, seven days and 14 days). In order to facilitate faster learning and to gradually decompose the complexity of bond price sequence, an Empirical Mode Decomposition (EMD) has been used, which has resulted in accuracy improvement of the standalone LSTM model. With a variety of Technical Indicators and EMD decomposed time series, Masked LSTM outperformed the other two counterparts in terms of prediction accuracy. To benchmark the proposed model, the results have been compared with traditional time series models (ARIMA), shallow neural networks and above discussed three different LSTM models. In summary, our results show that the use of LSTM models provide more accurate results and should be explored more within the asset management industry.

Keywords: bond prices, long short-term memory, time series forecasting, empirical mode decomposition

Procedia PDF Downloads 105

Authors: Farhan Beg

Abstract:

This paper presents a method for the efficient implementation of a unidirectional or bidirectional DC/DC converter. The DC/DC converter is used essentially for energy exchange between the low voltage service battery and a high voltage battery commonly found in Electric Vehicle applications. In these applications, apart from cost, efficiency of design is an important characteristic. A useful way to reduce the size of electronic equipment in the electric vehicles is proposed in this paper. The technique simplifies the mechanical complexity and maximizes the energy usage using the latest converter control techniques. Moreover a bidirectional battery charger for hybrid electric vehicles is also implemented in this paper. Several simulations on the test system have been carried out in Matlab/Simulink environment. The results exemplify the robustness of the proposed design methodology in case of a 1.5 KW DC-DC converter.

Keywords: DC-DC converters, electric vehicles, power electronics, direct current control

Procedia PDF Downloads 694

Authors: Akinbo Razak Yinka, Adesanya Kehinde Kazeem, Oladokun Oluwagbenga Peter

Abstract:

Time series data are sequences of observations collected over a period of time. Such data can be used to predict health outcomes, such as disease progression, mortality, hospitalization, etc. The Statistical approach is based on mathematical models that capture the patterns and trends of the data, such as autocorrelation, seasonality, and noise, while Neural methods are based on artificial neural networks, which are computational models that mimic the structure and function of biological neurons. This paper compared both parametric and non-parametric time series models of patients treated for malaria in Maternal and Child Health Centres in Lagos State, Nigeria. The forecast methods considered linear regression, Integrated Moving Average, ARIMA and SARIMA Modeling for the parametric approach, while Multilayer Perceptron (MLP) and Long Short-Term Memory (LSTM) Network were used for the non-parametric model. The performance of each method is evaluated using the Mean Absolute Error (MAE), R-squared (R2) and Root Mean Square Error (RMSE) as criteria to determine the accuracy of each model. The study revealed that the best performance in terms of error was found in MLP, followed by the LSTM and ARIMA models. In addition, the Bootstrap Aggregating technique was used to make robust forecasts when there are uncertainties in the data.

Keywords: ARIMA, bootstrap aggregation, MLP, LSTM, SARIMA, time-series analysis

Procedia PDF Downloads 34

Authors: Debneil Saha Roy

Abstract:

Weather forecasting is a complex topic and is well suited for analysis by deep learning approaches. With the wide availability of weather observation data nowadays, these approaches can be utilized to identify immediate comparisons between historical weather forecasts and current observations. This work explores the application of deep learning techniques to weather forecasting in order to accurately predict the weather over a given forecast hori­zon. Three deep neural networks are used in this study, namely, Multi-Layer Perceptron (MLP), Long Short Tunn Memory Network (LSTM) and a combination of Convolutional Neural Network (CNN) and LSTM. The predictive performance of these models is compared using two evaluation metrics. The results show that forecasting accuracy increases with an increase in the complexity of deep neural networks.

Keywords: convolutional neural network, deep learning, long short term memory, multi-layer perceptron

Procedia PDF Downloads 137

Authors: Sam Khozama, Ali M. Mayya

Abstract:

Breast cancer is one of the most common types in women. Early prediction of breast cancer helps physicians detect cancer in its early stages. Big cancer data needs a very powerful tool to analyze and extract predictions. Machine learning and deep learning are two of the most efficient tools for predicting cancer based on textual data. In this study, we developed a fusion model of two machine learning and deep learning models. To obtain the final prediction, Long-Short Term Memory (LSTM) and ensemble learning with hyper parameters optimization are used, and score-level fusion is used. Experiments are done on the Breast Cancer Surveillance Consortium (BCSC) dataset after balancing and grouping the class categories. Five different training scenarios are used, and the tests show that the designed fusion model improved the performance by 3.3% compared to the individual models.

