Wyniki wyszukiwania - BazTech

1

Artificial Neural Networks vs Long Short-Term Memory Prediction of Solid Flow in Tafna Basin (North-West Algeria)

Medfouni Mohamed Nadjib, Korichi Khaled, Marouf Nadir

Ecological Engineering & Environmental Technology

|

2024

|

Vol. 25, iss. 3

275--286

EN

The main objective of this work is to select the most reliable machine learning model to predict the generated solid flow in the Tafna basin (North-West of Algeria). It is about the artificial neural networks (ANN) and long short-term memory (LSTM). The sediment load is recorded through three hydrometric stations. The efficiency and performance of the two models is verified using the correlation coefficient (R2), the Nash-Sutcliffe coefficient (NSC) and the root mean square error (RMSE). The obtained simulated solids load shows a very good correlation in terms of precision although the ANN model gave relatively better results compared to the LSTM model where low RMSE values were recorded, which confirms that the artificial intelligence models remain also effective for the treatment and the prediction of hydrological phenomena such as the estimation of the solid load in a such watershed.

2

Comparative analysis of optimization value between artificial neural network and long short-term memory for prediction particulate matter (PM2.5) in Bangkok Thailand

Atiwanwong Thanpitcha, Jantakun Adirek, Sangsongfa Adisak

Przegląd Elektrotechniczny

|

2023

|

R. 99, nr 7

89--95

EN

The crisis that the general public is worried about is particulate matter as small as 2.5 microns, which is invisible to the naked eye, causing a great lack of awareness of health hazards. One of the key goals and visions of government leaders around the world is to tackle PM2.5 particulate matter, but without measurements, reports and predictions, how will it lead to emission reduction and remedial steps? Therefore, the prediction of PM2.5 is considered as the main factor that will help to reduce the pollution of PM2.5. So, Neural networks have been widely used in predictive research, but the problem is What type of neural network would be most suitable for predicting the value of PM2.5? In this research, the predictions were compared between Artificial Neural Network (ANN) and Long Short -Term Memory (LSTM) using values measured from the performance test results with accuracy. The results showed that when the values of similar hyperparameters were given different results, the average ANN accuracy is 91.1460%. The average accuracy LSTM is 96.8496%. The values obtained from the comparison clearly show that for the prediction of PM2.5, the LSTM neural network was significantly more suitable than the ANN neural network.

PL

Kryzys, który niepokoi opinię publiczną, to pył zawieszony o wielkości zaledwie 2,5 mikrona, który jest niewidoczny gołym okiem, powodując ogromny brak świadomości zagrożeń dla zdrowia. Jednym z kluczowych celów i wizji przywódców rządów na całym świecie jest rozwiązanie problemu pyłu zawieszonego PM2,5, ale bez pomiarów, raportów i prognoz, w jaki sposób doprowadzi to do redukcji emisji i działań zaradczych? Dlatego prognoza PM2,5 jest uważana za główny czynnik, który pomoże zmniejszyć zanieczyszczenie PM2,5. Tak więc sieci neuronowe były szeroko stosowane w badaniach predykcyjnych, ale problem polega na tym, jaki typ sieci neuronowej byłby najbardziej odpowiedni do przewidywania wartości PM2,5? W tym badaniu porównano przewidywania między sztuczną siecią neuronową (ANN) a pamięcią długokrótkoterminową (LSTM) przy użyciu wartości zmierzonych z wynikami testu wydajności z dużą dokładnością. Wyniki pokazały, że przy różnych wartościach podobnych hiperparametrów średnia dokładność ANN wynosi 91,1460%. Średnia dokładność LSTM wynosi 96,8496%. Uzyskane z porównania wartości jednoznacznie wskazują, że do predykcji PM2,5 sieć neuronowa LSTM okazała się znacznie bardziej odpowiednia niż sieć neuronowa ANN.

