Bulletin of Electrical Engineering and Informatics
Not a member yet
2885 research outputs found
Sort by
IoT-based health information system using MitApp for abnormal electrocardiogram signal monitoring
Get PDFInformation systems are currently developing very rapidly, and this is inseparable from the role of internet of things (IoT) technology, especially in the world of telemedicine. MitApp is an open-source application that can be used to monitor electrocardiogram (ECG) signals in real-time. The aim of this study is to develop an IoT-based ECG signal monitoring system that utilizes the MitApp application to detect abnormal ECG signals that are characterized by symptoms of cardiac arrhythmias. To process ECG signal data obtained from lead electrode results, the research method utilizes Arduino Uno as a microcontroller. The result is then displayed on the thin film transistor (TFT) layer using the Nextion module. The ESP32 module is used as a Wi-Fi module to send data to the MitApp app on a smartphone. The results showed that the results of the comparison test of ECG signal module data with ECG simulator tools with beats per minute values of 60, 80, 100, 120, and 140 obtained an error rate of 0.05. Based on these results, there is potential to develop this feature and integrate the system with the patient management system to improve the effectiveness of remote monitoring
Improved bidirectional long short term memory-based QRS complex detection using autoencoder
Get PDFIn this paper, we propose a new technique to improve QRS complex detection. This technique consists of incorporating an autoencoder and bidirectional long short term memory (BiLSTM). The autoencoder used is a stacked autoencoder and functions as signal filtering. Meanwhile, BiLSTM is used as a detector. Exploration of the effect of hyperparameter in the autoencoder was also carried out to determine the effect on QRS complex detection. Furthermore, the dataset used in this study is the MIT-BIH arrhythmia database. Based on the experimental results, the hyperparameter in the autoencoder that gives a better effect on QRS complex detection is 16-8. Finally, the proposed method out-of-perform state of the art algorithm with accuracy 99.94%
Enhancing the medical diagnosis of COVID-19 with learning based decision support systems
Get PDFSince late December 2019, the COVID-19 pandemic has had substantial impact and long-lasting impact on numerous lives. The surge in patients has overwhelmed hospitals and exhausted essential resources such as masks and gloves. However, in response to this crisis, we have developed a robust solution that can ease the burden on emergency services and manage the influx of patients. Our proposed framework comprises deep learning and machine learning models that can predict and manage patient demand with high accuracy. The first model, is specifically designed to classify computed tomography (CT) scan images for COVID or non-COVID cases. We trained multiple convolutional neural network (CNN) models on a large dataset of CT scan images and evaluated their performance on a separate test set. Our evaluation showed that the ResNet50 model was the most effective, achieving an accuracy of 93.28%. The second model uses patient measurements dataset to predict the likelihood of intensive care unit (ICU) admission for COVID-19 patients. We experimented with the XGBoost machine learning algorithm and found that the accuracy score achieved 88.40%
Enhancing voltage stability through wavelet-fuzzy control of hydrogen flow in OC-PEM fuel cell
Get PDFOpen cathode proton exchange membrane fuel cells (OC-PEM fuel cells) serve as electricity generators, utilizing hydrogen as an input source. While effective for fixed loads like residential applications, challenges arise in dealing with output voltage fluctuations caused by rapid load changes. These fluctuations not only impact fuel cell performance but also introduce instability in the supplied power. To solve this issue, the study proposes an innovative hydrogen flow control system employing a feedforward wavelet- fuzzy method. The primary goal of this control system is to enhance fuzzy control performance using wavelets, mitigating signal fluctuations and achieving optimal stability in fuel cell output voltage under constant load conditions. Wavelet functions act as filters on the fuzzy control input, minimizing fluctuations and refining the entire process. Additionally, a feedforward system is incorporated to maintain hydrogen flow at the set point value. The proposed control system is implemented on a validated model using experimental data. Performance analysis reveals that the proposed method effectively stabilizes voltage by accelerating the recovery time from disturbances
Secure and efficient data storage with Rivest Shamir Adleman algorithm in cloud environment
Get PDFCloud computing rapidly is a prerequisite and releases resources with minimal management effort. The surfacing of the cloud has significantly distorted the general insight into infrastructure, software services, and development models. In contrast to single-key encryption models based on public or private keys (PKs), hybrid encryption systems combine encryption methods using symmetric or asymmetric methods. Various hybrid algorithms fail to meet users’ expectations regarding data security and cannot prevent all security risks. The secure and efficient data storage and retrieval (SEDSR) algorithm was developed for scalable key management between the content owner, cloud user, and service providers in an un-trusted cloud environment. In the implementation, the SEDSR combines the Rivest Shamir Adleman (RSA) algorithm 4096 key length with a primary symmetric key method to provide adequate and compact security with optimal retrieval systems in the cloud. Based on the experimental evaluation, the SEDSR minimizes 1.7 seconds of encryption times (ET) and 1.5 seconds of decryption time (DT) and improves by 34% throughput (TRP) compared to existing parameters
Classifying possible hate speech from text with deep learning and ensemble on embedding method
