Indonesian Journal of Electrical Engineering and Informatics (IJEEI)
Not a member yet
776 research outputs found
Sort by
Acute Lymphoblastic Leukemia Blood Cells Prediction Using Deep Learning & Transfer Learning Technique
Get PDFWhite blood cells called lymphocytes are the target of the blood malignancy known as acute lymphoblastic leukemia (ALL). In the domain of medical image analysis, deep learning and transfer learning methods have recently showcased significant promise, particularly in tasks such as identifying and categorizing various types of cancer. Using microscopic pictures, we suggest a deep learning and transfer learning-based method in this research work for predicting ALL blood cells. We use a pre-trained convolutional neural network (CNN) model to extract pertinent features from the microscopic images of blood cells during the feature extraction step. To accurately categorize the blood cells into leukemia and non- leukemia classes, a classification model is built using a transfer learning technique employing the collected features. We use a publicly accessible collection of microscopic blood cell pictures, which contains samples from both leukemia and non-leukemia, to assess the suggested method. Our experimental findings show that the suggested method successfully predicts ALL blood cells with high accuracy. The method enhances early ALL detection and diagnosis, which may result in better patient treatment outcomes. Future research will concentrate on larger and more varied datasets and investigate the viability of integrating it into clinical processes for real-time ALL prediction
Examination on the Denoising Methods for Electrical and Acoustic Emission Partial Discharge Signals in Oil
Get PDFPartial discharge (PD) measurements either through electrical or acoustic emission approaches can be subjected to noises that arise from different sources. In this study, the examination on the denoising methods for electrical and acoustic emission PD signal is carried out. The PD was produced through needle-plane electrodes configuration. Once the voltage reached to 30 kV, the electrical and acoustic emission PD signals were recorded and additive white Gaussian noise (AWGN) was introduced. These signals were then denoised using moving average (MA), finite impulse response (FIR) low/high-pass filters, and discrete wavelet transform (DWT) methods. The denoising methods were evaluated through ratio to noise level (RNL), normalized root mean square error (NRMSE) and normalized correlation coefficient (NCC). In addition, the computation times for all denoising methods were also recorded. Based on RNL, NRMSE and NCC indexes, the performances of the denoising methods were analyzed through normalization based on the coefficient of variation (). Based on the current study, it is found that DWT performs well to denoise the electrical PD signal based on the RNL and NRMSE index while MA has a good denoising NCC and computation time index for acoustic emission PD signal
The Success Factors in Measuring the Millennial Generation’s Energy-Saving Behavior Toward the Smart Campus
Get PDFThe millennial generation has a pivotal role in leading the industrial digital revolution. Energy-saving behavior and millennials’ awareness of energy consumption for educational context become crucial in performing a smart campus. This study tries to identify the success factors in measuring the millennial generation’s energy-saving Behavior toward the smart campus. The measurement model considers two significant constructs, including energy-saving attitudes with energy-saving education (organizational saving climate); energy-saving education and environment knowledge (personal saving climate); and energy-saving information publicity as sub-indicators, and construct energy-saving Behavior viz sub-indicators Behavior regarding energy and behavior control. In order to determine the preference level of each indicator and sub-indicator, the Fuzzy Analytical Hierarchy Process (Fuzzy-AHP) approach was executed by disseminating the questionnaire to 100 respondents from energy practitioners, students, and academicians in Indonesia. The calculation reveals that the energy-saving behavior construct has a higher priority value (0.94) than the energy-saving attitude (0.06). Meanwhile, energy-saving education and environment knowledge (personal saving climate) have been analyzed at the cutting-edge sub-indicator, followed by energy-saving information publicity and education (organizational saving climate). In addition, the sub-indicator for behaviors regarding energy becomes more demanding compared to behavioral control. As a novelty, the priority analysis of this Model aids the management of the campus and government in developing smart campus policies and governance. This Model can be used as a guideline for the management level to execute the smart campus practices. Thus, the effectiveness and optimization of smart campus transformation can be cultivated and accelerated. Besides, the potential coming of risks can be avoidable
Efficient Pavement Crack Detection and Classification Using Custom YOLOv7 Model
Get PDFIt is crucial to detect and classify pavement cracks as part of maintaining road safety. The inspection process for identifying and classifying cracks manually is tedious, time-consuming, and potentially dangerous for inspectors. As a result, an efficient automated approach for detecting road cracks is essential for this development. Numerous issues, such as variations in intensity, uneven data availability, the inefficacy of traditional approaches, and others, make it challenging to accomplish. This research has been carried out to contribute towards developing an efficient pavement crack detection and classification system. This study uses state of the art deep learning algorithm, customized YOLOv7 model. Data from two sources, RDD2022, a publicly available online dataset, and the second set of data gathered from the roads of Malaysia have been used in this investigation. In order to have balanced data for training, many image preprocessing techniques have been applied to the data, such as augmentations, scaling, blurring, etc. Experimental results demonstrate that the detection accuracy of the YOLOv7 model is significant, 92% on the RDD2022 dataset and 88% on our custom dataset. This study reports the outcomes of experiments conducted on both datasets. RDD2022 achieved a precision of 0.9523 and a recall of 0.9545. On the custom dataset, the resulting values for precision and recall were 0.93 and 0.9158, respectively. The results of this study were compared to those of other recent studies in the same field in order toestablish a benchmark. Results from the proposed system were more encouraging and surpassed the benchmarking ones.
