Articles
9,174 Documents
An improved clustering based on K-means for hotspots data
Rani Rotul Muhima;
Muchamad Kurniawan;
Septiyawan Rosetya Wardhana;
Anton Yudhana;
Sunardi Sunardi;
Mitra Adhimukti
Indonesian Journal of Electrical Engineering and Computer Science Vol 31, No 2: August 2023
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v31.i2.pp1109-1117
Riau province is one of the provinces in Indonesia where forest fires frequently occur every year. Hotspot data is geothermal points and they can be utilized as an indicator of forest fires. Clustering’s method can be used to analyze potential forest fires from hotspot data’s cluster pattern. In this study, hybrid genetic algorithm polygamy with K-means (GAP K-means) was used for hotspot data clustering. GA polygamy was used to determine the initial centroid of K-means. It was used to solve the sensitivity of K-means to the initial centroid, and to find the optimal solution faster. Experimentally compared the performance of GAP K-means, GA K-means, and K-means on the hotspots data, two artificial datasets, and three real-life datasets. Sum square error (SSE), davies bouldin index (DBI), silhouette coefficient (SC) and F-measure are used to evaluation clustering. Based this experiment, GAP K-means outperforms than K-means but GAP K-means still not fast to achieve convergent than GA K-means.
Towards a new healthy food decision-making system
Ahmad Outfarouin;
Nourane Laaffat
Indonesian Journal of Electrical Engineering and Computer Science Vol 31, No 2: August 2023
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v31.i2.pp1088-1098
Latterly, food recommendation systems have received high attention due to their importance to healthy living. On the recommendation domain, most studies focus on recommendations that suggest healthy products for each user based on their profiles. These types of recommender systems offer additional functionality to persuade users to change their buying behavior profitably. However, these systems must highlight the health preferences of the users and their health problems must be adequately taken into account. In this work, healthy food products recommender systems (RS) are our interest study and more specifically using content-based filtering. We represented this content by the food product composition. Our goal was to provide a healthy recommendation to consumers or citizens around the world, especially at this time when disease abounds. Thus, we developed our new healthy recommendation system (HRS). In this paper, we present a new recommendation process for individuals in the area of healthy eating. Furthermore, we analyze the existing state of the art in recommender system techniques and implement an algorithm that responds to this new process with very satisfactory results from the beginning, to conclude we discuss the research challenges related to the development of this kind of HRS.
Citrus leaves disease diagnosis
Emad A. Mohammed;
Ghasaq Hashim Mohammed
Indonesian Journal of Electrical Engineering and Computer Science Vol 31, No 2: August 2023
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v31.i2.pp925-932
Agriculture is the most important sector in developing countries, so the main source of concern for farmers is plant diseases that lead to a lack of production and a waste of money and crops. In this paper, a system using computer-assisted convolutional neural networks (CNN) with camera is developed to characterize diseases of citrus trees. This proposed system can help farmers to increase and improve the quality of their agricultural productivity. In addition to reducing the spread of the disease through early detection. Citrus leaf dataset was created to train and test the model because citrus is one of the main crops in Iraq. The results of the experiment shown that the implemented CNN achieved high classification accuracy of (92%) with fewer parameters, making it flawless and promising outcomes.
FunAR-furniture augmented reality application to support practical laboratory experiments in interior design education
Fairuz Iqbal Maulana;
Baskoro Azis;
Tiara Ika Widia Primadani;
Pangeran Rasyach Artha Hasibuan
Indonesian Journal of Electrical Engineering and Computer Science Vol 31, No 2: August 2023
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v31.i2.pp845-855
Practical learning in the laboratory has been limited due to the COVID-19 pandemic. Conventional education must adapt to increasingly digital technological developments. The design of interactive learning media with augmented reality technology can be a solution and support the previous conventional learning. FunAR is a Furniture Augmented Reality Application developed using the analysis, design, development, implementation, and evaluation (ADDIE) method consisting of ADDIE. In its implementation, the FunAR application will provide basic information about existing equipment in Lab Furniture, accompanied by 2D images, and augmented reality technology that creates 3D objects from each piece of equipment in Lab Furniture. From 15 student respondents, the results reveal that distance, angle, and device specifications significantly impact camera marker reading. A distance of 20 cm to 80 cm and an angle of 25° to 100° can display 3D objects. Likewise, the camera’s ability to process reading markers is better on smartphones with better hardware specifications. The results of the respondents showed that 80% of respondents were satisfied with the FunAR application.
