Audiovisual Analysis for Recognising Frustration during Game-Play: Introducing the Multimodal Game Frustration Database

This article explores the suitability of a long short-term memory recurrent neural network (LSTM-RNN) and artificial intelligence (AI) method for low-flow time series forecasting. The long short-term memory works on the sequential framework which considers all of the predecessor data. This forecasting method used daily discharged data collected from the Basantapur gauging station located on the Mahanadi River basin, India. Different metrics [root-mean-square error (RMSE), Nash–Sutcliffe efficiency (ENS), correlation coefficient (R) and mean absolute error] were selected to assess the performance of the model. Additionally, recurrent neural network (RNN) model is also used to compare the adaptability of LSTM-RNN over RNN and naive method. The results conclude that the LSTM-RNN model (R = 0.943, ENS = 0.878, RMSE = 0.487) outperformed RNN model (R = 0.935, ENS = 0.843, RMSE = 0.516) and naive method (R = 0.866, ENS = 0.704, RMSE = 0.793). The finding of this research concludes that LSTM-RNN can be used as new reliable AI technique for low-flow forecasting.

Remaining useful life prediction of PEMFC based on long short-term memory recurrent neural networks

In this paper, we propose a Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) and multiple kernel learning (MKL) based multi-modal affect recognition scheme (LSTM-MKL). It takes the LSTM-RNN advantage to model the long range dependencies between successive observations, and uses the MKL power to model the non-linear correlations between the inputs and outputs. For each of the affect dimensions (arousal, valence, expectancy, and power), two LSTM-RNN models are trained, one for each modality. In the recognition phase, the audio and visual features are input to the corresponding learned LSTM models, which in turn produce initial estimates of the affect dimensions. The LSTM outputs are further input into a multi-kernel support vector regression (MK-SVR) for the final recognition. Experimental results carried out on the AVEC2012 database, show that compared to the traditional SVR-LLR (Support Vector Machine - local linear regression) or MK-SVR fusion scheme, the proposed LSTM-MKL fusion scheme obtains higher recognition results, with an correlation coefficient (COR) of 0.354, compared to a COR of 0.124 for SVR-LLR, and 0.168 for MK-SVR, respectively.

Lithium battery packs are the main driving energy source for electric vehicles. A battery pack equalization charging solution using a constant current source for variable rate charging is presented in this paper. The charging system consists of a main constant current source and independent auxiliary constant current sources. Auxiliary constant current sources are controlled by the battery management system (BMS), which can change the current rate of the corresponding single battery, and achieve full charging of each single cell in the series battery pack. At the same time, the state of charge (SOC) is regarded as time series data to establish a long short-term memory recurrent neural network (LSTM-RNN) model, and it is possible to obtain the single battery with lower capacity, so that the charging efficiency and battery pack consistency can be improved. The experimental results show that the open circuit voltage difference between the single cells is less than 50 mV after the charging of 20 strings of lithium battery packs by using this method, which achieve the purpose of equalization charging.

With the evolution of network threat, identifying attack from both external and internal is getting more and more difficult. To detect both known and unknown malicious attacks, several machine learning algorithms are utilized. However, these algorithms have still some limitations such as high false positive and false alarm rate. To overcome above challenge, we propose a threat analysis method combined with kernel principal component analysis (PCA) and long short-term memory recurrent neural network (LSTM-RNN). To achieve high accurate detection rate, data preprocessing, feature extraction, attack detection is seamlessly integrated into an end-to-end detection method. To assess the method, the well-known NSL-KDD dataset has been used. Experimental results show that the proposed threat analysis method greatly outperforms several attack detection methods that use SVM, neural network or Bayesian methods.

Abstract: The rapid expansion of digital transactions has intensified the need for real-time fraud detection systems capable of identifying anomalous patterns with high accuracy. Traditional rule-based and classical machine learning approaches often fall short in handling the complex, high-dimensional, and sequential nature of transaction data. This study investigates the application of deep learning models—specifically Convolutional Neural Networks (CNNs) and Long Short-Term Memory Recurrent Neural Networks (LSTM-RNNs)—to detect fraudulent behavior in real-time transaction networks. Using the IEEE-CIS Fraud Detection dataset, comprising over 500,000 records, the models were evaluated based on accuracy, precision, recall, and F1-score. Data preprocessing included normalization, categorical encoding, and sequence transformation. The LSTM-RNN model demonstrated superior performance, achieving 96% accuracy and an F1-score of 0.945, significantly outperforming baseline models such as logistic regression and random forest. Regression analysis further validated the stability of predictions across various transaction features. The results highlight the effectiveness of sequence-aware deep learning models in capturing subtle fraud indicators and reducing false negatives. The study underscores the importance of combining high model accuracy with low latency and interpretability for deployment in financial security systems. Keywords: deep learning, fraud detection, real-time transactions, LSTM-RNN, CNN, financial security, anomaly detection, predictive modeling, sequential data, IEEE-CIS dataset