3

Rotor Speed and Load Torque Estimations of Induction Motors via LSTM Network

Kosten Mehmet Muzaffer, Emlek Alper, Yildiz Recep, Barut Murat

Power Electronics and Drives

|

2023

|

Vol. 8 (43)

310-324

EN

In this study, a long short-term memory (LSTM) based estimator using rotating axis components of the stator voltages and currents as inputs is designed to perform estimations of rotor mechanical speed and load torque values of the induction motor (IM) for electrical vehicle (EV) applications. For this aim, first of all, an indirect vector controlled IM drive is implemented in simulation to collect both training and test datasets. After the initial training, a fine-tuning process is applied to increase the robustness of the proposed LSTM network. Furthermore, the LSTM parameters, layer size, and hidden size are also optimised to increase the estimation performance. The proposed LSTM network is tested under two different challenging scenarios including the operation of the IM with linear and step-like load torque changes in a single direction and in both directions. To force the proposed LSTM network, it is also tested under the variation of stator and rotor resistances for the both-direction scenario. The obtained results confirm the highly satisfactory estimation performance of the proposed LSTM network and its applicability for the EV applications of the IMs.

4

Surface Temperature Prediction Using Long Short-Term Memory – Case Study Java Island, Indonesia

Satriadi Alfi, Widada Sugeng, Prayogi Harmon

Ecological Engineering & Environmental Technology

|

2023

|

Vol. 24, iss. 4

73--78

EN

We predict the surface temperature of Java Island in Indonesia based on a dataset of wind speed, surface temperature, and surface pressure from 2002 to 2021. Long short-term memory model is employed to predict the surface temperature in 2022. The predicted surface temperature corresponds to the seasons of Indonesia. The result shows a pattern between dry and monsoon seasons of Indonesia. The performance of the model is evaluated using root mean square error. The root mean square error in the land area is larger than the water area.

5

A deep hybrid model for human-computer interaction using dynamic hand gesture recognition

Ramalingam Brindha, Angappan Geetha

Computer Assisted Methods in Engineering and Science

|

2023

|

Vol. 30, no. 3

263--276

EN

Dynamic hand gestures attract great interest and are utilized in different fields. Amongthese, man-machine interaction is an interesting area that makes use of the hand to providea natural way of interaction between them. A dynamic hand gesture recognition system isproposed in this paper, which helps to perform control operations in applications such asmusic players, video games, etc. The key motivation of this research is to provide a simple, touch-free system for effortless and faster human-computer interaction (HCI). As thisproposed model employs dynamic hand gestures, HCI is achieved by building a modelwith a convolutional neural network (CNN) and long short-term memory (LSTM) net-works. CNN helps in extracting important features from the images and LSTM helpsto extract the motion information between the frames. Various models are constructedby differing the LSTM and CNN layers. The proposed system is tested on an existing EgoGesture dataset that has several classes of gestures from which the dynamic gesturesare utilized. This dataset is used as it has more data with a complex background, actionsperformed with varying speeds, lighting conditions, etc. This proposed hand gesture recognition system attained an accuracy of 93%, which is better than other existing systemssubject to certain limitations.

6

Data-driven virtual sensor for powertrains based on transfer learning

Karhinen Aku, Hämäläinen Aleksanteri, Manngård Mikael, Miettinen Jesse, Viitala Raine

Bulletin of the Polish Academy of Sciences. Technical Sciences

|

2023

|

Vol. 71, nr 6

art. no. e147061

EN

Variation in powertrain parameters caused by dimensioning, manufacturing and assembly inaccuracies may prevent model-based virtual sensors from representing physical powertrains accurately. Data-driven virtual sensors employing machine learning models offer a solution for including variations in the powertrain parameters. These variations can be efficiently included in the training of the virtual sensor through simulation. The trained model can then be theoretically applied to real systems via transfer learning, allowing a data-driven virtual sensor to be trained without the notoriously labour-intensive step of gathering data from a real powertrain. This research presents a training procedure for a data-driven virtual sensor. The virtual sensor was made for a powertrain consisting of multiple shafts, couplings and gears. The training procedure generalizes the virtual sensor for a single powertrain with variations corresponding to the aforementioned inaccuracies. The training procedure includes parameter randomization and random excitation. That is, the data-driven virtual sensor was trained using data from multiple different powertrain instances, representing roughly the same powertrain. The virtual sensor trained using multiple instances of a simulated powertrain was accurate at estimating rotating speeds and torque of the loaded shaft of multiple simulated test powertrains. The estimates were computed from the rotating speeds and torque at the motor shaft of the powertrain. This research gives excellent grounds for further studies towards simulation-to-reality transfer learning, in which a virtual sensor is trained with simulated data and then applied to a real system.

