Indonesian Journal of Electrical Engineering and Computer Science
Not a member yet
9109 research outputs found
Sort by
CNN-CatBoost ensemble deep learning model for enhanced disease detection and classification of kidney disease
Get PDFAn efficient deep-learning prediction model for identifying chronic kidney disease (CKD) from exhaled breath is presented in this paper. The concentration of urea will be higher in CKD patients. Salivary urease breaks down the stored urea into ammonia, which is then excreted through breath. Thus, by monitoring the breath ammonia content, it is possible to identify the presence of high urea levels in the body. In this work, a novel sensing module is developed and applied to measure and assess the amount of ammonia in exhaled breath. Moreover, an effective deep learning prediction model that combines the CatBoost algorithm and convolutional neural network (CNN) is used to automate the prediction of disease. The proposed model, which combines the benefits of gradient-boosting and CNN, attained an exceptional accuracy of 98.37%. Experiments are conducted to evaluate the proposed model using real-time data and to assess how well it performs in comparison with existing deep learning methods. Our study's findings demonstrate that kidney disease can be accurately and noninvasively diagnosed using the proposed approach
Revolutionizing healthcare image analysis in pandemic-based fog-cloud computing architectures
Get PDFHealthcare data analysis has become essential after epidemic outbreaks. The manual examination of medical images such as X-rays and computed tomography (CT) scans became one of these challenges. This paper introduces a healthcare architecture that tackles the analysis efficiency and accuracy challenges by harnessing artificial intelligence (AI) capabilities. This architecture utilizes fog computing and presents a modified convolutional neural network (CNN) designed specifically for image analysis. Different architectures of CNN layers are thoroughly explored and evaluated to optimize overall performance. To demonstrate the effectiveness of the proposed approach, a dataset of X-ray images is utilized for analysis and evaluation. Comparative assessments are conducted against recent models such as VGG16, VGG19, MobileNet, and related research papers. Notably, the proposed approach achieves an exceptional accuracy rate of 99.88% in classifying normal cases, accompanied by a validation rate of 96.5%, precision and recall rates of 100%, and an F1 score of 100%. These results highlight the immense potential of fog computing and modified CNNs in revolutionizing healthcare image analysis and diagnosis, not only during pandemics but also in the future. By leveraging these technologies, healthcare professionals can improve the efficacy and accuracy of medical image analysis, leading to improved patient care and outcomes
Cell nuclei image segmentation using U-Net and DeepLabV3+ with transfer learning and regularization
Get PDFSemantic nuclei segmentation is a challenging area of computer vision. Accurate nuclei segmentation can help medics in diagnosing many diseases. Automatic nuclei segmentation can help medics in diagnosing many diseases such as cancer by providing automatic tissue analysis. Deep learning algorithms allow automatic feature extraction from medical images, however, hematoxylin and eosin (H&E) stained images are challenging due to variability in staining and textures. Using pre-trained models in deep learning speeds up development and improves their performance. This paper compares Deeplabv3+ and U-Net deep learning methods with the pre-trained models ResNet-50 and EfficientNetB4 embedded in their architecture. In addition, different regularization and dropout parameters are applied to prevent overtraining. The experiment was conducted on the PanNuke dataset consisting of nearly 8,000 histological images and annotated nuclei. As a result, the ResNet50-based DeepLabV3+ model with L2 regularization of 0.02 and dropout of 0.7 showed efficiency with dice coefficient (DCS) of 0.8356, intersection over union (IOU) of 0.7280, and loss of 0.3212 on the test set
A quality control system for logistic ports goods movable harbor cranes based on internet of things and deep learning
Get PDFThe growth of commercial activity and the transportation of goods around the world has increased the challenges of stevedoring within ports. In case of loading and unloading ships safely, quickly, and efficiently, goods movable harbor cranes play an important role. This work aims to propose an industrial internet of things (IIoT)-based quality control system for logistic services ports goods movable harbor crane (QC-GMHC). The GMHC system based on using programmable logic controller (PLC), along with a multi-sensor data collecting system. Several operations have been done to establish the QC-GMHC system as: GMHC sensors real-time data storage, and data sharing; monitoring the GMHC status (remote-local); and the efficiency reporting. In order to validate the proposed system’s hardware, it was used in an already operational GMHC for six months, during which data were collected and analyzed. The results revealed that the proposed hardware system worked efficiently for 24 hours. To forecast the efficiency of the GMHC, a deep learning (DL) conventional long short-term memory (LSTM) and neural network model was trained and validated using synthetic data generated from acquired real data. The results showed that QC-GMHC can calculate efficiency with an accuracy of 80%, which is sufficient for our application
Cervical cancer: empowering diagnosis with VGGNet transfer learning
Get PDFThis study addresses the critical issue of cervical cancer, which stands as the fourth most prevalent cancer among women. With early detection being pivotal for successful treatment, the research focuses on evaluating the effectiveness of deep learning-based models in cervical cancer detection. Leveraging the widely employed Papanicolaou (Pap) smear test, the study proposes a transfer learning approach, incorporating contrast limited adaptive histogram equalization for image enhancement. Convolutional neural network models, including AlexNet, visual geometry group (VGGNet)-16, and VGGNet-19, are employed to accurately distinguish between cancerous and non-cancerous cervical cell images. The evaluation metrics encompass accuracy, precision, sensitivity, specificity, F1-score, and the matthew correlation coefficient (MCC). Notably, the findings reveal the exceptional performance of the VGGNet-19 model, achieving an accuracy of 98.71%, sensitivity of 98.33%, and specificity of 99% for a single smear cell. This research marks a significant advancement in the application of deep learning for precise cervical cancer detection. The promising results underscore the potential of these models to enhance early diagnosis and contribute to improved treatment outcomes, thereby addressing a crucial aspect of women's health