Get PDFHate speech can be defined as the use of language to express hatred towards another party. Twitter is one of the most widely used social media platforms in the community. In addition to submitting user-generated content, other users can provide feedback through comments. There are several users who intentionally or unintentionally provide negative comments. Even though there are regulations regarding the prohibition of hate speech, there are still those who make negative comments. Using the deep learning method with the long short-term memory (LSTM) model, a classifier of possible hate speech from messages on Twitter is carried out. With the ensemble method, term frequency times inverse document frequency (TF-IDF) and global vector (GloVe) get 86% accuracy, better than the stand-alone word to vector (Word2Vec) method, which only gets 80%. From these results, it can be concluded that the ensemble method can improve accuracy compared to only using the stand-alone method. Ensemble methods can also improve the performance of deep learning systems and produce better results than using only one method
Design of mapping system for domestic service robot using light detection and ranging
Get PDFService robots are becoming increasingly essential in offices or domestic environments, usually called domestic service robots (DSR). They must navigate and interact seamlessly with their surroundings, including humans and objects, which relies on effective mapping and localization. This study focuses on mapping, employing the light detection and ranging (LiDAR) sensor. The sensor, tested at proximity, gathers distance data to generate two-dimensional maps on a mini-PC. Additionally, it provides rotational positioning and robot odometry, broadening coverage through robot movement. A microcontroller with wireless smartphone connectivity facilitates control via Bluetooth. The robot is also equipped with ultrasonic sensors serving as a bumper. Testing in rooms of varying sizes using three methods (i.e., Hector simultaneous localization and mapping (SLAM), Google Cartographer, and real-time appearance-based mapping (RTAB-Map)) yielded good quality maps. The best F1-measure value was 96.88% achieved by Google Cartographer. All the results demonstrated the feasibility of this approach for DSR development across diverse applications
Reliability analysis in distribution system by deep belief neural network
Get PDFRapid increase in the usage of intermittent renewable energy, ongoing changes in electrical power system structure and operational needs posing growing problems while ensuring adequate service reliability and retaining the quality of power. Power system reliability is a pertinent factor to consider while planning, designing, and operating distribution systems. utilities are obligated to offer their customers uninterrupted electrical service at the least cost while maintaining a satisfactory level of service quality. The important metrics for gauging the effect of distributed renewable energy on distribution networks is reliability analysis. Reliability analysis in distribution systems involves evaluating the performance and robustness of electrical distribution networks. An artificial intelligence approach is implemented in this paper to improve reliability analysis with dispersed generations in distribution network. Deep belief neural networks (DBNNs) are a type of artificial neural network that can be used for various tasks, including analyzing complex data such as those found in power distribution systems. This paper integrated a DBNN using a particle swarm optimization (PSO) technique. The proposed model performance is assessed using mean square error, mean absolute error, root mean square error, and R squared error. The findings reveal that reliability analysis with this novel technique is more accurate
A convolution neural network integrating climate variables and spatial-temporal properties to predict influenza trends
Get PDFThe spread of influenza is contingent upon a multitude of outbreak-related factors, including viral mutation, climate conditions, acquisition of immunity, crowded environments, vaccine efficacy, social gatherings, and the health and age profiles of individuals in contact with infected individuals. An epidemic in the region impacted by spatial transmission risk from adjacent regions. A few influenzas epidemic models start highlighting the spatial correlations between influenza patients and geographically adjacent regions. The proposed model is based on the concept of climatic, immunization, and spatial correlations which are represented by a convolution neural network (CNN) for influenza epidemic forecasting. This study presents an integration of three determinants for predicting influenza outbreaks, multivariate climate data, spatial data on influenza vaccination, and spatial-temporal data of historical influenza patients. The performance of three comparison models, CNN, recurrent neural network (RNN), and long short-term memory (LSTM) was compared by the root mean squared error metric (RMSE). The findings revealed that the CNN model represents human interaction at intervals of 12, 16, 20, 24, and 28 weeks resulting in the best effectiveness of the lowest RMSE=0.00376 with learning rate=0.0001
Triangular fuzzy number for similarity measurement of Y chromosome DNA profile
Get PDFThis study measures the similarity of the short tandem repeat (STR) profile of human DNA. The similarity measurement had been done to the STR value of the allele loci in DNA profile between the query’s DNA to the reference’s DNA profile. The measurements were conducted on 27 DNA profile loci including the Y chromosome loci (YSTR). The YSTR loci were used as the main comparison of similarity measurements to determine the biological kinship relationship between the query DNA profile and the alleged male biological family. To measure the similarity of two STR values that have shifted due to several factors in the DNA source extraction process, a fuzzy similarity measure was used. The STR values of the DNA profile loci are described as triangular fuzzy numbers. Similarity value of the STR is the intersection of two isosecle that been compared. To conclude that the query has a biological relationship with the male reference, the similarity of the YSTR locus is equal or more than 0.75 and the similarity value of the other 24 DNA profile loci is greater or equal to 0.5. From the trial that have been done, 90% give the right results