7

How many neurons are needed to make a short-term prediction of the Bitcoin exchange rate?

Frontczak Michał, Hachaj Tomasz

Technical Transactions

|

2022

|

Vol. 119, iss. 1

art. no. e2022011

EN

The goal of our work was to select a neural network architecture that would give the best prediction of the Bitcoin exchange rate using historical data. Our work fits into the very important topic of predicting the value of the cryptocurrency exchange rate, and makes use of recent data which, as a result of the high Bitcoin exchange rate dynamics of the last year, differs significantly from those of previous years. We propose and test a number of neural network-based architectures and conduct a discussion of the results. Unlike previous state of-the-art works, we conducted a comprehensive comparison of three different neural network-based models: MLP (multilayer perceptron), LSTM (long short-term memory) and CNN (convolutional neural network). We tested them for a wide range of parameters. The results we present are, to the best of our knowledge, the most up to date when it comes to the application of artificial intelligence methods for the prediction of cryptocurrency exchange rates. The best-performing architectures were used for a website that gives real-time predictions of the Bitcoin exchange rate. The website is available at http://stpbtc-ii.up.krakow.pl/. Source codes of our research are available to download in order to make our experiment reproducible.

PL

Celem naszej pracy było stworzenie architektury sieci neuronowej, która przy wykorzystaniu danych historycznych pozwalałaby na dokładną predykcję kursu Bitcoin. Nasza praca wpisuje się w bardzo ważny temat przewidywania wartości kursu kryptowaluty. Niemniej istotny jest fakt, że w naszej pracy wykorzystujemy najnowsze dane, które z powodu dużej dynamiki kursu Bitcoin w ostatnim roku znacznie różnią się od danych z lat wcześniejszych. Proponujemy i testujemy kilka architektur opartych na sieciach neuronowych oraz przeprowadzamy dyskusję wyników. W odróżnieniu od poprzednich prac, przeprowadzamy wszechstronne porównanie trzech różnych modeli opartych na sieciach neuronowych: MLP (multilayer perceptron), LSTM (long short-term memory) i CNN (convolutional neural network). Przetestowaliśmy je dla szerokiego zakresu parametrów. Przedstawione przez nas wyniki są, według naszej wiedzy, najbardziej aktualnymi, jeśli chodzi o zastosowanie metod sztucznej inteligencji do przewidywania kursów kryptowalut. Najlepiej działająca architektura została wykorzystana na stronie internetowej, która w czasie rzeczywistym prognozuje kurs Bitcoina. Strona ta jest dostępna pod adresem http://stpbtc-ii.up.krakow.pl/. Kody źródłowe naszych badań są dostępne do pobrania w celu umożliwienia odtworzenia naszego eksperymentu.

8

Missing Precipitation Data Estimation Using Long Short-Term Memory Deep Neural Networks

Djerbouai Salim

Journal of Ecological Engineering

|

2022

|

Vol. 23, nr 5

216--225

EN

Due to the spatiotemporal variability of precipitation and the complexity of physical processes involved, missing precipitation data estimation remains as a significant problem. Algeria, like other countries in the world, is affected by this problem. In the present paper, Long Short-Term Memory (LSTM) deep neural Networks model was tested to estimate missing monthly precipitation data. The application was presented for the K'sob basin, Algeria. In the present paper, the optimal architecture of LSTM model was adjusted by trial-and-error-procedure. The LSTM model was compared with the most widely used classical methods including inverse distance weighting method (IDWM) and the coefficient of correlation weighting method (CCWM). Finally, it was concluded that the LSTM model performed better than the other methods.

9

Detection and Localization of Audio Event for Home Surveillance Using CRNN

Suruthhi V. S., Smita V., Rolant Gini J., Ramachandran K. I.

