Short-term Memory Algorithm Research Articles

Application of Long Short-Term Memory (LSTM) in Stock Price Prediction

No doubt, the stock market has been one of the most volatile and this makes it very difficult to carry out forecast or prediction about the movement in share prices. However, the advent of machine learning is gradually changing the narratives as there are a number of neural networks which could be used to develop models to effectively predict the stock prices. This study examined the application of Long Short-Term Memory algorithms in predicting stock prices using time series data on Apple shares from 2017 to 2022. The closing price of the stocks was adopted and the data split into 98% for training and 2% for test because the study only wanted to make prediction for the last 20 days. TensorFlow together with its subset Keras libraries were employed with other libraries like Dropout for regularization and sklearn for normalization. NumPy to build array, pandas for data analysis were also imported with matplotlib for the purpose of plotting the result graph. The LSTM model was trained to learn from the sequential data and predict the share price. The outcome revealed that the machine learnt very effectively and has a predictive ability for share prices. The model was able to predict the trend or pattern in prices almost accurately.

Effective Facial Expression Recognition System Using Machine Learning

The co Facial expression recognition (FER) is a topic that has seen a lot of study in computer vision and machine learning. In recent years, deep learning techniques have shown remarkable progress on FER tasks. With this abstract, A Novel Is Advised By Us FER method that combines combined use of k-nearest neighbours and long short-term memory algorithms better efficiency and accurate facial expression recognition. The proposed system features two primary steps—feature extraction and classification—to get results. When extracting features, we extract features from the facial images using the Local Binary Patterns (LBP) algorithm. LBP is a simple yet powerful feature extraction technique that captures texture information from the image. In the classification stage, we use the KNN and LSTM algorithms for facial expression recognition. KNN is a simple and effective classification algorithm that finds the k closest to the given value neighbours to the test training-set-sample and assigning it to the class that is most frequent among its neighbours. However, KNN has limitations in handling temporal information. To address this limitation, we propose to use LSTM, which is a subclass of RNNs capable of capturing temporal relationships in time series data. The LSTM network takes as input the LBP features of a sequence of facial images and processes them through a series of LSTM cells to estimate the ultimate coding of the phrase. We examine the planned and system on two publicly available records: the CK+ and the Oulu-CASIA datasets. According on the experimental findings, the proposed system achieves performance at the cutting edge on both datasets. The proposed system performs better than other state-of-the-art methods, including those that use deep learning systems, quantitatively, in terms of F1-score and precision.In conclusion, the proposed FER system that combines KNN and LSTM algorithms achieves high accuracy and an F1 score in recognising facial expressions from sequences of images. This system can be used in many contexts, including human-computer interaction, emotion detection, and behaviour analysis.

A proposed reconstruction method of a 3D animation scene based on a fuzzy long and short-term memory algorithm.

With the development of computer technology leading to a broad range of virtual technology implementations, the construction of virtual tasks has become highly demanded and has increased rapidly, especially in animation scenes. Constructing three-dimensional (3D) animation characters utilizing properties of actual characters could provide users with immersive experiences. However, a 3D face reconstruction (3DFR) utilizing a single image is a very demanding operation in computer graphics and vision. In addition, limited 3D face data sets reduce the performance improvement of the proposed approaches, causing a lack of robustness. When datasets are large, face recognition, transformation, and animation implementations are relatively practical. However, some reconstruction methods only consider the one-to-one processes without considering the correlations or differences in the input images, resulting in models lacking information related to face identity or being overly sensitive to face pose. A face model composed of a convolutional neural network (CNN) regresses 3D deformable model coefficients for 3DFR and alignment tasks. The manuscript proposes a reconstruction method for 3D animation scenes employing fuzzy LSMT-CNN (FLSMT-CNN). Multiple collected images are employed to reconstruct 3D animation characters. First, the serialized images are processed by the proposed method to extract the features of face parameters and then improve the conventional deformable face modeling (3DFDM). Afterward, the 3DFDM is utilized to reconstruct animation characters, and finally, high-precision reconstructions of 3D faces are achieved. The FLSMT-CNN has enhanced both the precision and strength of the reconstructed 3D animation characters, which provides more opportunities to be applied to other animation scenes.

