Indonesian Journal of Electrical Engineering and Informatics (IJEEI)
Not a member yet
776 research outputs found
Sort by
Review of Intelligent Control Systems with Robotics
Get PDFInteractive between human and robot assumes a significant job in improving the productivity of the instrument in mechanical technology. Numerous intricate undertakings are cultivated continuously via self-sufficient versatile robots. Current automated control frameworks have upset the creation business, making them very adaptable and simple to utilize. This paper examines current and up and coming sorts of control frameworks and their execution in mechanical technology, and the job of AI in apply autonomy. It additionally expects to reveal insight into the different issues around the control frameworks and the various approaches to fix them. It additionally proposes the basics of apply autonomy control frameworks and various kinds of mechanical technology control frameworks. Each kind of control framework has its upsides and downsides which are talked about in this paper. Another kind of robot control framework that upgrades and difficulties the pursuit stage is man-made brainpower. A portion of the speculations utilized in man-made reasoning, for example, Artificial Intelligence (AI) such as fuzzy logic, neural network and genetic algorithm, are itemized in this paper. At long last, a portion of the joint efforts between mechanical autonomy, people, and innovation were referenced. Human coordinated effort, for example, Kinect signal acknowledgment utilized in games and versatile upper-arm-based robots utilized in the clinical field for individuals with inabilities. Later on, it is normal that the significance of different sensors will build, accordingly expanding the knowledge and activity of the robot in a modern domai
A Novel 2DOF Fractional Controller for Wind-Solar Integrated Power System
Get PDFPower system is an integration of many power generating units with continuous load variation due to which the frequency of the power system changes. Using traditional proportional integral (PI) controllers, frequency transients are reduced, and with sufficient time delay zero steadystate error is obtained. In this proposed research article, a three-area thermal plant system with wind and solar photovoltaic power generating systems is considered. This integration of renewable system will lead to the frequency transients which has to be addressed seriously. To improve the frequency profile of this diverse-source interconnected power system, a novel two degree of freedom proportional fractional integral double derivative (2-DOF-PFIDD) controller is proposed. The integral square error (ISE) cost function is utilized to discover the best parameter gains of the proposed controller using the intelligent water drops algorithm (IWDs). The benefits of the proposed controller are evaluated using an IEEE-39 bus system with wind and solar photovoltaic (SPV) generation. Uncertainties in the wind and solar power system characteristics such as wind speed and irradiance are considered. Comparisons with typical proportional integral derivative (PID), two degree of freedom proportional integral derivative (2-DOF PID), and 2-DOF-PIDD controllers are presented to demonstrate the efficacy of proposed controller for improving the frequency and tie-line power profiles
Forward Body Biased Low Power 4.0-10.6 GHz Wideband Low Noise Amplifier
Get PDFA forward body biased low power Low Noise Amplifier (LNA) is designed using Common Gate (CG) topology. By using current reuse technique between the first stage and second stage Common Source topology accompanied with forward body biasing leads to low power dissipation. A series to parallel tank circuit at this stage leads to wideband design. A shunt peaking inductor at the drain terminal of second stage causes the higher frequency peak to increase leading to wide bandwidth. Two CS cascade stages are used to increase the overall gain of the proposed LNA with a buffer stage at the output for output matching. The proposed LNA attained maximum gain of 26.39 dB with a gain greater than 16 dB over entire range. The circuit gives reflection coefficient less than – 10 dB with NF 2.7 dB. With Vdd of 0.925 V, a DC current of 8.32 mA is consumed giving 7.7 mW power consumption
Fruits Disease Classification using Machine Learning Techniques
Get PDFDue to increased population, there is a high demand for agricultural products these days and therefore, effective growth and increased fruit production have become critical. Consequently, for better fruit yield cultivators employ traditional methods for monitoring fruit yield from harvest till ripening of fruit. However, manual monitoring and visual inspection doesn’t always bring the actual identification of fruit disease due to variety of reasons, such as less knowledge about pathogens, requiring more time for disease analysis and that too with less accuracy and so on, consequently, leaving for the need of a professional assistance and expertise. Moreover, the task also becomes difficult as various fruits demonstrate their gesticulation by changing the colour of their skin which can come from nature and resulting in various black or dark brown spots on the fruit skin indicating various diseases. As a result, it is necessary to propose an efficient smart farming strategy that will aid in increased productivity while at the same time involving less human effort. The proposed research work attempts to classify the fruit disease at its early stage by using machine learning techniques. For this purpose, fruit’s texture, and skin colour have been utilized. The approach fundamentally employs three machine learning classifier algorithms - KNN, Decision Tree, and Random Forest. Whereas the features have been determined by using three prominent feature extractors - Haralick, Hu Moments and colour histogram. Finally, the system has been evaluated by utilizing the k-fold cross validation method. Specimen dataset was divided into two groups — the training subset and the test subset. As a rule, four-fold cross-validation, three-fourths of the images were used for training the models whereas, the remaining one-fourth were used for testing purposes. Assessment results for suggested methodology after conducting experimentation on publicly available dataset and drawn confusion matrix and learning cure shows that Random Forest classifiers achieves accuracy about 99% while for K-Means accuracy statistics stands at 98.67% and for Decision trees it is about 97.75% - for colour histogram features
A Comparison Between CCCV and VC Strategy for the Control of Battery Storage System in PV installation