Mixed-type Variables Clustering for Learners’ Behavior in Flipped Classroom Implementation
Get PDFNumerous approaches have been developed to group learners’ behavior in an online/blended learning environment. However, most clustering analyses in this particular field only consider numeric features despite the existence of categoric features that are found important in other studies. In this study, we compare K-Means and K-Prototypes algorithms to cluster learners’ behavior in a flipped classroom implementation. From the model selection, we found that the model produced by the K-Prototypes algorithm — which included categoric features — is a better one. The statistical analysis of the clustering results of the selected K-Prototypes model shows significant differences in most of the inter-cluster comparisons, implying a good separation of the data. More importantly, we can identify the behavior in each cluster which then can be used to help learners in achieving better results in learning
A Review on VANET Security: Future Challenges and Open Issues
Get PDFVehicular Adhoc Network (VANET) is an established technology that is well-suited for emerging technologies such as the Internet of Vehicles (IoV) and Unmanned Aerial Vehicles (UAVs). However, while VANET offers improved methods for addressing contemporary technology, it also presents significant challenges in providing adequate security measures for intended access. VANET operates on multiple execution platforms, such as roadside units, vehicle-tovehicle, vehicle-to-device, and vehicle-to-everything (V2X) communication. As a result, VANET must establish robust security measures for future purposes and strengthen protocol authentications to ensure secure data delivery and network-wide execution. In this work, we provide an overview of some of the recent security problems faced by VANET to raise awareness among developers and engineers about the specific security needs of VANET and how to avoid errors or intrusions when deploying VANETs in cities and urban areas. We cover topics such as the classification of security attacks, standard or security protocol problems and solutions, and the best feasible security criteria for extended VANETs. Finally, we discuss open issues and future VANET security developments or concerns
Innovative Emerging Ontology-driven Frameworks: A Systematic Literature Review
Get PDFPrevious research has shown that ontologies and related semantic web technologies have positioned themselves as good solutions for data integration and resource reusability. Pitfalls and traps in modelling domains can be avoided if researchers and scholars adopt and use ontology-driven frameworks for their research. This research work aims to review currently developed or proposed ontology-driven frameworks, and clearly illustrate their development, application, and practicality. The review then ultimately addresses three main research questions driving the literature review through a synthesis of information that exists about ontology-driven frameworks. Search strings were used to obtain articles from online electronic databases. The PRISMA chart was used for the final selection of the 60 articles for review. A method of scoring called the Assessment of Multiple System Reviews (AMSTAR) was used on the included studies for quality assessment. The AMSTAR mean overall result was 9, the median 10, and the standard deviation 0.99. The results reveal a downward trend of ontologies in 2010, with Web Ontology Language (OWL) being the most used language for ontology-driven frameworks and systems, with over 70% usage
Techniques for Improving the Performance of Unsupervised Approach to Sentiment Analysis
Get PDFIn this work, few techniques were proposed to enhance the performance of unsupervised sentiment analysis method to categorize review reports into sentiment orientations (positive and negative). In review reports, generally negations can change the polarity of other terms in a sentence. Therefore, a new technique for handling negations was proposed. As it is seen that, the positions of terms in a report are also important i.e. the same term appearing at different positions in a report may convey different amount of sentiments. Thus, a new technique was proposed to assign weights to the terms depending on their positions of occurrences within a review. Again, another technique was proposed to use the presence of exclamatory marks in the reviews as the effects of exclamatory marks are equally important in categorizing review reports. After incorporating all these concepts in the first phase of the proposed method, in the second phase, analysis of sentiment orientations was done using cluster ensemble method. The proposed method was tested on a state-of-the-art Movie review dataset and 91.75% accuracy was achieved. A significant improvement over some of the unsupervised and supervised methods in terms of accuracy was achieved with incorporation of the new techniques
Improved Sensor Fault-Tolerant Control Technique Applied to Three-Phase Induction Motor Drive
Get PDFAn improved fault-tolerant control (FTC) method using mathematical functions is applied to the induction motor drive (IMD) against current sensors and speed encoder failures, which occur when the sensor is disconnected or completely damaged. The IMD with two current sensors and an encoder is speed controlled based on the field-oriented control (FOC) technique in regular operation. In this paper, an FTC unit is implemented in the FOC controller to detect and solve the sensor fault to increase the reliability of the speed control process. The measured stator currents and the feedback speed signal are integrated into the diagnosis algorithms to create a sensor fault-tolerant control function. Three diagnosis functions operating in a defined sequence are proposed for determining the health status of current and speed sensors. The FTC function performs isolation and replaces the faulty sensor signals with the proper estimated signals; then, the IMD will operate in the corresponding sensorless mode. Simulations will be performed to verify the accuracy and reliability of the proposed method under various sensor faults
Reduction of Emission Cost, Loss Cost and Energy Purchase Cost for Distribution Systems With Capacitors, Photovoltaic Distributed Generators, and Harmonics
Get PDFIn this paper, a bonobo optimizer (BO) and two other methods, particle swarm optimization (PSO) and salp swarm algorithm (SSA), are implemented to determine the location and sizing of photovoltaic distributed generators (PDGs) and capacitors in IEEE 69-bus radial distribution system with many nonlinear loads. The objective of the study is to minimize the costs for purchasing energy from main grid for load demand and power loss on transmission lines as well as cost for emission fines from fossil fuel generation units of the grid under considering strict constraints on penetration, voltage, current and harmonic distortions. The results have shown that BO is the best and most stable method in solving the considered optimization problem. With the use of the optimal solution from BO, the total cost is significantly reduced up to 80.52%. As compared to base system without capacitors and PDGs, the obtained solution can reduce power loss up to 94.48% and increase the voltage profile from the range of [0.9092 1.00] pu to higher range of [0.9907 1.0084] pu. In addition, total harmonic distortion (THD) and individual harmonic distortion (IHD) are also much improved and satisfied under the IEEE Std. 519. Thus, BO is a suitable method for the application of installing capacitors and PDGs in distribution systems