ANALISIS SENTIMEN VAKSIN COVID-19 PADA TWITTER MENGGUNAKAN RECURRENT NEURAL NETWORK (RNN) DENGAN ALGORITMA LONG SHORT-TERM MEMORY (LSTM)

The Coronavirus, also known as the Covid-19 pandemic, has reached every country worldwide, including Indonesia. Covid-19 is still prevalent and has killed many people in Indonesia. This makes it impossible to stop Covid-19 from spreading. The government's attempt to stop the Covid-19 pandemic is acquiring the vaccine. The administration of the Covid-19 vaccine has generated much discussion on social media, particularly Twitter. Tweets displaying public opinion on Twitter can be used for sentiment analysis and categorizing public opinion on the Covid-19 vaccine. 20,000 tweets were collected by Twitter crawling between January 10 and January 15, 2022. 3.290 tweets were left after pre-processing and meaningless tweets were eliminated. The data were processed using the Recurrent Neural Network method with the Long Short-Term Memory algorithm to determine its accuracy and identify topics often discussed by the public on Twitter. The LSTM method is capable of storing old information/data. A model with 70% training data, a learning rate of 0.01, 100 LSTM units, 32 batch sizes, 100 epochs, a cross-entropy loss function, and Adam optimizers was used to build the classification in this study. The accuracy value obtained from the performance evaluation of the Long Short-Term Memory model research was 80.34%.

Diagnosis of Multiple Open-Circuit Faults in Three-Phase Induction Machine Drive Systems Based on Bidirectional Long Short-Term Memory Algorithm

Availability and continuous operation under critical conditions are very important in electric machine drive systems. Such systems may suffer from several types of failures that affect the electric machine or the associated voltage source inverter. Therefore, fault diagnosis and fault tolerance are highly required. This paper presents a new robust deep learning-based approach to diagnose multiple open-circuit faults in three-phase, two-level voltage source inverters for induction-motor drive applications. The proposed approach uses fault-diagnosis variables obtained from the sigmoid transformation of the motor stator currents. The open-circuit fault-diagnosis variables are then introduced to a bidirectional long short-term memory algorithm to detect the faulty switch(es). Several simulation and experimental results are presented to show the proposed fault-diagnosis algorithm’s effectiveness and robustness.

Predicting Hypoxia Using Machine Learning: Systematic Review.

Hypoxia is an important risk factor and indicator for the declining health of inpatients. Predicting future hypoxic events using machine learning is a prospective area of study to facilitate time-critical interventions to counter patient health deterioration. This systematic review aims to summarize and compare previous efforts to predict hypoxic events in the hospital setting using machine learning with respect to their methodology, predictive performance, and assessed population. A systematic literature search was performed using Web of Science, Ovid with Embase and MEDLINE, and Google Scholar. Studies that investigated hypoxia or hypoxemia of hospitalized patients using machine learning models were considered. Risk of bias was assessed using the Prediction Model Risk of Bias Assessment Tool. After screening, a total of 12 papers were eligible for analysis, from which 32 models were extracted. The included studies showed a variety of population, methodology, and outcome definition. Comparability was further limited due to unclear or high risk of bias for most studies (10/12, 83%). The overall predictive performance ranged from moderate to high. Based on classification metrics, deep learning models performed similar to or outperformed conventional machine learning models within the same studies. Models using only prior peripheral oxygen saturation as a clinical variable showed better performance than models based on multiple variables, with most of these studies (2/3, 67%) using a long short-term memory algorithm. Machine learning models provide the potential to accurately predict the occurrence of hypoxic events based on retrospective data. The heterogeneity of the studies and limited generalizability of their results highlight the need for further validation studies to assess their predictive performance.

