Bulletin of Electrical Engineering and Informatics
Not a member yet
2885 research outputs found
Sort by
Addressing the complexities of postoperative brain MRI cavity segmentation–a comprehensive review
Get PDFPostoperative brain magnetic resonance images (MRI) is pivotal for evaluating tumor resection and monitoring post-surgical changes. The segmentation of surgical cavities in these images poses challenges due to artifacts, tissue reorganization, and heterogeneous appearances. This study explores challenges and advancements in postoperative brain MRI segmentation, examining publicly accessible datasets and the efficacy of various deep learning models. The analysis focuses on different U-Net models (U-Net, V-Net, ResU-Net, attention U-Net, dense U-Net, and dilated U-Net) using the EPISURG dataset. The training dice scores are as follows: U-Net 0.8150, attention U-Net 0.8534, V-Net 0.7602, ResU-Net 0.7945, dense U-Net 0.83, dilated U-Net 0.80. The study thoroughly assesses existing postoperative cavity segmentation models and proposes a fine-tuning approach to enhance the performance further, particularly for the best-performing model, attention U-Net. This fine-tuning involves introducing dilated convolutions and residual connections to the existing attention U-Net model, resulting in improved results. These improvements underscore the necessity for ongoing research to select and adapt efficient models, retrain specific layers with a comprehensive collection of post-operative images, and fine-tune model parameters to enhance feature extraction during the encoding phase
Best Agile method selection approach at workplace
Get PDFSelecting the most suitable agile software development method is a challenging task due to the variety of available methods, each with its strengths and weaknesses. To achieve project goals effectively, factors such as project needs, team size, complexity, and customer involvement should be carefully evaluated. Choosing the appropriate agile method is crucial for achieving high client satisfaction and effective team management, but it can be a challenging task for project managers and higher-level management officials.This paper presents a solution aiming to help them in selecting the most suitable software development method for their project. In this regard, this solution includes a pre-project management approach model and a decision tree that considers the unique requirements of the project. In the proposed solution results, Scrum was found to be suitable for both small and large projects, on the condition that roles and responsibilities are clearly defined and that the approach is people-centric. Furthermore, high-risk mitigation measures should be added for small projects. To facilitate the use of our model, a software application has been developed which implements the decision-making tree
Handover management in vehicle communication: applications, techniques, issues, and challenges: a review
Get PDFVehicle-to-everything (V2X) communication is an emerging technology that facilitates communication among vehicles and numerous environmental entities. However, it encounters certain challenges throughout the handover process. This study analyses the challenges and complexity of managing handover, specifically in maintaining uninterrupted connection and meeting the service criteria outlined in the 3GPP 5G new radio (NR) standard. Various applications of V2X technology that require handover management are explored, such as vehicle safety and traffic management, enhanced driver assistance, and autonomous driving. Furthermore, this paper illuminates the most recent developments in V2X communication, highlighting the significance of efficient handover management, resolving technical issues, based on the full potential of the use of V2X apps that contribute to the establishment of a transportation ecosystem that is characterized by enhanced safety, increased intelligence, and improved connectivity. This paper can be used as a starting point for thinking about how to improve C-V2X communication
Comparing horizontal versus vertical arrangement on the ground resistance values
Get PDFIt is important to compare the horizontal electrodes versus vertical ground electrodes particularly when there is limited area to extend the horizontal ground electrode and hard soil at the deeper soil in order to install the vertical rod electrode. Although all of these can be assessed by computational work, much work has shown that computed resistance values are different than measured resistance values and these computational softwares are not always available to the users. For these reasons, the aim of this paper is to address this shortfall by considering two sites with two-layer soil resistivity model where site 1 with upper layer higher than the lower layer and vice versa for site 2. For the same size of ground electrodes, vertical arrangement is found to have lower ground resistance values, despite higher soil resistivity at the lower layer soil. Soil compaction after backfilling the trench during the installation of horizontal electrode has been identified as the main factor that contributes to differences between the measured and computed resistance values
Enhancing spyware detection by utilizing decision trees with hyperparameter optimization
Get PDFIn the realm of cybersecurity, spyware has emerged as a formidable adversary due to its persistent and stealthy nature. This study delves deeply into the multifaceted impact of spyware, meticulously examining its implications for individuals and organizations. This work introduces a systematic approach to spyware detection, leveraging decision trees (DT), a machine-learning classifier renowned for its analytical prowess. A pivotal aspect of this research involves the meticulous optimization of DT's hyperparameters, a critical operation for enhancing the precision of spyware threat identification. To evaluate the efficacy of the proposed methodology, the study employs the Obfuscated-MalMem2022 dataset, well-regarded for its comprehensive and detailed spyware-related data. The model is implemented using the Python programming language. Significantly, the findings of this study consistently demonstrate the superiority of the DT classifier over other methods. With an accuracy rate of 99.97%, the DT proves its exceptional effectiveness in detecting spyware, particularly in the face of more intricate threats. By advancing our understanding of spyware and providing a potent detection mechanism, this research equips cybersecurity professionals with a valuable tool to combat this persistent online menace