Get PDFTo meet demand with unpredictable daily and seasonal variations, the power grid faces significant hurdles in transmission and distribution. Electrical Energy Storage (EES), in which energy is stored in a specific state, depending on the technology utilized, and is converted to electrical energy, is acknowledged as a technology involved with significant potential for solving these difficulties. This paper deals with the modeling and control of a renewable energy production system based on solar panel. To improve the performance of the investigated power generation system, a lithium-ion battery storage system and bidirectional converter are associated to a solar panel that is unable to compensate for rapid variations in load power demand. In this situation, to meet load power demand, a rule-based energy management algorithm is used to share energy between the grid and the energy production system. Furthermore, two solutions are developed and compared: VC (Variable Current) and CC-CV (Constant Current Constant Voltage). The VC approach is used in conjunction with an energy management and protection system, whereas the CC-CV method is used in conjunction with an artificial neural network (ANN). The simulation results show that the VC control strategy give greater energy performance and installation stability compared to the CC-CV strategy, but not improved safety and protection of lithium-ion batteries
On Reducing ShuffleNets’ Block for Mobile-based Breast Cancer Detection Using Thermogram: Performance Evaluation
Get PDFIn this paper, we proposed a reduced-block-Shufflenet (RB-ShuffleNet) for thermal breast cancer detection. RB-ShuffleNet is a modification of Shufflenet obtained by reducing blocks from the original architecture. The images for training and testing were obtained from Database for Mastology Research (DMR). First, we detected and cropped the image based on the region of interest (ROI), in which the ROI is determined by using the red intensity profile. Then, the ROI images were trained using RB-ShuffleNets. In the experiments, we built eight architectures, based on ShuffleNet, each with a different number of reduced blocks. The result showed that RB-Shufflenet with four reduced blocks had fewer than 50% of the learning parameters of the original Shufflenet, without compromising its performance. The RB-ShuffleNet with up to four reduced blocks could achieve 100% testing accuracy. Furthermore, The RB-ShuffleNets performed better than MobileNetV2 and resulted in higher accuracy when fed with ROI images. Due to its light structure and good performance, we recommend RB-ShuffleNet as mobile-based CNN model which is preferable to implement in breast cancer detection
Weightless Neural Networks Face Recognition Learning Process for Binary Facial Pattern
Get PDFThe facial recognition process is normally used to verify and identify individuals, especially during the process of analyzing facial biometrics. The face detection algorithm automatically determines the presence or absence of a face. It is, however, theoretically difficult to analyze the face of a system with limited resources due to the complex pattern of a face. This implies an embedded platform scheme which is a combination of several learning methods supporting each other is required. Therefore, this research proposed the combination of the Haar Cascade method for the face detection process and the WNNs method for the learning process. The WNNs face recognition Algorithm (WNNs-FRA) uses facial data at the binary level and for binary recognition. Moreover, the sample face data in the binary were compared with the primary face data obtained from a particular camera or image. The parameters tested in this research include detection distance, detection coordinates, detection degree, memory requirement analysis, and the learning process. It is also important to note that the RAM node has 300 addresses divided into three face positions while the RAM discriminator has three addresses with codes (00), (10), and (10). Meanwhile, the largest amount of facial ROI data was found to be 900 pixels while the lowest is 400 pixels. The total RAM requirements were in the range of 32,768 bytes and 128 bytes and the execution time for each face position was predicted to be 33.3% which is an optimization because it is 66.67% faster than the entire learning proces
Modelling of River Catfish (Cephalocassis Jatia) Population in Malaysia
Get PDFThis research presents the mathematical modeling of the economic cycle of fish-population structures in Malaysia. This paper shows how to develop a model of river catfish based on system dynamics and simulates the model for policy planning and sustainable development. These experiences are essential if dynamic systems are to be modeled and simulated. The mathematical model predicts long-term trends for hatching, growth, and harvesting of the river catfish population. Simulated results suggest that the economic harvesting of adults entering the rivers has been discussed and effective strategies for sustainable fish production. Management strategies are put in place to harvest juvenile mortality and spawn adult harvesting, sustainable development of catfish could be maintained
A Multimodal Deep Learning Approach for Identification of Severity of Reflective Depression
Get PDFSocial media consumes a greate time of our dialy times that generate a significant amount of information through expressing feeling and activities, sharing admiral contents, viewing, and more. This information mostly contains valuable discoveries. Despite many attempts to mining such produced data, it is still unexploited in certain issues and attracts many research areas. In this paper, we use the data extracted from social media from female’s pages to detect possibility of depression. A new deep learning model based on the psycholinguistic vocabulary to create the embedding words is developed. First, we extract the features from the data before and after the preprocessing phase. Second, the Convolutional Neural Network (CNN) is used to label the data for extracting the remaining features. Based on the previouse two phases; the developed model succeeded to predict the depression possibilty. Adetailed comparative analysis is also presented for the evaluation of the proposed system. The proposed indicator model proved promising results in predicting depression
Non-destructive Inspection System Development for Secondary Battery Welding Part
Get PDFIn this paper, we develop a non-destructive inspection system for secondary battery welding. In a secondary battery, when the insulation or separator of each electrode is damaged by an impact from the outside depending on the degree of welding, an internal short circuit occurs during charging and fires even if it does not ignite at that time. To detect this, a non-destructive AOI (Automatic Optical Inspection) system is developed that compares the inspection target with the reference image to determine whether there is a proper indentation in the welding part. The system consists of a precision alignment stage on the lower part and imaging equipment that performs AOI, a non-destructive inspection on the upper part. And the appropriate exposure, i.e., the aperture setting of the used camera, was confirmed through the experiment according to the position of the pole