Remaining useful life (RUL) prognosis is one of the most important techniques in concrete structure health management. This technique evaluates the concrete structure strength through determining the advent of failure, which is very helpful to reduce maintenance costs and extend structure life. Degradation information with the capability of reflecting structure health can be considered as a principal factor to achieve better prognosis performance. In traditional data-driven RUL prognosis, there are drawbacks in which features are manually extracted and threshold is defined to mark the specimen’s breakdown. To overcome these limitations, this paper presents an innovative SAE-DNN structure capable of automatic health indicator (HI) construction from raw signals. HI curves constructed by SAE-DNN have much better fitness metrics than HI curves constructed from statistical parameters such as RMS, Kurtosis, Sknewness, etc. In the next stage, HI curves constructed from training degradation data are then used to train a long short-term memory recurrent neural network (LSTM-RNN). The LSTM-RNN is utilized as a RUL predictor since its special gates allow it to learn long-term dependencies even when the training data is limited. Model construction, verification, and comparison are performed on experimental reinforced concrete (RC) beam data. Experimental results indicates that LSTM-RNN generally estimates more accurate RULs of concrete beams than GRU-RNN and simple RNN with the average prediction error cycles was less than half compared to those of the simple RNN.

Intrusion Detection System (IDS) is built to detect both known and unknown malicious attacks. Several machine learning algorithms are used widely in IDS such as neural network, SVM, KNN etc. However, these algorithms have still some limitations such as high false positive and false alarm rate. To overcome above challenge, we propose a novel effective attack detection method based on kernel principal component analysis (PCA) and long short-term memory recurrent neural network (LSTM-RNN). To achieve high accurate detection rate, data preprocessing, feature extraction, attack detection is seamlessly integrated into an end-to-end detection method. To assess the method, the well-known NSL-KDD dataset has been used. The results of experimental show that the proposed attack detection strategy greatly outperforms several attack detection strategy that use SVM, neural network or Bayesian methods.

In this paper, an empirical evaluation of different classification techniques is conducted on user movement data. The datasets used here for experiments are composed of accelerometer data collected from various devices, including smartphones and smart watches. The user movement data was processed and fed into five traditional machine learning algorithms. The classification performances were then compared with a deep learning technique, the Long Short Term Memory-Recurrent Neural Network (LSTM-RNN). LSTM-RNN achieved its highest accuracy at 89% as opposed to 97% from a traditional machine learning algorithm, specifically, K-Nearest Neighbors (k-NN), on wrist-worn accelerometer data.

Anomaly detection is a concept that has been studied for many decades now, and many frameworks and algorithms are proposed after that. Intrusion can occur in any scenario, so identifying one becomes a vital task. The reverberation of not detecting these outliers can be severe and can result in a huge loss. In this chapter, we concentrate on identifying an anomaly using supervised and unsupervised learning techniques, for instance support vector machine (SVM), artificial neural network (ANN), long short-term memory recurrent neural network (LSTM-RNN), isolation forest, and K-means clustering algorithm. Four real-world open-source datasets are studied for this purpose, and a statistical method known as the adaptive threshold is utilized for the detection of anomalous data points in these datasets. Several regression metrics are obtained for the datasets, and anomalies corresponding to these datasets are compared with unsupervised learning algorithms.

Time plays a crucial role in influencing and understanding users' changeable preferences among various factors which directly or indirectly result in users' interesting behavior. In this paper, we propose a neural time series forecasting model (NTSF) to fit and predict user preference trend according to time. In this model, we integrate emerging/hot topic detection to deal with the short-term aspects, and use Fast Fourier Transformation (FFT) to differentiate cyclic behavior of users. Considering the nonstationary and nonlinear characteristics appearing through user interest patterns, Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) is employed to balance the influence of short and long term aspects, as well as adjust model parameters according to historical results. Our experimental results with extensive Twitter datasets verify the effectiveness of our approach.