An intelligent dual-sensing e-skin system for pressure and temperature detection using laser-induced graphene and polydimethylsiloxane

Motivated by artificial intelligence, we present a novel electronic skin (e-skin) system capable of dual-sensing pressure and temperature signals. Our approach utilizes laser-induced graphene and polydimethylsiloxane, offering a simple yet efficient method for e-skin preparation. Experimental results reveal exceptional performance with good pressure sensitivity (0.037 kPa−1 at 0–50 kPa), a wide detection range (0–220 kPa), a fast response time of 56 ms, an ultra-low detection limit (30 Pa), and excellent stability (8000 cycles). Additionally, the e-skin exhibits positive temperature coefficients (0.0025 ℃-1) within 20–100 ℃, a rapid response time of 2.57 s, an extremely low detection limit (1 ℃), and stability after 50 cycles. Crucially, our intelligent e-skin system, employing a Long Short-Term Memory algorithm, enables real-time multi-modal tactile perception, accurately separating mixed pressure and temperature signals. This versatile technology holds immense potential for applications in intelligent robotics and human health monitoring.

Electricity demand error corrections with attention bi-directional neural networks

Reliable forecast of electricity demand is crucial to stability, supply, and management of electricity grids. Short-term hourly and sub-hourly demand forecasts are difficult due to the stochastic nature of electricity demand. To improve the electricity demand forecasts, artificial neural networks are combined with attention-based bi-directional neural network as well as Error Correction methods, and Bayesian hyperparameter optimizations. As part of the hybrid VMD-CABLSTM-ANN-EC model, the intrinsic mode functions, representing distinct predictive features, are separated from electricity demand data using variational mode decomposition algorithm. For predicting each intrinsic mode function and respective error time series, convolutional neural networks-bi-directional long short-term memory algorithms are applied. In a second stage, error time series are split, followed by a model to predict the error series’ intrinsic mode functions, and a final integration stage to predict the error. The results of the proposed VMD-CABLSTM-ANN-EC model are benchmarked against decomposition-based and standalone models at substations in Queensland, Australia. The proposed VMD-CABLSTM-ANN-EC model outperformed all benchmark models. By splitting the predictor and target variables, it will be shown that the variational model decomposition method improves error corrections by revealing key features of historical demand data. Using error correction method in short-term electricity demand modelling can provide greater confidence in the prediction of electricity demand. The models can be used by energy providers for market analysis and insight research, to manage power failure risk, and make financial decisions.

Rainfall rate prediction using recurrent neural network with long short-term memory algorithm: Iraq case study

Rainfall rate prediction using recurrent neural network with long short-term memory algorithm: Iraq case study

Rainfall rate prediction using recurrent neural network with long short-term memory algorithm: Iraq case study

Rainfall rate prediction using recurrent neural network with long short-term memory algorithm: Iraq case study

A Hybrid Extreme Gradient Boosting and Long Short-Term Memory Algorithm for Cyber Threats Detection

The vast amounts of data, lack of scalability, and low detection rates of traditional intrusion detection technologies make it impossible to keep up with evolving and increasingly sophisticated cyber threats. Therefore, there is an urgent need to detect and stop cyber threats early. Deep Learning has greatly improved intrusion detection due to its ability to self-learn and extract highly accurate features. In this paper, a Hybrid XG Boosted and Long Short-Term Memory algorithm (HXGBLSTM) is proposed. A comparative analysis is conducted between the computational performance of six established evolutionary computation algorithms and the recently developed bio-inspired metaheuristic algorithm called Zebra Optimisation Algorithm. These algorithms include the Particle Swarm Optimisation Algorithm, the Bio-inspired Algorithms, Bat Optimisation Algorithm, Firefly Optimisation Algorithm, and Monarch Butterfly Optimisation Algorithm, as well as the Genetic Algorithm as an Evolutionary Algorithm. The dimensionality curse has been mitigated by using these metaheuristic methods for feature selection, and the results are compared with the wrapper-based feature selection XGBoost algorithm. The proposed algorithm uses the CSE-CIC -IDS2018 dataset, which contains the latest network attacks. XGBoost outperformed the other FS algorithms and was used as the feature selection algorithm. In evaluating the effectiveness of the newly proposed HXGBLSTM, binary and multi-class classifications are considered. When comparing the performance of the proposed HXGBLSTM for cyber threat detection, it outperforms seven innovative deep learning algorithms for binary classification and four of them for multi-class classification. Other evaluation criteria such as recall, F1 score, and precision have been also used for comparison. The results showed that the best accuracy for binary classification is 99.8\%, with F1-score of 99.83\%, precision of 99.85\%, and recall of 99.82\%, in extensive and detailed experiments conducted on a real dataset. The best accuracy, F1-score, precision, and recall for multi-class classification were all around 100\%, which does give the proposed algorithm an advantage over the compared ones.

