Bulletin of Electrical Engineering and Informatics
Not a member yet
2885 research outputs found
Sort by
Recent advancements in postpartum depression prediction through machine learning approaches: a systematic review
Get PDFPostpartum depression (PPD) is a significant mental health concern affecting mothers worldwide, irrespective of demographic factors. Detecting and managing PPD at an early stage is crucial for effective intervention. In the context of mental health, intelligent predictive models based on machine learning (ML) have emerged as valuable tools. However, there remains a relative scarcity of research specifically targeting postpartum mental health due to several prominent factors that collectively impede the widespread adoption and practical implementation of ML in the field of PPD. This paper provides an updated overview of ML approaches for PPD prediction. A systematic search across IEEE Xplore, PubMed, Science Direct, and Scopus yielded 1,074 relevant articles. The performance of ML algorithms varies depending on the dataset and the problem being addressed. Notably, the findings reveal that the random forest (RF) algorithm consistently demonstrates the highest predictive accuracy, followed by support vector machine (SVM), logistic regression (LR), XGBoost, and AdaBoost. The development of advanced data techniques in PPD has encouraged interdisciplinary collaboration between researchers in psychiatry and computer science that holds great potential for refining the accuracy and reliability of PPD predictive models, ultimately resulting in improved outcomes for mothers and their families through early detection, intervention, and support
A frequency adaptive multiple complex coefficient filter for grid connected applications
Get PDFIn the realm of synchronization techniques, the dichotomy between open loops (OLSs) and closed loops (CLSs) presents a perennial challenge: how to enhance dynamic performance without sacrificing stability and disturbance rejection. While OLS techniques offer rapid dynamic response and unwavering stability, they often falter in non-nominal frequency scenarios. Conversely, CLS techniques grapple with the delicate balance of bolstering dynamic performance while maintaining robust stability. To surmount these obstacles, this study proposes an innovative approach: the integration of a frequency locked loop (FLL) as a secondary frequency detector within synchronization structures, coupled with the multiple-complex coefficient-filter (MCCF). This amalgamation bestows notable advantages. Firstly, from a control perspective, the resultant synchronization technique resembles a quasi-OLS, obviating the need for intricate stability analyses. Moreover, it exhibits commendable disturbances rejection alongside swift dynamic response. Through comprehensive simulation, our proposed technique showcases superiority over existing counterparts, evidencing enhanced settling time, disturbances rejection, and efficiency in the face of frequency drifts
6G networks: insights and reliability analysis
Get PDFAs we are living in a fast-moving dynamic world. Emerging technologies such as artificial intelligence (AI), internet of things (IoT), virtual reality (VR), augmented reality (AR), fourth industrial revolution (Industry 4.0), metaverse, and edge computing are expected to play an essential role in our daily life. These technologies require high-speed, sustainable, and reliable communications networks which are expected by sixth generation (6G) wireless communications networks. 6G will be the backbone for these emerging technologies as well as for the technology-driven digital infrastructure. Governments as well as research and development (RD) of the technology companies are gearing up to conduct a regulatory framework to standardize 6G networks; studying and conducting experimental setups to examine and evaluate the deployment of 6G networks; both in which they will have opportunities and challenges. This paper provides insights and guidelines for 6G networks in terms of standards, implementations, applications, and research trends. In addition, it provides reliability analysis for terrestrial 6G networks. A carrier class availability could be achieved over a maximum of 4 km link distance. These insights and availability figures may be used as a useful tool for researchers and industry stakeholders for the deployment and rollout of the next generation 6G wireless communications networks
Controlling a vehicle braking and longitudinal acceleration using a seeking control approach
Get PDFTraditional methods for tracking the paths of driverless vehicles use plant models to determine the corresponding control laws. Due to the intricate interactions between the road and the tires, time-varying characteristics, and unidentified disturbances. It is challenging to create an accurate vehicle model. As a result, data-driven controllers, which are independent of a predetermined plant model are becoming more and more well-liked. This work implements adaptive cruise control (ACC) by employing a control approach called extremum seeking technique (EST), which is a model-free control (MFC), to control a vehicle braking and longitudinal acceleration. The main aim here is to create an ego vehicle that travels at a specific speed with maintaining a secure space with respect to a guide vehicle. A car including an ACC technique called ego car, exploits radar to determine relative velocity and relative space relating to the guiding car. The ACC technique is considered to keep maintain a relatively secure space or a preferred cruising velocity concerning the guiding vehicle. The developed model succeeded to determine the relative velocity and relative space according for the ego car to another guiding car with acceleration not more than ±2 m/s2 and spacing error less than 6 m
FiMoDeAL: pilot study on shortest path heuristics in wireless sensor network for fire detection and alert ensemble
Get PDFWith the incessant outbreak of fire, the heavy loss to both lives and properties in the society fire has since become a critical issue and challenge that needs our daily attention to be resolved. Loss of lives and properties to fire outbreak in 2021 alone as occurring in major Nigerian markets and residential homes was estimated at over 3 trillion Naira. Our study proposes a wireless sensor network internet of things (IoT) based ensemble to aid the effective monitoring, detection and alerting of residents and fire service departments. With cost as a major issue and the requisite installation of fire and smoke detectors in many houses our ensemble can efficiently integrate into the existing system using the ESP8285-controller to create a comprehensive access control system. The system provides real time monitor and control capabilities that will allow administrators to track and manage fire monitor and detection within a facility. Thus, enhances system's efficiency and performance