An improved features selection approach for control chart patterns recognition
Waseem Alwan;
Nor Hasrul Akhmal Ngadiman;
Adnan Hassan;
Mohd Syahril Ramadhan Mohd Saufi;
Azanizawati Ma’aram;
Ibrahim Masood
Indonesian Journal of Electrical Engineering and Computer Science Vol 31, No 2: August 2023
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v31.i2.pp734-746
Control chart patterns (CCPs) are an essential diagnostic tool for process monitoring using statistical process control (SPC). CCPs are widely used to improve production quality in many engineering applications. The principle is to recognize the state of a process, either a stable process or a deterioration to an unstable process. It is used to significantly narrow the set of possible assignable causes by shortening the diagnostic process to improve the quality. Machine learning techniques have been widely used in CCPs. Artificial neural networks with multilayer perceptron (ANN-MLP) are one of the standard tools used for this purpose. This paper proposes an improved features selection method to select the best features as input representation for control chart patterns recognition. The results demonstrate that the proposed approach can effectively recognize CCPs even for small patterns with a mean shift of less than 1.5 sigma. The dimensional reduction was achieved by employing Relief, correlation, and Fisher algorithms (RCF) for feature selection and (ANN-MLP) as a classifier (RCF-ANN). This study provides an experimental result that compares the performance before and after dimensional reduction.
Dzongkha to English translation using the neural machine translation approach
Karma Wangchuk;
Subalalitha Chinnaudayar Navaneethakrishnan;
Yeshi Jamtsho;
Yeshi Wangchuk
Indonesian Journal of Electrical Engineering and Computer Science Vol 31, No 2: August 2023
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v31.i2.pp885-892
In this era of technology, a communication barrier is a thing of the past. With each passing day, different types of language-based applications are being launched. There are 109 official languages Google has translated to date. However, the Dzongkha translation has not been studied. The purpose of this paper was to study Dzongkha to English translation. The parallel corpus was collected from the Dzongkha development commission of Bhutan. The dataset consisted of 53018 sentence pairs. Unique words in Dzongkha and English were 13,393 and 12,506 respectively. Different neural machine translation models were implemented. The experimental results show that the bleu score of Seq2Seq models followed a fluctuating trend. However, the bleu score of the transformer model increases gradually. It was observed that the transformer outperformed the Seq2Seq models. The highest accuracy and the lowest training loss obtained were 84.46% and 0.014858 respectively with a bleu score of 64.89.
For 5G applications, high-gain patch antenna in Ka-Band
Safa Nassr Nafea;
Nasser N. Khamiss
Indonesian Journal of Electrical Engineering and Computer Science Vol 31, No 2: August 2023
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v31.i2.pp802-809
The fifth generation (5G) of telecommunications is an attractive application for many researchers during the last years. The 5G requires high date rate with low latency communication medium and patch antenna was used recently for this application. In this article a patch antenna for 5G at 38 GHz was proposed. This article worked on enhancing the gain of patch antenna at Ka-Band and reducing side lobes level (SLL) in radiation pattern. The gain of the patch antenna was improved using a reflector layer located under antenna’s ground with free space air gap separating between two layers. Moreover, the SLL were reduced to satisfy low latency condition for 5G communications. The proposed antenna shows high gain around 8.10 dB with high front-to-back (F/B) ratio of 16.24 dB and wide operating bandwidth around 1.4 GHz for high data rate requirements as well as having reduced overall size antenna. The article based on analytical calculations for patch dimensions and optimization procedure to achieve the desired performance of antenna. Computer simulation technology (CST) had been used as an environment for simulation.
