A Feed-Forward Neural Network Approach for Energy-Based Acoustic Source Localization

Correia, Sérgio D.; Tomic, Slaviša; Beko, Marko

doi:10.3390/jsan10020029

Cited by 16 publications

(10 citation statements)

References 68 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The momentum constants are represented by Δw ij n and computed via Equations ( 9) and (10). The overall performance of our proposed algorithm was 5.21 and 3.95 in terms of RMSE and MAE respectively.…”

Section: T a B L E 4 Overall Results Of The α-β Filter With And Witho...mentioning

confidence: 99%

“…The DELM algorithm needs a huge amount of data to train the model, has a slower computation time with respect to the learning rate, and may lead to overfit the model sometimes because it takes a long time and more computation epochs [9]. The feed-forward backpropagation neural network [8][9][10] is very simple and easy to train and has the advantages of fast computation and learning rate to help counterbalance the problems of the DELM when tuning the alpha and beta values [1]. When using the backpropagation algorithm, ELM can deliver correct predictive performance, and the computational rate is much lower than those of the other models.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

A higher prediction accuracy–based alpha–beta filter algorithm using the feedforward artificial neural network

Khan

Lee

Kim

2022

CAAI Trans on Intel Tech

View full text Add to dashboard Cite

The alpha–beta filter algorithm has been widely researched for various applications, for example, navigation and target tracking systems. To improve the dynamic performance of the alpha–beta filter algorithm, a new prediction learning model is proposed in this study. The proposed model has two main components: (1) the alpha–beta filter algorithm is the main prediction module, and (2) the learning module is a feedforward artificial neural network (FF‐ANN). Furthermore, the model uses two inputs, temperature sensor and humidity sensor data, and a prediction algorithm is used to predict actual sensor readings from noisy sensor readings. Using the novel proposed technique, prediction accuracy is significantly improved while adding the feed‐forward backpropagation neural network, and also reduces the root mean square error (RMSE) and mean absolute error (MAE). We carried out different experiments with different experimental setups. The proposed model performance was evaluated with the traditional alpha–beta filter algorithm and other algorithms such as the Kalman filter. A higher prediction accuracy was achieved, and the MAE and RMSE were 35.1%–38.2% respectively. The final proposed model results show increased performance when compared to traditional methods.

show abstract

Section: T a B L E 4 Overall Results Of The α-β Filter With And Witho...mentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

A higher prediction accuracy–based alpha–beta filter algorithm using the feedforward artificial neural network

Khan

Lee

Kim

2022

CAAI Trans on Intel Tech

View full text Add to dashboard Cite

show abstract

“…In the past decades, an increase in its research interest led to more and more areas of science finding application within ML algorithms. Application can be found in agriculture [8], industry [9], sensor networks [10], fashion [11,12] or healthcare [13,14], just to mention a few examples.…”

Section: Methodsmentioning

confidence: 99%

Application of Machine Learning Techniques to Predict a Patient’s No-Show in the Healthcare Sector

et al. 2021

Self Cite

View full text Add to dashboard Cite

The health sector faces a series of problems generated by patients who miss their scheduled appointments. The main challenge to this problem is to understand the patient’s profile and predict potential absences. The goal of this work is to explore the main causes that contribute to a patient’s no-show and develop a prediction model able to identify whether the patient will attend their scheduled appointment or not. The study was based on data from clinics that serve the Unified Health System (SUS) at the University of Vale do Itajaí in southern Brazil. The model obtained was tested on a real collected dataset with about 5000 samples. The best model result was performed by the Random Forest classifier. It had the best Recall Rate (0.91) and achieved an ROC curve rate of 0.969. This research was approved and authorized by the Ethics Committee of the University of Vale do Itajaí, under opinion 4270,234, contemplating the General Data Protection Law.

show abstract

“…Also, 𝑃 𝑖 𝑡 denotes the best optimal solution computed until the current iteration. To determine the best solution, each of the above relationships can be implemented like equations (10), with a probability of 50% on a problem solution like 𝑋 𝑖 𝑡 , so this results in the calculation of its position in the new iteration. [14]: (10)…”

Section: Optimization With Sine and Cosine Equationsmentioning

confidence: 99%

Localization in a wireless sensor network with a geometric approach of Trilateration and mathematical modeling of sine and cosine functions

Ghadami

2024

Preprint

View full text Add to dashboard Cite

Wireless sensor network (WSN) has several applications in agriculture, military, rescue, and environmental applications. In a WSN, a large number of sensor nodes are scattered in an operating environment and gather environmental information. The data collected by the WSN is sent to an application in the cloud computing layer or base station for analysis. Gathering information without having their localization and position is not of high value, and accurate localization and position determination of sensor nodes are required in various applications. One method for localization is to use a Global Positioning System (GPS) and install it on all sensor nodes. localization with GPS costs a lot, and on the other hand, this method consumes a lot of energy for localization. DV-Hop technique is a practical method for positioning by reducing the positioning cost. The challenge of the DV-Hop approach for localization is the significant error in locating sensor nodes without a GPS. In this article, a practical localization method is presented by combining the DV-Hop method and the geometric localization method of three references. In this study, the sensor nodes first estimate their distance from the three guide nodes with the step measurement algorithm and then locate them using the Trilateration method. In the proposed approach, the sine and cosine optimization algorithm (SCA) are applied to minimize the positioning error. The evaluations illustrate that the localization error of the suggested approach is lower than the DV-Hop approach. The proposed positioning algorithm has less positioning error than the whale optimization algorithm (WOA), the Harris Hawk Optimization (HHO) algorithm, and the Jellyfish Search optimizer (JSO). The evaluations show that the proposed method of advanced localization methods based on steps such as GSDV-Hop and MGDV-Hop has fewer errors in localization.

show abstract

A Feed-Forward Neural Network Approach for Energy-Based Acoustic Source Localization

Cited by 16 publications

References 68 publications

A higher prediction accuracy–based alpha–beta filter algorithm using the feedforward artificial neural network

A higher prediction accuracy–based alpha–beta filter algorithm using the feedforward artificial neural network

Application of Machine Learning Techniques to Predict a Patient’s No-Show in the Healthcare Sector

Localization in a wireless sensor network with a geometric approach of Trilateration and mathematical modeling of sine and cosine functions

Contact Info

Product

Resources

About