User authentication using gait and enhanced attribute-based encryption: a case of smart home
Get PDFWith the increasing popularity of the internet of things (IoT) application such as smart home, more data is being collected, and subsequently, concerns about preserving the privacy and confidentiality of these data are growing. When intruders attack and get control of smart home devices, privacy is compromised. Attribute-based encryption (ABE) is a new technique proposed to solve the data privacy issue in smart homes. However, ABE involves high computational cost, and the length of its ciphertext/private key increases linearly with the number of attributes, thus limiting the usage of ABE. This study proposes an enhanced ABE that utilises gait profile. By combining lesser number of attributes and generating a profiling attribute that utilises gait, the proposed technique solves two issues: computational cost and one-to-one encryption. Based on experiment conducted, computational time has been reduced by 55.27% with nine static attributes and one profile attribute. Thus, enhanced ABE is better in terms of computational time
Gamma and ultraviolet radiation radiation analysis: an internet of things-based dosimetric study
Get PDFThis study presents the implementation of an internet of things (IoT)-based device for the accurate and continuous measurement of gamma and ultraviolet (UV) radiation in a rural area of Sincelejo, Colombia. The device, calibrated with an error margin below 5%, allowed for the reliable collection of data during the year 2022. An average effective dose rate of gamma radiation of (0.998±0.037) mSv/year was recorded, a value that approaches the recommended limit. Additionally, the inverse square law of radiation was confirmed, observing a decrease in radiation with an increase in altitude. Concurrently, a constant risk of high to extremely high UV radiation exposure was detected throughout the year. These findings emphasize the need for constant monitoring and the implementation of UV protection measures in the region. The integration of IoT in environmental dosimetry has proven to be an invaluable tool for detailed tracking of radiation levels, significantly contributing to the understanding of radiation in rural areas. The exploration of more advanced sensors and data analysis tools in future research is recommended to further improve the accuracy and utility of these devices
Impact of business intelligence on incident management in the control center of a security company
Get PDFThe main objective of this article is to implement business intelligence (BI) technology to improve incident management in the control center of a security company; making use of the Ralph Kimball method for the development of the data mart, contemplating the phases: planning of projects, definition of requirements, design of technological architecture, performing a dimensional modeling a star with 9 dimensions and 1 table made, also used the structured query language (MySQL) database, extract, transform, and load (ETL). Development the pentaho data integration, which allowed the migration, transformation and cleaning of the data from the online transaction processing (OLTP) and online analytical processing (OLAP) database, obtaining as a result that the BI managed to increase the level of the service by 28.42% and reducing the frequency index by 25%
Enhancing power conversion efficiency in five-level multilevel inverters using reduced switch topology
Get PDFThis paper presents extensive research on improving the power conversion efficiency of five-level multilevel inverters (MLIs) by utilizing a reduced switch topology. MLIs have received an abundance of focus because of their ability to generate high-quality output waveforms and have better harmonic outcomes than traditional two-level inverters. The high number of switches in MLIs, on the other hand, can result in increased power losses and lower overall efficiency. In this paper, a novel reduced switch topology for five-level MLIs, which is having five switches is proposed with the aim of minimizing power losses while preserving superior performance due to lesser number of switches. To achieve efficient power conversion, the proposed topology employs advanced pulse width modulation control strategies and optimized switching patterns. The simulation results show that the minimized switch topology improves the power conversion efficiency of the five-level MLI, resulting in lower losses and better overall system performance. The total harmonic distortion (THD) value of the output current has been reduced to 7.12% and the efficiency has been achieved to 96.92%. The findings of this investigation help to advance MLI technology, allowing for more efficient and reliable power conversion in a variety of applications such as renewable energy systems, electric vehicles, and industrial drives
An intelligent obfuscated mobile malware detection using deep supervised learning algorithms
Get PDFObfuscated mobile malware (OMM) is a malicious software in mobile that hides to avoid detection and annihilation. These types of malwares are thorny to identify due to their inevitable nature. Deep learning (DL) algorithms are the most desirable to detect obfuscated malware based on the ‘n’ number of iterations with adjustable weights and neurons. This study investigates the accurate detection of OMM using significant DL algorithms such as multi-layer perceptron (MLP), self-organizing maps (SOM), long short-term memory (LSTM) networks, auto encoders (AE), and convolutional neural network (CNN) based on appropriate parameter tuning. The dataset taken for the study is CICMalMem2022 that contains 58,596 samples with 57 features which is basically designed for OMM detection. The dataset comprises Spyware, Ransomware, Trojan horse, and Benign. The DL models are evaluated based on performance metrics such as precision, recall, accuracy, training accuracy, test accuracy, validation accuracy, training loss, validation loss and receiver operating characteristic (ROC) curve. Based on the experimental evaluation, the study reveals that LSTM outperforms with 100% accuracy and MLP achieves 99.9% accuracy in detecting and classifying the OMM using deep supervised learning (SL) mechanism