Keywords: machine learning, deep learning, cancer prediction, breast cancer, LSTM, fusion

Procedia PDF Downloads 132

Authors: Haidy S. Ghali, Engy Serag, A. Samer Ezeldin

Abstract:

Copper is an essential raw material used in the construction industry. During the year 2021 and the first half of 2022, the global market suffered from a significant fluctuation in copper raw material prices due to the aftermath of both the COVID-19 pandemic and the Russia-Ukraine war, which exposed its consumers to an unexpected financial risk. Thereto, this paper aims to develop two ANN-LSTM price prediction models, using Python, that can forecast the average monthly copper prices traded in the London Metal Exchange; the first model is a multivariate model that forecasts the copper price of the next 1-month and the second is a univariate model that predicts the copper prices of the upcoming three months. Historical data of average monthly London Metal Exchange copper prices are collected from January 2009 till July 2022, and potential external factors are identified and employed in the multivariate model. These factors lie under three main categories: energy prices and economic indicators of the three major exporting countries of copper, depending on the data availability. Before developing the LSTM models, the collected external parameters are analyzed with respect to the copper prices using correlation and multicollinearity tests in R software; then, the parameters are further screened to select the parameters that influence the copper prices. Then, the two LSTM models are developed, and the dataset is divided into training, validation, and testing sets. The results show that the performance of the 3-Month prediction model is better than the 1-Month prediction model, but still, both models can act as predicting tools for diverse economic situations.

Keywords: copper prices, prediction model, neural network, time series forecasting

Procedia PDF Downloads 77

Authors: Ons Slimene, Aroua Taamallah, Maha Khemaja

Abstract:

In recent years, human activity recognition (HAR) has been a key area of research due to its diverse applications. It has garnered increasing attention in the field of computer vision. HAR plays an important role in people’s daily lives as it has the ability to learn advanced knowledge about human activities from data. In HAR, activities are usually represented by exploiting different types of sensors, such as embedded sensors or visual sensors. However, these sensors have limitations, such as local obstacles, image-related obstacles, sensor unreliability, and consumer concerns. Recently, several deep learning-based approaches have been proposed for HAR and these approaches are classified into two categories based on the type of data used: vision-based approaches and sensor-based approaches. This research paper highlights the importance of multimodal data fusion from skeleton data obtained from videos and data generated by embedded sensors using deep neural networks for achieving HAR. We propose a deep multimodal fusion network based on a twostream architecture. These two streams use the Convolutional Neural Network combined with the Bidirectional LSTM (CNN BILSTM) to process skeleton data and data generated by embedded sensors and the fusion at the feature level is considered. The proposed model was evaluated on a public OPPORTUNITY++ dataset and produced a accuracy of 96.77%.

Keywords: human activity recognition, action recognition, sensors, vision, human-centric sensing, deep learning, context-awareness

Procedia PDF Downloads 68

Authors: Huawei Bai, Jianguo Yao, Fellow, IEEE

Abstract:

Atrial fibrillation (AF) is the most common form of heart arrhythmia and is closely associated with mortality and morbidity in heart failure, stroke, and coronary artery disease. The development of single spot optical sensors enables widespread photoplethysmography (PPG) screening, especially for AF, since it represents a more convenient and noninvasive approach. To our knowledge, most existing studies based on public and unbalanced datasets can barely handle the multiple noises sources in the real world and, also, lack interpretability. In this paper, we construct a large- scale PPG dataset using measurements collected from PPG wrist- watch devices worn by volunteers and propose an attention-based two-stream heterogeneous neural network (TSHNN). The first stream is a hybrid neural network consisting of a three-layer one-dimensional convolutional neural network (1D-CNN) and two-layer attention- based bidirectional long short-term memory (Bi-LSTM) network to learn representations from temporally sampled signals. The second stream extracts latent representations from the PPG time-frequency spectrogram using a five-layer CNN. The outputs from both streams are fed into a fusion layer for the outcome. Visualization of the attention weights learned demonstrates the effectiveness of the attention mechanism against noise. The experimental results show that the TSHNN outperforms all the competitive baseline approaches and with 98.09% accuracy, achieves state-of-the-art performance.

