Indonesian Journal of Electrical Engineering and Computer Science
Not a member yet
9109 research outputs found
Sort by
Optimizing dynamic response and stability of pressure-controlled swash plate type axial piston pump
Get PDFThe main objective of the paper is to explore the role of lead-lag compensators in improving the performance of control systems for variable delivery hydraulic axial piston pumps (VAPP). These compensators offer a range of benefits, including stability enhancement, transient response optimization, frequency response modification, disturbance rejection, and robustness improvement. A mathematical model of the hydro-mechanical system is developed, and the transfer function for the dynamic system is established. The simulation of the model with lead-lag compensator significantly enhanced the phase margin to 55.70 and gain margin to 12.3 dB ensuring robust control for pressure-controlled VAPP, whereas the uncompensated system is marginally stable. The compensated system exhibits better transient and steady-state response. The optimized lead-lag compensated system achieves a maximum percentage overshoot of 12.1% and a settling time of 1.95 sec. This is a substantial improvement compared to the uncompensated system with a maximum % overshoot of 20.5% and a settling time of 2.39 sec. The improved response tends to induce greater damping (ζ) in the compensated system from 0.015 to 0.108 and increases leakage coefficient (K) from 3.38×10-12 m3/Pa.s to 24.34×10-12 m3/Pa.s. Optimized lag-lead compensator ensures stability, responsiveness adapting effectively to dynamic operating conditions of VAPP for aerospace application
Breast cancer prediction using genetic algorithm and sand cat swarm optimization algorithm
Get PDFBreast cancer is the second leading type of cancer, which is mainly found in women and which increases the death rate among women. Early detection and diagnosis of breast cancer can reduce its occurrence and the death rate. Unfortunately, even if cancer treatment is initiated quickly after diagnosis, cancer may relapse because cancer cells may continue to exist in the body, which is also a major problem faced by women who fear facing the same treatment twice. So, detecting cancer at its early stage and predicting the recurrence of it is a major issue in the medical field that needs to be solved. Machine learning (ML) algorithms such as support vector machine (SVM), random forest (RF), k-nearest neighbor (KNN), and voting classifier (VC) are used for breast cancer prediction. Due to high-dimension data, the predicted results using Machine learning algorithms will increase the errors and decrease the accuracy. So, bioinspired algorithms such as the genetic algorithm (GA) and sand cat swarm optimization (SCSO) are used to reduce the data dimension. Convolutional neural network (CNN) is used for feature extraction from the image dataset. CNN algorithms are used for feature selection, which selects the important features for classification and prediction by applying 10 cross-validation methods. The proposed model using bioinspired optimization algorithms outcomes will yield high accuracy and the best solution
Identification of ocular disease from fundus images using CNN with transfer learning
Get PDFEye diseases are one of the serious health problems affecting human life. Detecting and diagnosing them early is critical to prompt treatment and preventing vision loss. However, all studies in the field of eye disease classification using machine learning models are limited to the detection of single diseases, and the accuracy rate is still low in multi-class systems. In this study, we propose a multi-class classification model using four pre-trained CNNs (DenseNet121, ResNet50, EfficientNetB3 and VGG16). The model classified eye diseases into four categories: diabetic retinopathy, cataract, glaucoma, and normal. To improve the training process, another data augmentation technique is applied to increase the amount of data. The performance metrics of the system are calculated using the confusion matrix. DenseNet-121 shows excellent performance in retinal disease classification in 30 epochs of training, with training and test accuracy reaching 99.97% and 96.21% respectively. The implementation of this system should be considered as a very useful means to help ophthalmologists to rapid and precision detection of various eye diseases in the future
Performance analysis of 10 machine learning models in lung cancer prediction
Get PDFLung cancer is one of the diseases with the highest incidence and mortality in the world. Machine learning (ML) models can play an important role in the early detection of this disease. This study aims to identify the ML algorithm that has the best performance in predicting lung cancer. The algorithms that were contrasted were logistic regression (LR), decision tree (DT), k-nearest neighbors (KNN), gaussian Naive Bayes (GNB), multinomial Naive Bayes (MNB), support vector classifier (SVC), random forest (RF), extreme gradient boosting (XGBoost), multilayer perceptron (MLP) and gradient boosting (GB). The dataset used was provided by Kaggle, with a total of 309 records and 16 attributes. The study was developed in several phases, such as the description of the ML models and the analysis of the dataset. In addition, the contrast of the models was performed under the metrics of specificity, sensitivity, F1 count, accuracy, and precision. The results showed that the SVC, RF, MLP, and GB models obtained the best performance metrics, achieving 98% accuracy, 98% precision, and 98% sensitivity
Recognition of plant leaf diseases based on deep learning and the chemical reaction optimization algorithm
Get PDFAgriculture plays a crucial role in developing countries such as Vietnam, where 70 percent of the population is employed in agriculture, and 57 percent of the social labor force works in the agricultural sector. Therefore, crop productivity directly affects the lives of many people. One of the primary reasons for reduced crop yields is plant leaf diseases caused by bacteria, fungi, and viruses. Hence, there is a need for a method to help farmers identify leaf diseases early to take appropriate action to protect crops and shift to smart agricultural production. This paper proposes lightweight deep learning (DL) models combined with a support vector machine (SVM), with hyperparameters fine-tuned by chemical reaction optimization (CRO), for detecting plant leaf diseases. The main advantage of the method is the simplicity of the architecture and optimization of the DL model’s hyperparameters, making it easily deployable on low hardware devices. To test the performance of the proposed method, experiments are performed on the PlantVillage dataset using Python. The superiority of the proposed method over the well-known visual geometry group-16 (VGG-16) and MobileNetV2 models is demonstrated by a 10% increase in accuracy prediction and a decrease of 5% and 66% in training time, respectively