A crucial element for the reliable and safe usage of lithium-ion (Li-ion) batteries is the capacity to precisely and effectively predict the remaining useful life of the battery. This research involves training a long short-term memory recurrent neural network (LSTMRNN) model to analyse sequential data regarding discharge capabilities over various cycles and voltages. Furthermore, the model is designed to serve as a cycle life prediction for battery cells subjected to various environments. This model achieves a commendable level of predictive accuracy on test sets including roughly 200 items by employing experimental data from the NASA dataset.

Intrusion Detection Systems (IDS) play a vital role in monitoring and preventing unauthorized access within critical network infrastructures. However, current IDS approaches often suffer from limitations in detection accuracy, scalability, and adaptability to evolving threats. To address these challenges, this study proposes an optimized Long Short-Term Memory Recurrent Neural Network (LSTM-RNN) model for network-based intrusion detection. The model is specifically designed to capture temporal dependencies in sequential network traffic data, enabling accurate classification of benign and malicious activity while maintaining computational efficiency. The proposed model underwent rigorous validation to assess both its detection accuracy and generalizability. This was achieved by utilizing two distinct datasets that encompass realistic network traffic and a wide array of attack scenarios, including Denial of Service (DoS), Probe, User-to-Root (U2R), and Remote-to-Local (R2L) intrusions. The performance of the model is compared with several other recent models. The proposed model achieved high classification results among all the compared models, with an accuracy of 99.94%, precision of 99.98%, recall of 99.93%, and an F1-score of 99.95%. These outstanding results underscore the model’s robust capability to accurately identify and flag malicious activities within complex network environments. The model’s generalization power was similarly affirmed on a second independent dataset. The model maintained strong performance with an accuracy of 99.42%, precision of 99.20%, recall of 99.69%, and an F1-score of 99.45%. The successful demonstration of both high detection accuracy and strong generalization capability highlights the practical utility and inherent reliability of our proposed model for real-world threat detection.

In order to personalize users’ recommendations, it is essential to consider their personalized preferences on non-functional attributes during service recommendation. However, to increase recommendation accuracy, it is essential that recommendation systems include users’ evolving preferences. It is not sufficient to only consider users’ preferences at a point in time. Existing time-based recommendation systems either disregard rich and useful historical user invocation information, or rely on information from similar users, and thus, fail to thoroughly capture users’ dynamic preferences for personalized recommendation. This work proposes a method to personalize users’ recommendations based on their dynamic preferences on non-functional attributes. First, we compose a user’s preference profile as a time series of his/her invocation preference and pre-invocation dependencies (i.e. the different services that were viewed prior to invoking the preferred service). We model a user’s invocation preference as a combination of non-functional attribute values observed during service invocation, and topic distribution from WSDL of the invoked service using Hierarchical Dirichlet Process (HDP). Next, we employ long short-term memory recurrent neural networks (LSTM-RNN) to predict the user’s future invocation preference. Finally, based on the predicted future invocation preference, we recommend service(s) to that user. To evaluate our proposed method, we perform experiments using real-world service dataset, WS-Dream.

Wireless indoor localization is a significant challenge because of the noise generated by building structures, electromagnetic fields, and distances between connected nodes inside a building. This study compares two main localization methods: fingerprints (real and synthetic) and ranging schemes based on the Received Signal Strength Indicator (RSSI) of the ZigBee network. We followed four steps for the fingerprinting scheme. First, we obtained real data from the transceivers. Second, we computed the path-loss exponent for each device. Third, we produced a synthetic fingerprint dataset. Finally, we used three localization methods: k-nearest neighbor (KNN), multilayer perceptron (MLP), and long short-term memory recurrent neural network (LSTM-RNN). We assessed the performance of the localization methods by measuring their accuracy, precision, error-to-active area ratio, and installation difficulties. The results show that the real fingerprint scheme has the best performance, but it requires more installation time. While the synthetic fingerprint generation is based on the path-loss method that mixes the advantage of both fingerprint and path-loss. Furthermore, we compared the proposed estimated path-loss with that of a state-of-the-art method and demonstrated that the proposed method exhibits superior performance. These results suggest that the proposed method is more precise and suitable for real datasets.