Keywords: PPG wearables, atrial fibrillation, feature fusion, attention mechanism, hyber network

Procedia PDF Downloads 85

Authors: Tahani Aljohani, Jialin Yu, Alexandra. I. Cristea

Abstract:

The more an educational system knows about a learner, the more personalised interaction it can provide, which leads to better learning. However, asking a learner directly is potentially disruptive, and often ignored by learners. Especially in the booming realm of MOOC Massive Online Learning platforms, only a very low percentage of users disclose demographic information about themselves. Thus, in this paper, we aim to predict learners’ demographic characteristics, by proposing an approach using linguistically motivated Deep Learning Architectures for Learner Profiling, particularly targeting gender prediction on a FutureLearn MOOC platform. Additionally, we tackle here the difficult problem of predicting the gender of learners based on their comments only – which are often available across MOOCs. The most common current approaches to text classification use the Long Short-Term Memory (LSTM) model, considering sentences as sequences. However, human language also has structures. In this research, rather than considering sentences as plain sequences, we hypothesise that higher semantic - and syntactic level sentence processing based on linguistics will render a richer representation. We thus evaluate, the traditional LSTM versus other bleeding edge models, which take into account syntactic structure, such as tree-structured LSTM, Stack-augmented Parser-Interpreter Neural Network (SPINN) and the Structure-Aware Tag Augmented model (SATA). Additionally, we explore using different word-level encoding functions. We have implemented these methods on Our MOOC dataset, which is the most performant one comparing with a public dataset on sentiment analysis that is further used as a cross-examining for the models' results.

Keywords: deep learning, data mining, gender predication, MOOCs

Procedia PDF Downloads 114

Authors: Gong Zhilin, Jing Yang, Jian Yin

Abstract:

The purpose of this paper is to develop a novel system for credit card fraud detection based on sequential modeling of data using hybrid deep learning models. The projected model encapsulates five major phases are pre-processing, imbalance-data handling, feature extraction, optimal feature selection, and fraud detection with an ensemble classifier. The collected raw data (input) is pre-processed to enhance the quality of the data through alleviation of the missing data, noisy data as well as null values. The pre-processed data are class imbalanced in nature, and therefore they are handled effectively with the K-means clustering-based SMOTE model. From the balanced class data, the most relevant features like improved Principal Component Analysis (PCA), statistical features (mean, median, standard deviation) and higher-order statistical features (skewness and kurtosis). Among the extracted features, the most optimal features are selected with the Self-improved Arithmetic Optimization Algorithm (SI-AOA). This SI-AOA model is the conceptual improvement of the standard Arithmetic Optimization Algorithm. The deep learning models like Long Short-Term Memory (LSTM), Convolutional Neural Network (CNN), and optimized Quantum Deep Neural Network (QDNN). The LSTM and CNN are trained with the extracted optimal features. The outcomes from LSTM and CNN will enter as input to optimized QDNN that provides the final detection outcome. Since the QDNN is the ultimate detector, its weight function is fine-tuned with the Self-improved Arithmetic Optimization Algorithm (SI-AOA).

Keywords: credit card, data mining, fraud detection, money transactions

Procedia PDF Downloads 102

Authors: Getaneh Berie Tarekegn

Abstract:

Wireless communication via unmanned aerial vehicles (UAVs) has drawn a great deal of attention due to its flexibility in establishing line-of-sight (LoS) communications. However, in complex urban and dynamic environments, the movement of UAVs can be blocked by trees and high-rise buildings that obstruct directional paths. With reconfigurable intelligent surfaces (RIS), this problem can be effectively addressed. To achieve this goal, accurate channel estimation in RIS-assisted UAV-enabled wireless communications is crucial. This paper proposes an accurate channel estimation model using long short-term memory (LSTM) for a multi-user RIS-assisted UAV-enabled wireless communication system. According to simulation results, LSTM can improve the channel estimation performance of RIS-assisted UAV-enabled wireless communication.