Single nucleotide polymorphism based on hypertension potential risk prediction using LSTM with Adam optimizer
Get PDFRecent healthcare research has focused a great deal of interest on using genetic data analysis to predict the risk of hypertension. This paper presents a unique method for accurately predicting the vulnerability to hypertension by utilizing single nucleotide polymorphism (SNP) data. We present a novel neural network design utilizing the adaptive moment (Adam) optimizer to describe the intricate temporal correlations in SNPs. The study used a dataset with carefully preprocessed SNP data from a broad cohort for model input. The long short-term memory (LSTM) network was methodically built and trained with hyper-parameter and fine-tuning using the Adam optimizer to converge on ideal weights. Our findings indicate encouraging predictive performance, highlighting the suggested methodology’s usefulness in determining hypertension risk factors. The result showed that the proposed method achieved stability in the performance of 89% accuracy, 96% precision, 88% recall, and 92% F1-score. Due to its higher accuracy and greater predictive power, our SNP-based LSTM methodology is superior to the conventional machine learning method. By providing a novel framework that uses genetic data to predict the risk of hypertension, this research makes substantial contribution to the field of predictive healthcare. This framework helps with early intervention and customized preventative efforts
HybridCSF model for magnetic resonance image based brain tumor segmentation
Get PDFThe human brain comprises a complex interconnection of nerve cells and vital organs, which regulates crucial bodily processes. Although neurons commonly undergo developmental stages, they may occasionally experience abnormalities, leading to abnormal growths known as brain tumors. The objective of brain tumor segmentation is to produce precise boundaries of brain tumor regions. This study extensively analyzes deep learning methods for brain tumor detection, evaluating their effectiveness across diverse datasets. It introduces a hybrid model, which is proposed by the name HybriCSF: hybrid convolutional-SVM-fuzzy C-means model combining convolutional neural network (CNN) with the classifier support vector machine (SVM) and clustering technique fuzzy C-means (FCM). The proposed model was implemented on Br35H, BraTs 2020 and BraTs2021 datasets. The suggested model outperformed the existing methods by achieving 98.6% of accuracy on Br35H dataset and dice score of 0.63, 0.87, 0.81 on BraTs 2020 dataset for enhancing tumor (ET), whole tumor (WT), and tumor core (TC), respectively. The achieved dice scores on the BraTs 2021datasets are 0.89, 0.95, and 0.89 for ET, WT, and TC, respectively. The results show that the suggested model HybriCSF outperforms the other CNN-based models in terms of accuracy
Optimal proportional-integral speed control for closed-loop engine timing system
Get PDFIn internal combustion engines, adjusting the air-fuel ratio is essential to control the speed and minimize the burnt fuel. The throttle opening is the actuator to control the air-fuel. A better design for the used/conventional controller can give a better response without additional cost. In this work, the proposed controller gains of the proportional-integral (PI) controller are tuned to enhance the speed in constant and variable drive cycle modes. The tuning process is conducted based on two of the most efficient performance indices used in this field. The performance indices are integral absolute error (IAE) and integral time absolute error (ITAE). The optimization problem is solved using three reliable stochastic optimization algorithms to ensure mature convergence of the solutions, to avoid local optima solutions, and to ensure effective shrinking of the search space. The optimization algorithms are teaching-learning-based optimization (TLBO), particle swarm optimization (PSO), and genetic algorithm (GA). Different simulations are conducted to validate the results. The results are compared with conventional tuning methods regarding the system's time response
Novel modified Chernobyl disaster optimizer for controlling DC motor
Get PDFThis article presents the modified Chernobyl disaster optimizer (CDO) method for DC motor control to find the optimal proportional integral derivative (PID) settings. DC motors are widely used machinery. DC motors are also simple to use. The detonation of the Chernobyl nuclear reactor core served as the inspiration for the idea and guiding principles of the CDO. CDO has limitations in the stability of exploration and exploitation areas. This research aims to obtain a new balance of exploration and exploitation. This study suggests incorporating the levy flight and chaotic algorithm (CA) techniques to enhance the CDO method. This study was conducted with the MATLAB/Simulink software. A comparative technique, which included the marine predator algorithm (MPA), golden jackal optimization (GJO), and CDO, was utilized to determine the performance of the MCDO method. According to the study’s findings, the MCDO method’s overshoot value outperformed all other approaches
Improvement of electricity reliability on the 330 kV Nigeria transmission network with static synchronous compensators
Get PDFThe increasing demand for power has caused distortions in Nigeria’s 330 kV transmission network. This is a result of the bulk of the lines being heavily loaded at the moment, which leads to voltage drops and inconsistent electrical delivery. To ensure system reliability, it is therefore crucial to make sure that the system maintains a constant state under specific conditions. This research presents the use of static synchronous compensators (STATCOM) in the Nigerian 330 kV transmission network to reduce power loss and improve the voltage profile. To solve the problem of insufficient voltage and power losses, a three-phase network is simulated using the MATLAB/Simulink software. A three-level, 48- pulse STATCOM was employed to rectify the problem after weak buses were identified through load flow analysis. A 48- pulse converter that handled the STATCOM was used to control harmonic distortions in the system. The outcomes show how crucial the reactive power control mechanism is for regulating the system’s harmonics. However, the method was able to achieve real and reactive power losses of 12.5%. The STATCOM’s 3-level 48- pulse converter also resulted in a total 4.64% reduction in total harmonic distortion (THD)