International Journal of Electronics and Telecommunications

|

2021

|

Vol. 67, No. 4

735--741

EN

Safety and security have been a prime priority in people’s lives, and having a surveillance system at home keeps people and their property more secured. In this paper, an audio surveillance system has been proposed that does both the detection and localization of the audio or sound events. The combined task of detecting and localizing the audio events is known as Sound Event Localization and Detection (SELD). The SELD in this work is executed through Convolutional Recurrent Neural Network (CRNN) architecture. CRNN is a stacked layer of convolutional neural network (CNN), recurrent neural network (RNN) and fully connected neural network (FNN). The CRNN takes multichannel audio as input, extracts features and does the detection and localization of the input audio events in parallel. The SELD results obtained by CRNN with the gated recurrent unit (GRU) and with long short-term memory (LSTM) unit are compared and discussed in this paper. The SELD results of CRNN with LSTM unit gives 75% F1 score and 82.8% frame recall for one overlapping sound. Therefore, the proposed audio surveillance system that uses LSTM unit produces better detection and overall performance for one overlapping sound.

10

Comparing the effectiveness of Convolutional Neural Network and Long Short-Term Memory Network for Disaster Based Social Media Messages - Using Thunderstorm and Cyclone as Case Studies

Singla Annie, Agrawal Rajat, Linh Nguyen Thi Dieu

Annals of Computer Science and Information Systems

|

2021

|

Vol. 28

273--275

EN

We present a framework to ameliorate the classification of disaster-related social media messages. In the present work, we have incorporated the Convolutional Neural Network, and Long Short-Term Memory Network. To demonstrate the applicability and effectiveness of the proposed approach, it is applied to the thunderstorm and cyclone Fani dataset. The results indicate that CNN is better than the LSTM model with an accuracy score of 0.9999 (99.99%) and loss score of 0.0410. The output from the research study is helpful for disaster managers to make effective decisions on time.

11

Forecasting future values of time series using the lstm network on the example of currencies and WIG20 companies

Mróz Bartosz, Nowicki Filip

Zeszyty Naukowe. Telekomunikacja i Elektronika / Uniwersytet Technologiczno-Przyrodniczy w Bydgoszczy

|

2020

|

nr 24

13--30

EN

The article presents a comparison of the RNN, GRU and LSTM networks in predicting future values of time series on the example of currencies and listed companies. The stages of creating an application which is a implementation of the analyzed issue were also shown – the selection of networks, technologies, selection of optimal network parameters. Additionally, two conducted experiments were discussed. The first was to predict the next values of WIG20 companies, exchange rates and cryptocurrencies. The second was based on investments in cryptocurrencies guided solely by the predictions of artificial intelligence. This was to check whether the investments guided by the predictions of such a program have a chance of effective earnings. The discussion of the results of the experiment includes an analysis of various interesting phenomena that occurred during its duration and a comprehensive presentation of the relatively high efficiency of the proposed solution, along with all kinds of graphs and comparisons with real data. The difficulties that occurred during the experiments, such as coronavirus or socio-economic events, such as riots in the USA, were also analyzed. Finally, elements were proposed that should be improved or included in future versions of the solution – taking into account world events, market anomalies and the use of supervised learning.

PL

W artykule przedstawiono porównanie sieci RNN, GRU i LSTM w przewidywaniu przyszłych wartości szeregów czasowych na przykładzie walut i spółek giełdowych. Przedstawiono również etapy tworzenia aplikacji będącej realizacją analizowanego zagadnienia – dobór sieci, technologii, dobór optymalnych parametrów sieci. Dodatkowo omówiono dwa przeprowadzone eksperymenty. Pierwszym było przewidywanie kolejnych wartości spółek z WIG20, kursów walut i kryptowalut. Drugi opierał się na inwestycjach w kryptowaluty, kierując się wyłącznie przewidywaniami sztucznej inteligencji. Miało to na celu sprawdzenie, czy inwestowanie na podstawie przewidywania takiego programu pozwala na efektywne zarobki. Omówienie wyników eksperymentu obejmuje analizę różnych ciekawych zjawisk, które wystąpiły w czasie jego trwania oraz kompleksowe przedstawienie relatywnie wysokiej skuteczności proponowanego rozwiązania wraz z wszelkiego rodzaju wykresami i porównaniami z rzeczywistymi danymi. Analizowano również trudności, które wystąpiły podczas eksperymentów, takie jak koronawirus, wydarzenia społeczno-gospodarcze czy zamieszki w USA. Na koniec zaproponowano elementy, które należałoby ulepszyć lub uwzględnić w przyszłych wersjach rozwiązania, uwzględniając wydarzenia na świecie, anomalie rynkowe oraz wykorzystanie uczenia się nadzorowanego.