An Arduino-based voice-recognition elevator for special purposes
Hassan Falah Fakhruldeen;
Azal Alaa Meri;
Ali Hameed Sa'id;
Alaa Naeem Makttoof;
Musafer Awad Kadhim;
Heba Abdul-Jaleel Al-Asady
Indonesian Journal of Electrical Engineering and Computer Science Vol 31, No 2: August 2023
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v31.i2.pp828-834
This paper presents the design and implementation of five floors electrical elevator system that utilizes voice recognition technology, specifically using an Arduino microcontroller, for special applications. The purpose of this project is to provide a convenient and accessible means of transportation for individuals with disabilities, specifically those who may have difficulty using traditional elevators due to physical limitations or mobility issues. The system consists of an Arduino microcontroller, a voice recognition module, a motor driver, and an elevator car with a lift mechanism. The microcontroller receives voice commands from the user and processes them to determine the desired floor. The motor driver then activates the lift mechanism to move the car to the desired floor. The system was tested and found to be reliable and efficient in transporting individuals to their desired floor. It has the potential to greatly improve the accessibility and convenience of buildings for individuals with disabilities.
Implementing a novel fault prognosis technique based on nonlinear fault observer and online parameters estimation
Ahmad Hussain AlBayati
Indonesian Journal of Electrical Engineering and Computer Science Vol 31, No 2: August 2023
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v31.i2.pp713-724
This research presents a methodology for predicting errors of parameters, as the algorithm tries to monitor the parameters in order to maintain or replace them when needed to avoid excessive expenses. The presented implementation mechanism is based on monitoring parameters according to a specific number of batches and each batch consists of a number of iterations, which in turn are a number of samples. The proposed algorithm involves designing a new nonlinear observer and writing a secondary algorithm for parameter estimation based on the online nonlinear recursive least squares algorithm associated with the observer states. In addition, the algorithm presents an attempt to find a relationship between the error states and the state of the parameters by creating a new function to determine the weight of the error according to four components; parameter changes, output residuals, output errors and the error diagnosed by the new observer. The algorithm also includes introducing the probability form of the weights using the kernel density function for the average and maximum weights for each batch. Finally, relying on the results, it is possible to take the appropriate decision to maintain or change the parameters as shown a non-linear direct current motor model case study.
Design and measurement of the receiving antenna for electromagnetic field energy harvesting in UHF band
Fahmy Rinanda Saputri;
Sunarno Sunarno;
Singgih Hawibowo
Indonesian Journal of Electrical Engineering and Computer Science Vol 31, No 2: August 2023
Publisher : Institute of Advanced Engineering and Science
Show Abstract
|
Download Original
|
Original Source
|
Check in Google Scholar
|
DOI: 10.11591/ijeecs.v31.i2.pp681-691
This paper aims to design a receiving antenna for harvesting energy using the wireless energy transfer method based on the ultra-high frequency (UHF) band. The study was conducted by comparing four types of the receiving antenna design. A mathematical and experimental analysis has been done to evaluate the performance of the designed antennas. A Yagi-Uda antenna is utilized as the transmitter. The results show that the zig-zag type antenna has the best performance. It can receive electromagnetic energy from a transmitter with maximum efficiency is 0.1% for the receiving antenna volume of 0.34 cm3. The proposed method can meet the energy necessity of an implant device with a charging time of approximately 21.61 hours for the 700 mAh rechargeable battery capacity. As our preliminary conclusion, based on our results, this proposed method can be used as a reference for the practice in the WET field and the medical and restricted areas in the electromagnetic energy harvesting case.