Improving forecasting model for fuzzy time series using the Self-updating clustering and Bi-directional Long Short Term Memory algorithm

This paper proposes a new model for creating fuzzy time series and conducting future forecasts using the Bi-directional Long Short-term Memory model (Bi-LSTM). This study contributes by using both classical machine learning and deep learning techniques. Firstly, a self-updating clustering algorithm is used to determine the optimal number of clusters for time series. Secondly, the study describes a method for determining the fuzzy relationship between elements of time series and the identified clusters. Thirdly, the developed model creates the fuzzy time series based on the established rules. Finally, forecasting for the future value using the Bi-LSTM model with some improvement in optimizing the parameters and increasing the accuracy of forecasting result. The steps of the proposed model are clearly illustrated by a numerical example. Moreover, this model also tested on various datasets, including M3, M4, and M5 datasets. By evaluating its performance using parameters such as sMAPE and RMSSE, the proposed model has shown significant enhancements when compared to existing models. Additionally, the model’s effectiveness is further demonstrated through its successful application in forecasting the VN index stock in Vietnam.

Analyzing Sentiment with Self-Organizing Map and Long Short-Term Memory Algorithms

This research delves into the impact of Chat Generative Pre-trained Transformer, one of Open Artificial Intelligence Generative Pretrained Transformer models. This model underwent extensive training on a vast corpus of internet text to gain insights into the mechanics of human language and its role in forming phrases, sentences, and paragraphs. The urgency of this inquiry arises from Chat Generative Pre-trained Transformer emergence, which has stirred significant debate and captured widespread attention in both research and educational circles. Since its debut in November 2022, Chat Generative Pre-trained Transformer has demonstrated substantial potential across numerous domains. However, concerns voiced on Twitter have centered on potential negative consequences, such as increasedforgery and misinformation. Consequently, understanding public sentiment toward Chat Generative Pre-trained Transformer technology through sentiment analysis has become crucial. The research’s primary objective is to conduct Sentiment Analysis Classification of Chat Generative Pre-trained Transformer regarding public opinions on Twitter in Indonesia. This goal involves quantifying and categorizing public sentiment from Twitter’s vast data pool into three clusters: positive, negative, or neutral. In the data clustering stage, the Self-Organizing Map technique is used. After the text data has been weighted and clustered, the next step involves using the classification technique with LongShort-Term Memory to determine the public sentiment outcomes resulting from the presence of Chat Generative Pre-trained Transformer technology. Rigorous testing has demonstrated the robust performance of the model, with optimal parameters: relu activation function, som size of 5, num epoch som and num epoch lstm both at 128, yielding an impressive 95.07% accuracy rate.

Smart nano generation of transgenic algae expressing white spot syndrome virus in shrimps for inner ear-oral infection treatments using the spotted hyena optimizer (SHO)-Long short-term memory algorithm