Enhanced convolutional neural network enabled optimized diagnostic model for COVID-19 detection
Get PDFComputed tomography (CT) films are used to construct cross-sectional pictures of a particular region of the body by using many x-ray readings that were obtained at various angles. There is a general agreement in the medical community at this time that chest CT is the most accurate approach for identifying COVID-19 disease. It was demonstrated that chest CT had a higher sensitivity than reverse transcription polymerase chain reaction (RT-PCR) for the detection of COVID-19 illness. This article presents gray-level co-occurrence matrix (GLCM) texture feature extraction and convolutional neural network (CNN)-enabled optimized diagnostic model for COVID-19 detection. In this diagnostic model, CT scan images of patients are given as input. Firstly, GLCM algorithm is used to extract texture features from the CT scan images. This feature extraction helps in achieving higher classification accuracy. Classification is performed using CNN. It achieves higher accuracy than the k-nearest neighbors (KNN) algorithm and multi-layer preceptor (MLP). The accuracy of GLCM based CNN is 99%, F1 score is 99% and the recall rate is also 98%. CNN has achieved better results than MLP and KNN algorithms for COVID-19 detection
Streamlined multi-scenario revocation method leveraging blockchain and auxiliary trees
Get PDFAccess revocation is a fundamental aspect of modern information systems, ensuring that data remains secure and authorized personnel have appropriate access rights. However, existing access revocation methods address only one type of scenario, offering either partial or complete revocation functionalities but not both, leading to limitations in flexibility and effectiveness. This paper introduces a novel approach called streamlined multi-scenario revocation method (SMSRM) that combines block chain technology and auxiliary trees to streamline the process of multi-scenario access revocation. The SMSRM method defines two separate revoke request formats for partial and complete revocation. Auxiliary trees are used to keep track of non-revoked users, which is very important during the revocation process. In addition, the proposed method utilizes a block chain to record each and every revocation-related operation to provide forward secrecy. Through a comparative analysis, we evaluate the performance of our approach against existing methods. The results highlight that our method performs better in terms of response time and various performance metrics
Potential and economic feasibility analysis of solar-biomass-based hybrid system for rural electrification
Get PDFA significant portion of the population lives in rural regions where the grid cannot provide them with enough power. Rising power demand, fossil fuel prices, limited fossil fuels such as coal, and environmental issues are the key drivers driving the usage of renewable energy resources for generating electricity. As a result, an alternate option for electricity generation in such remote places is required. Using renewable resources as alternatives would undoubtedly aid in mitigating the effects of global warming. The hybrid energy system combines electric power production with renewable sources such as solar, biomass, wind, biogas, hydro, and diesel generators (DGs). In light of this, a feasibility study on hybrid renewable energy was carried out for a specified remote region. This research investigates the efficacy of a solar-biomass-based hybrid power generation for rural electrification. The effective and sustainable alternative is found in a standalone hybrid version based on solar biomass. Electricity produced from the hybrid model proposed is $0.603.555 per unit, which is almost free of emissions of greenhouse gas (GHG), equally economical, and cleaner than the traditional supply. This system can be beneficial to electrify other adjacent remote zones
Design and implementation of pulse width modulation gate control signals for two-level three-phase inverters
Get PDFThe switching control circuit in a DC to AC inverter is the critical part that is applied to control the power transistors insulated-gate bipolar transistor (IGBTs) and metal-oxide semiconductor field-effect transistor (MOSFETs). This paper proposes a high-performance and low-cost pulse width modulation (PWM) control signal with a 120º phase shift circuit for a two-level three-phase inverter. Typically, a PWM signal with a 120º phase shift for three-phase inverters is generated with the help of analogue components with more complicated designs and power losses or by using a microcontroller with necessary programming or coding. The proposed solution is to design a 120° three-phase shift circuit based on D flip-flops and the 555-timer to generate the clock signal for the flip-flop input in addition to the dead-time control circuit. The proposed circuit is controlled by one square wave signal as an input signal to generate six output PWM control signals at 50 Hz to operate six MOSFETs in the three-phase inverter. Simulation results in power simulation software PSIM and PROTEUS simulation tools are used to verify the proposed circuit. Hardware implementation of the proposed circuit and three-phase inverter is carried out to validate the performance of the proposed design
Pre-processing technique of Aquilaria species from Malaysia for four different qualities
Get PDFThe paper interprets data distribution by using boxplot pre-processing in classify the quality of Agarwood oil for eleven chemical substances into four different qualities. The varieties usage of Agarwood oil makes it considered as an expensive and valuable product on the essential oil market. Perfumes, fragrances, incense, aromatherapy, and traditional medicine are the most popular Agarwood oil applications. However, the classification of Agarwood oil grades does not yet have standard grading method. This because it has been graded manually into different qualities by using human sensory evaluation. Boxplot analysis involving eleven chemical subtances that will be focusing in this study by concerned the quality for low, medium low, medium high and high. ɤ-eudesmol, ar-curcumene, β-dihydro agarofuran, ϒ-cadinene, α-agarofuran, allo aromadendrene epoxide, valerianol, α-guaiene, 10-epi-ɤ-eudesmol, β-agarofuran, and dihydrocollumellarin compounds are the selected significant compounds that represent the input for boxplot. Agarwood oil consist 660 data samples from low, medium low, medium high, and high quality. The result in this study showed that the four selected significant compounds (ɤ-eudesmol, 10-epi-ɤ-eudesmol, β-agarofuran, and dihydrocollumellarin) are important as a marker for Agarwood oil quality classification. The identification of chemical substances on high quality done as reference for future research studies