Keywords: channel estimation, reconfigurable intelligent surfaces, long short-term memory, unmanned aerial vehicles

Procedia PDF Downloads 23

Authors: Getaneh Berie Tarekegn

Abstract:

Wireless communication via unmanned aerial vehicles (UAVs) has drawn a great deal of attention due to its flexibility in establishing line-of-sight (LoS) communications. However, in complex urban and dynamic environments, the movement of UAVs can be blocked by trees and high-rise buildings that obstruct directional paths. With reconfigurable intelligent surfaces (RIS), this problem can be effectively addressed. To achieve this goal, accurate channel estimation in RIS-assisted UAV-enabled wireless communications is crucial. This paper proposes an accurate channel estimation model using long short-term memory (LSTM) for a multi-user RIS-assisted UAV-enabled wireless communication system. According to simulation results, LSTM can improve the channel estimation performance of RIS-assisted UAV-enabled wireless communication.

Keywords: channel estimation, reconfigurable intelligent surfaces, long short-term memory, unmanned aerial vehicles

Procedia PDF Downloads 56

Authors: Xinyuan Liu, Xiaojun Jing, Yuan He, Junsheng Mu

Abstract:

Aspect-based Sentiment Analysis (ABSA) has attracted much attention due to its capacity to determine the sentiment polarity of the certain aspect in a sentence. In previous works, great significance of the interaction between aspect and sentence has been exhibited in ABSA. In consequence, a Multi-Level Attentional Networks (MLAN) is proposed. MLAN consists of four parts: Embedding Layer, Encoding Layer, Multi-Level Attentional (MLA) Layers and Final Prediction Layer. Among these parts, MLA Layers including Aspect Level Attentional (ALA) Layer and Interactive Attentional (ILA) Layer is the innovation of MLAN, whose function is to focus on the important information and obtain multiple levels’ attentional weighted representation of aspect and sentence. In the experiments, MLAN is compared with classical TD-LSTM, MemNet, RAM, ATAE-LSTM, IAN, AOA, LCR-Rot and AEN-GloVe on SemEval 2014 Dataset. The experimental results show that MLAN outperforms those state-of-the-art models greatly. And in case study, the works of ALA Layer and ILA Layer have been proven to be effective and interpretable.

Keywords: deep learning, aspect-based sentiment analysis, attention, natural language processing

Procedia PDF Downloads 113

Authors: Ammarah Irum, Muhammad Ali Tahir

Abstract:

Document-level sentiment analysis in Urdu is a challenging Natural Language Processing (NLP) task due to the difficulty of working with lengthy texts in a language with constrained resources. Deep learning models, which are complex neural network architectures, are well-suited to text-based applications in addition to data formats like audio, image, and video. To investigate the potential of deep learning for Urdu sentiment analysis, we implemented five different deep learning models, including Bidirectional Long Short Term Memory (BiLSTM), Convolutional Neural Network (CNN), Convolutional Neural Network with Bidirectional Long Short Term Memory (CNN-BiLSTM), and Bidirectional Encoder Representation from Transformer (BERT). In this study, we developed a hybrid deep learning model called BiLSTM-Single Layer Multi Filter Convolutional Neural Network (BiLSTM-SLMFCNN) by fusing BiLSTM and CNN architecture. The proposed and baseline techniques are applied on Urdu Customer Support data set and IMDB Urdu movie review data set by using pre-trained Urdu word embedding that are suitable for sentiment analysis at the document level. Results of these techniques are evaluated and our proposed model outperforms all other deep learning techniques for Urdu sentiment analysis. BiLSTM-SLMFCNN outperformed the baseline deep learning models and achieved 83%, 79%, 83% and 94% accuracy on small, medium and large sized IMDB Urdu movie review data set and Urdu Customer Support data set respectively.

Keywords: urdu sentiment analysis, deep learning, natural language processing, opinion mining, low-resource language

Procedia PDF Downloads 36