Optimized dense convolutional network with conditional autoregressive value-at-risk for chronic kidney disease detection through group-based search
Get PDFChronic kidney disease (CKD) is the gradual decrease in renal functionality that leads to kidney failure or damage. This disease is the most severe worldwide health condition that kills numerous people every year as an outcome of hereditary factors and worse lifestyles. As CKD progresses, it becomes difficult to diagnose. Utilizing regular doctor consultation data for evaluating diverse phases of CKD can assist in earlier detection and timely inference. Furthermore, effectual detection methods are vital owing to an increased count of patients with CKD. Here, group search conditional autoregressive value-at-risk based dense convolutional network (GSCAViaR-DenseNet) is introduced for CKD detection. Firstly, chronic data is acquired from the dataset and Min-Max normalization is utilized to pre-process considered chronic kidney data. Thereafter, feature selection (FS) is performed based on Topsoe similarity. Lastly, CKD detection is executed by dense convolutional network (DenseNet) and group search conditional autoregressive value-at-risk (GSCAViaR) is employed to train DenseNet. However, GSCAViaR is designed by incorporating a group search optimizer (GSO) with a conditional autoregressive value-at-risk (CAViaR) model. Additionally, GSCAViaR-DenseNet acquired a maximal accuracy of about 91.5%, sensitivity of about 92.8% and specificity of about 90.7%
A review based on sentimental analysis for Hindi language
Get PDFThe 'Mother Tongue' of India is considered to be Hindi. The demand for Hindi content rises as the Indian population grows. Hindi is typically used when Indians express their opinions about something. This generates data in Hindi that may later be analyzed. Sentiment analysis (SA) is a category for one of the analyses. SA examines how a speaker or author's emotions, sentiments, and attitudes are expressed in a particular text. SA, occasionally referred to as "Opinion Mining," is a sort of contextual mining that uses algorithmic recognition and categorization to detect the viewpoints expressed in a text and determine whether they are positive, negative, or neutral. Word polarity, that SA gives, enables us to assess the text's impact and decide if it is good or negative. It is possible to implement SA using a variety of methods. There was a lot of study on SA in the English language, but not as much for Hindi. In this essay, SA studies regarding the Hindi language are reviewed and analyzed
HorseNet: a novel deep learning approach for horse health classification
Get PDFIn equestrian sports and veterinary medicine, horse welfare is paramount. Horse tiredness, lameness, colic, and anemia can be identified and classified using deep learning (DL) models. These technologies analyze horse images and videos to help vets and researchers find symptoms and trends that are hard to see. Early detection and better treatment of certain disorders can improve horses’ health. DL models can also improve with new data, improving diagnosis accuracy and efficiency. This study comprehensively evaluates three convolutional neural network (CNN) models to distinguish normal and abnormal horses using the generated horse dataset. For this study, a unique dataset of horse breeds and their normal and abnormal states was collected. The dataset includes mobility patterns from this study’s initial data collection. DL models like CNNs and transfer learning (TL) models (visual geometry group (VGG)16, InceptionV3) were employed for categorization. The InceptionV3 model outperformed CNN and VGG16 with over 97% accuracy. Its depth and multi-level structure allow the InceptionV3 model to recognize characteristics in images of varied scales and complexities, explaining its excellent performance
Advancing airway management for ventilation optimization in critical healthcare with cloud computing and deep learning
Get PDFImproving patient outcomes in critical care settings is significantly connected to effective ventilation control. This research introduces a new method for improving ventilation methods in critical healthcare utilizing a long short-term memory (LSTM) network hosted in the cloud. Ventilators, pulse oximeters, and capnography are just a few examples of medical equipment that input data into the system, which then uploads the data to the cloud for analysis. The LSTM network can learn from data patterns and correlations, drawing on respiratory parameters' time dynamics, to provide real-time suggestions and predictions for ventilation settings. The system aims to improve clinical results and reduce the risk of ventilator-induced lung damage by tailoring ventilation techniques according to each patient's requirements and by forecasting potential issues. Due to remote monitoring technology, medical professionals can quickly analyze their patient's conditions and act accordingly. The system allows for continuous improvement using iterative learning of more data and feedback. With the ability to optimize breathing and enhance patient care in critical healthcare situations, a hopeful development in airway management is needed
Video mosaic: employing an efficient ORB feature extraction technique with hamming distance matching for enhanced performance
Get PDFVideo mosaicing is a computer vision and image processing technique used to create a panoramic or wide-angle view from a sequence of video frames. The goal is to seamlessly combine multiple video frames to form a larger and more comprehensive view of a scene. In recent years, the field of image processing has witnessed a growing interest in video mosaic research owing to its application in surveillance and defense applications. This paper introduces an automatic algorithm for video mosaic creation, addressing the alignment and blending of non-overlapping frames within each input video. The proposed algorithm navigates through several key steps to achieve a seamless and continuous mosaic, particularly tackling issues related to camera motion and content variations across frames. The effect of the good number of matches to be chosen while performing frame stitching is evaluated. The proposed algorithm effectively produces a video mosaic with aligned and blended non-overlapping frames, resulting in a visually continuous mosaic. The output video serves as a testament to the algorithm’s prowess in addressing challenges related to video frame alignment and blending