An Experimental Comparison of RSSI-Based Indoor Localization Techniques Using ZigBee Technology

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.

Keyphrases are single or multiple word phrases of a document which portrays the principal points of that document. These keyphrases help readers to get an overview of the document. In this paper, we proposed a system that uses Long Short-Term Memory (LSTM) Recurrent Neural Network (RNN) to automatically detect keyphrases from a document. We also implemented Multilayer Perceptron (MLP) network to compare the performance of our proposed LSTM approach. We applied several pre-processing steps on a document to generate the candidate keyphrases. Finally, we found better performance from our proposed approach with compared to the MLP network.

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

Nowadays, location awareness becomes the key to numerous Internet of Things (IoT) applications. Among the various methods for indoor localisation, received signal strength indicator (RSSI)-based fingerprinting attracts massive attention. However, the RSSI fingerprinting method is susceptible to lower accuracies because of the disturbance triggered by various factors from the indoors that influence the link quality of radio signals. Localisation using body-mounted wearable devices introduces an additional source of error when calculating the RSSI, leading to the deterioration of localisation performance. The broad aim of this study is to mitigate the user’s body shadowing effect on RSSI to improve localisation accuracy. Firstly, this study examines the effect of the user’s body on RSSI. Then, an angle estimation method is proposed by leveraging the concept of landmark. For precise identification of landmarks, an inertial measurement unit (IMU)-aided decision tree-based motion mode classifier is implemented. After that, a compensation model is proposed to correct the RSSI. Finally, the unknown location is estimated using the nearest neighbour method. Results demonstrated that the proposed system can significantly improve the localisation accuracy, where a median localisation accuracy of 1.46 m is achieved after compensating the body effect, which is 2.68 m before the compensation using the classical K-nearest neighbour method. Moreover, the proposed system noticeably outperformed others when comparing its performance with two other related works. The median accuracy is further improved to 0.74 m by applying a proposed weighted K-nearest neighbour algorithm.

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.

Deep underground laboratories offer advantages for conducting high-precision observations of weak geophysical signals, benefiting from a low background noise level. Enhancing strong, noisy ground electromagnetic (EM) field data using synchronously recorded underground EM signals, which typically exhibit a high signal-to-noise ratio, is both valuable and feasible. In this study, we propose an EM field reconstruction method employing a Long Short-Term Memory (LSTM) recurrent neural network with referenced deep underground EM observations. Initially, a deep learning model was developed to capture the time-varying features of underground multi-component EM fields using the LSTM recurrent neural network. Subsequently, this model was applied to process synchronously observed strong, noisy data from other conventional observation systems, such as those at the surface, to achieve noise suppression through signal reconstructions. Both the theoretical analysis and the practical observational data suggest that the proposed method effectively suppresses noise and reconstructs clean EM signals. This method is efficient and time-saving, representing an effective approach to fully utilizing the advantages of deep underground observation data. Furthermore, this method could be extended to the processing and analysis of other geophysical data.

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.

Automatic recognition of frustration, by analysing facial and vocal expressions, can help user experience designers to identify interaction obstacles. To encourage the development of automated systems such as these, we present a novel audiovisual database: the Multimodal Game Frustration Database (MGFD), consisting of ca. 5 hours of audiovisual data, collected from 67 Chinese students speaking in English. For data collection, we developed ‘Crazy Trophy’, a Wizard-of-Oz voice activated web-game designed with a variety of usability problems and aimed to induce increasing amounts of frustration. We also present a baseline for binary multimodal frustration classification (frustration vs no-frustration). For this, we compare the performance of a conventional method, Support Vector Machine classifier, and a state-of-the-art method utilising Long Short-Term Memory Recurrent Neural Networks (LSTM-RNN), extracting both audio (Mel-frequency Cepstral Coefficients) and video (facial action units) features. Using LSTM-RNN and a feature-based multi-model fusion strategy, the best result acheived for the baseline was 60.3 % UAR. To enable further research in this area, the game (‘Crazy Trophy’), the database (MGFD), and the partitioning considered in the presented baseline, are made accessible to the research community.

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

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.

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.

Received Signal Strength Indicator (RSSI) is used in indoor positioning for measuring object distance to the base station. However, acquiring accurate RSSI values is challenging because wireless interference factors, such as multipath decline interference, make RSSI values of the same object fluctuate over time. Therefore, instead of a single RSSI, RSSI acquisition will collect a set of RSSI values from which the most moderate RSSI is derived. For this purpose, we propose an Enhanced Gaussian Mixture Model (EGMM) to derive a more precise RSSI for improving indoor positioning accuracy. EGMM enhances Gaussian Mixture Model (GMM) by applying Akaike information criterion (AIC) to determine the best K value for GMM to divide RSSI values into K sets representing signals from different paths. Then, EGMM identifies the most appropriate set of RSSI values to derive a more precise RSSI and thus improves the accuracy of indoor positioning. Our EGMM solution performs well in an open indoor space. The experiment is conducted with iBeacon devices, and the average error distance of EGMM is about 64% of those generated by existing Gaussian filtering. The average positioning error of EGMM is about 0.48 meter, which is adequate to indoor positioning accuracy.

An indoor localization system in wireless sensor networks has become a hot development area. Received signal strength indicator (RSSI)-based localization is a promising technique since it requires a relatively low configuration, battery power and easy control. However, the received signal strength is influenced by channel interference and propagation environments. This characteristic affects channel stability and location accuracy in RSSI-based localization. As a result, we propose a novel indoor localization system consisting of a preprocessing method and a post-processing method. To improve channel stability, the pre-processing method selects an optimal channel in terms of the smallest distance error. The optimal channel is less affected to IEEE 802.11. To develop location accuracy, the post-processing method performs maximum likelihood estimation-based location tracking scheme considering the reliability of the RSSI value measurement. We apply three methods to the existing MLE to improve the reliability of the RSSI value. By using this indoor localization system with preprocessing and post-processing, the location error can be reduced. We also proved the performance of the indoor localization system by conducting experiments in a real indoor environment.