Nanotechnology offers a promising avenue to amplify the effectiveness and precision of using transgenic algae in managing WSSV in shrimp by possibly crafting nano-carriers for targeted therapeutic agent delivery or modifying algae cells at a molecular level. Leveraging the capabilities of nano-scale interventions, this study could explore innovative means to manipulate cellular processes, control biological interactions, and enhance treatment efficacy while minimizing undesirable impacts in aquatic environments. The White Spot Syndrome Virus (WSSV) is a double-stranded DNA virus with a tail and rod form that belongs to theNimaviridaefamily. There is no workable way to manage this illness at the moment. This research proposes a new model based on the Long Short-Term Memory (LSTM) and Spotted Hyena Optimizer (SHO) method to control the inner ear-oral infection, utilizing transgenic algae (Chlamydomonas reinhardtii). It is pretty tricky to modify the weight matrix in LSTM. The output will be more accurate if the weight of the neurons is exact. Histological examinations and nested polymerase chain reaction (PCR) testing were performed on the challenged shrimp every 4 h to assess the degree of white spot disease. The SHO-LSTM has shown the highest accuracy and Roc value (98.12% and 0.93, respectively) and the lowest error values (MSE = 0.182 and MAE = 0.48). The hybrid optimized model improves the overall inner ear-oral linked neurological diseases detection ratio. Additionally, with the slightest technical complexity, it effectively controls the forecast factors required to anticipate the ENT. Algal cells were found to be particularly well-suited for inner ear-oral infections, and shrimps fed a transgenic line had the best survival ratio in WSSV infection studies, with 87% of the shrimp surviving. This shows that using this line would effectively stop the spread of WSSV in shrimp populations.

The application of Long Short-Term Memory algorithm in American multinational technology company stock prediction

The fast development in American multinational technology companies has attracted both professional and new investors to buy the stocks. However, the price of these companies are unstable and therefore hard to be predicted. The focus of this article is to use AI and deep learning algorithms to find a pattern of the stock price. Long Short-Term Memory Algorithm (LSTM) is the main algorithm used to predict the trend, and other methods including Autoregressive integrated moving average (ARIMA), Seasonal autoregressive integrated moving average (SARIMA), and prophet are also discussed in this piece.

Coordination control strategy for PEM fuel cell system considering vehicle velocity prediction information

Accurate air supply and stable temperature control are important factors to ensure fuel cell safety and high efficiency. In automotive applications, frequent load changes challenge the air supply and thermal management systems of fuel cells. In this paper, a coordination model predictive control strategy based on velocity prediction is proposed to regulate the oxygen excess ratio and stack temperature to improve the fuel cell system efficiency. First, the impact of load current, temperature and oxygen excess ratio on the efficiency is analyzed to obtain the optimal control reference. Then, the future velocity information is predicted by the long short term memory algorithm and integrated into the disturbance sequences. Optimal control trajectory obtained by collaborative optimization of the global objective function for sub-controllers. Finally, the impact of parameters on control performance is analyzed, and the effectiveness of the coordination control strategy is verified under the combined driving condition. The results show that the proposed method can reduce the oxygen excess ratio and temperature control errors by 13.8% and 4.5% compared to the control algorithm without velocity prediction. In addition, the system efficiency is increased by 1.15% due to the introduction of the optimal control reference.

Forest Sound Event Detection with Convolutional Recurrent Neural Network-Long Short-Term Memory

Sound event detection tackles an audio environment's complex sound analysis and recognition problem. The process involves localizing and classifying sounds mainly to estimate the start point and end points of the separate sounds and describe each sound. Sound event detection capability relies on the type of sound. Although detecting sequences of distinct temporal sounds is straightforward, the situation becomes complex when the sound is multiple overlapping of much single audio. This situation usually occurs in the forest environment. Therefore, this aim of the paper is to propose a Convolution Recurrent Neural Network-Long Short-Term Memory algorithm to detect an audio signature of intruders in the forest environment. The audio is extracted in the Mel-frequency cepstrum coefficient and fed into the algorithm as an input. Six sound categories are chainsaw, machete, car, hatchet, ambiance, and bike. They were tested using several epochs, batch size, and filter of the layer in the model. The proposed model can achieve an accuracy of 98.52 percent in detecting the audio signature with a suitable parameter selection. In the future, additional types of audio signatures of intruders and further aspects of evaluation can be added to make the algorithm better at detecting intruders in the forest environment.

Lab: an R package for generating analysis-ready data from laboratory records.