12

Analysis and Forecasting of the Primary Energy Consumption in Poland Using Deep Learning

Manowska Anna

Inżynieria Mineralna

|

2020

|

no. 1, vol. 1

217--222

EN

Consumption of fossil energy resources were increased dramatically, due to the economic and population growth. In turn, the consumption of fossil resources causes depletion of resources and contributes to environmental pollution. The European Union's "climate neutrality" initiative requires effective energy management from the member states. By this is meant a resource-efficient and competitive economy in which there is no greenhouse gas emission and where economic growth is decoupled from resource consumption. The article analyzes the level of primary energy consumption in Poland. It was examined whether a 23% drop in energy consumption could be achieved in 2030 compared to the base year and according with energy efficiency assumptions. A methodology for forecasting primary energy consumption based on deep neural networks, in particular on Long Short Term Memory (LSTM) algorithms was also presented.

PL

Zużycie kopalnych surowców energetycznych wzrasta, a wzrost ten jest skorelowany ze wzrostem ludności i rozwojem gospodarczym. Z kolei zużycie kopalnych surowców energetycznych powoduje wyczerpywanie się zasobów i przyczynia się do zanieczyszczenia środowiska. Inicjatywa Unii Europejskiej "neutralność klimatyczna" wymaga od państw członkowskich efektywnego zarządzania energią. Przez co rozumie się zasobooszczędną i konkurencyjną gospodarką, w której nie ma emisji netto gazów cieplarnianych i gdzie wzrost gospodarczy jest oddzielony od zużycia zasobów. W artykule przeanalizowano poziom zużycia energii pierwotnej w Polsce. Zbadano, czy w roku 2030 uda się osiągnąć 23% spadek konsumpcji energii w odniesieniu do roku bazowego, zgodnie z przyjętymi założeniami o efektywności energetycznej. Przedstawiono również metodologię prognozowania zużycia energii pierwotnej opartą na głębokich sieciach neuronowych, w szczególności na algorytmach Long Short Term Memory (LSTM).

13

Human activity recognition using improved complete ensemble EMD with adaptive noise and long short-term memory neural networks

Altuve Miguel, Lizarazo Paula, Villamizar Javier

Biocybernetics and Biomedical Engineering

|

2020

|

Vol. 40, no. 3

901--909

EN

The recognition of human activities is a topic of great relevance due to its wide range of applications. Different approaches have been proposed to recognize human activities, ranging from the comparison of signals with thresholds to the application of deep and machine learning techniques. In this work, the classification of six human activities (walking, walking downstairs, walking upstairs, standing, sitting, and lying down) is performed using bidirectional LSTM networks that exploit intrinsic mode function (IMF) representation of inertial signals. Records with inertial signals (accelerometer and gyroscope) of 2.56 s, available at the UCI Machine Learning Repository, were collected from 30 subjects using a smartphone. First, inertial signals were standardized to take them to the same scale and were decomposed into IMF using the improved complete ensemble empirical mode decomposition with adaptive noise (ICEEMDAN). IMF were then segmented (split) into nine segments of 1.28 s with 12.5% overlap and introduced to a first network with four outputs to identify the dynamic activities and the statics as a single class called ‘‘statics’’, giving 98.86% accuracy. Then, the non-segmented IMF of the records assigned to the statics class were introduced to a second network to classify their three activities, giving an accuracy of 88.46%. In total, 92.91% accuracy was obtained to classify the six human activities. This performance is because ICEEMDAN allowed the extraction of information that was embedded in the signal, and the segmentation of the IMF allowed the network to discriminate between static and dynamic activities.