Electronic health records (EHRs) play a crucial role in healthcare decision-making by giving physicians insights into disease progression and suitable treatment options. Within EHRs, laboratory test results are frequently utilized for predicting disease progression. However, processing laboratory test results often poses challenges due to variations in units and formats. In addition, leveraging the temporal information in EHRs can improve outcomes, prognoses, and diagnosis predication. Nevertheless, the irregular frequency of the data in these records necessitates data preprocessing, which can add complexity to time-series analyses. To address these challenges, we developed an open-source R package that facilitates the extraction of temporal information from laboratory records. The proposed lab package generates analysis-ready time series data by segmenting the data into time-series windows and imputing missing values. Moreover, users can map local laboratory codes to the Logical Observation Identifier Names and Codes (LOINC), an international standard. This mapping allows users to incorporate additional information, such as reference ranges and related diseases. Moreover, the reference ranges provided by LOINC enable us to categorize results into normal or abnormal. Finally, the analysis-ready time series data can be further summarized using descriptive statistics and utilized to develop models using machine learning technologies. Using the lab package, we analyzed data from MIMIC-III, focusing on newborns with patent ductus arteriosus (PDA). We extracted time-series laboratory records and compared the differences in test results between patients with and without 30-day in-hospital mortality. We then identified significant variations in several laboratory test results 7 days after PDA diagnosis. Leveraging the time series-analysis-ready data, we trained a prediction model with the long short-term memory algorithm, achieving an area under the receiver operating characteristic curve of 0.83 for predicting 30-day in-hospital mortality in model training. These findings demonstrate the lab package's effectiveness in analyzing disease progression. The proposed lab package simplifies and expedites the workflow involved in laboratory records extraction. This tool is particularly valuable in assisting clinical data analysts in overcoming the obstacles associated with heterogeneous and sparse laboratory records.

Detection of Anomalies in Additively Manufactured Metal Parts Using CNN and LSTM Networks

The process of metal additive manufacturing (AM) involves creating strong, complex components by using fine metal powders. Extensive use of AM methods is expected in near future for the production of small and medium-sized batches of end-use products and tools. The ability to detect loads and defects would enable AM components to be used in critical applications and improve their value. In this study, the Surface Response to Excitation (SuRE) method was used to investigate wave propagation characteristics and load detection on AM metallic specimens. With completely solid infills and the same geometry, three stainless steel test bars are produced: one conventionally and two additively. To investigate the effect of infills, four bars with the same geometries are 3D printed with triangular and gyroid infills with either 0.5 mm or 1 mm skin thickness. Two piezoelectric disks are attached to each end of the test specimens to excite the parts with guided waves from one end and monitor the dynamic response to excitation at the other end. The response to excitation was recorded when bars were in a relaxed condition and when compressive loads were applied at five levels in the middle of them. For converting time-domain signals into 2D time-frequency images, the Short-Time Fourier Transform (STFT) and Continuous Wavelet Transform (CWT) were implemented. To distinguish the data based on fabrication characteristics and level of loading, two deep learning models (Long Short-term Memory algorithm (LSTM) and Convolutional Neural Networks (2D CNN)) were utilized. Time-frequency images were used to train 2D CNN, while raw signal data was used to train LSTM. It was found that both LSTM and 2D CNN could estimate solid parts' loading level with an accuracy of more than 90%. In parts with infills, CNN outperformed LSTM for the classification of over five classes (internal geometry and loading level simultaneously).

Enhancement of Coronary Heart Disease Prediction using Stacked Long Short Term Memory

The high incidence of death caused by coronary heart disease has become a global concern in the world of health, where patients with coronary heart disease are no longer only adults and the elderly, yet there are now so many cases of coronary heart disease experienced by underage patients. As a result, it is critical to be able to prevent and reduce the number of instances. One of them is the ability to predict a person's risk of coronary heart disease so that patients can be treated and provided early therapy. The risk of coronary heart disease will be predicted in this study utilizing Stacked long short-term memory algorithms. By appling this algorithm, the accuracy of 81.3% from previous study can be increased to 91.8% by this study.