14

A novel deep LSTM network for artifacts detection in microelectrode recordings

Hosny Mohamed, Zhu Minwei, Gao Wenpeng, Fu Yili

Biocybernetics and Biomedical Engineering

|

2020

|

Vol. 40, no. 3

1052--1063

EN

Microelectrode recording (MER) signals are world-widely used for validating the planned trajectories in the procedure of deep brain stimulation (DBS) surgery to obtain accurate position of electrodes inside the brain structure. Besides, MER signals are important source for studying extracellular neuronal activity and DBS biomarkers, such as, spike clustering and sorting. However, MER signals are prone to several artifacts derived from electrical equipment in the operating room, electrode movement and patient activities, etc., which reduce the signal-to-noise ratio of the MER signals. Therefore, in this paper, we propose a novel deep learning architecture based on long short-term memory (LSTM) network for automatic artifact detection in MER signals. Frequency and time-domain features were extracted from the raw MER signals and fed to the deep LSTM network. A manually annotated MER database obtained from 17 Parkinson's disease (PD) patients were used to validate the proposed architecture. The proposed architecture achieved promising results of 97.49% accuracy, 98.21% sensitivity and 96.87% specificity on an unseen test set. To our best knowledge, this is the first study to use LSTM network for artifacts detection in MER signals. The MER data will be available at http://homepage.hit.edu.cn/wpgao.

15

Shallow, Deep, Ensemble models for Network Device Workload Forecasting

Liu Cenru

Annals of Computer Science and Information Systems

|

2020

|

Vol. 21

101--104

EN

Reliable prediction of workload-related characteristics of monitored devices is important and helpful for management of infrastructure capacity. This paper presents 3 machine learning models (shallow, deep, ensemble) with different complexity for network device workload forecasting. The performance of these models have been compared using the data provided in FedCSIS'20 Challenge. The R2 scores achieved from the cascade Support Vector Regression (SVR) based shallow model, Long short-term memory (LSTM) based deep model, and hierarchical linear weighted ensemble model are 0.2506, 0.2831, and 0.3059, respectively, and was ranked 3rd place in the preliminary stage of the challenges.

16

Deep Bi-Directional LSTM Networks for Device Workload Forecasting

Ruta Dymitr, Cen Ling, Vu Quang Hieu

Annals of Computer Science and Information Systems

|

2020

|

Vol. 21

115--118

EN

Deep convolutional neural networks revolutionized the area of automated objects detection from images. Can the same be achieved in the domain of time series forecasting? Can one build a universal deep network that once trained on the past would be able to deliver accurate predictions reaching deep into the future for any even most diverse time series? This work is a first step in an attempt to address such a challenge in the context of a FEDCSIS'2020 Competition dedicated to network device workload prediction based on their historical time series data. We have developed and pre-trained a universal 3-layer bi-directional Long-Short-Term-Memory (LSTM) regression network that reported the most accurate hourly predictions of the weekly workload time series from the thousands of different network devices with diverse shape and seasonality profiles. We will also show how intuitive human-led post-processing of the raw LSTM predictions could easily destroy the generalization abilities of such prediction model.

17

Urban sound classification using long short-term memory neural network

Lezhenin Iurii, Bogach Natalia, Pyshkin Evgeny

Annals of Computer Science and Information Systems

|

2019

|

Vol. 18

57--60

EN

Environmental sound classification has received more attention in recent years. Analysis of environmental sounds is difficult because of its unstructured nature. However, the presence of strong spectro-temporal patterns makes the classification possible. Since LSTM neural networks are efficient at learning temporal dependencies we propose and examine a LSTM model for urban sound classification. The model is trained on magnitude mel-spectrograms extracted from UrbanSound8K dataset audio. The proposed network is evaluated using 5-fold cross-validation and compared with the baseline CNN. It is shown that the LSTM model outperforms a set of existing solutions and is more accurate and confident than the CNN.