Indonesian Journal of Electrical Engineering and Computer Science

Journal Information
ISSN / EISSN : 2502-4752 / 2502-4760
Total articles ≅ 3,438
Current Coverage

Latest articles in this journal

Jonalyn Mae E. Aranda, Jasper Rae Zeus A. Antonio
Indonesian Journal of Electrical Engineering and Computer Science, Volume 24, pp 99-107;

The world is now faced with a devastating pandemic outbreak coronavirus disease-2019 (COVID-19). The latest coronavirus infected almost all continents and witnessed sharp rises in cases diagnosed. The engineers tend to eliminate the matter and have solutions, one in every utilizing technical innovation. Researchers from Singapore, Taiwan, and Denmark have developed a fully automated robot that may take coronavirus swabs in order for health care professionals don’t seem to be exposed to the chance of infection. The objective of this study is to present the potential effects of robotics to help healthcare professionals on getting specimens and testing for COVID-19. These possible consequences include positive and negative outcomes and as a result, the overall impact on the profit or loss to society is far from obvious. The paper discusses two theoretical scenarios, distinguished fundamentally by the different behavioral responses of the automated swab robot and the selection of results in line with policy interventions.
Ashwaq N. Hassan, Sarab Al-Chlaihawi, Ahlam R. Khekan
Indonesian Journal of Electrical Engineering and Computer Science, Volume 24, pp 317-328;

A well Fifth generation (5G) mobile networks have been a common phrase in recent years. We have all heard this phrase and know its importance. By 2025, the number of devices based on the fifth generation of mobile networks will reach about 100 billion devices. By then, about 2.5 billion users are expected to consume more than a gigabyte of streamed data per month. 5G will play important roles in a variety of new areas, from smart homes and cars to smart cities, virtual reality and mobile augmented reality, and 4K video streaming. Bandwidth much higher than the fourth generation, more reliability and less latency are some of the features that distinguish this generation of mobile networks from previous generations. Clearly, at first glance, these features may seem very impressive and useful to a mobile network, but these features will pose serious challenges for operators and communications companies. All of these features will lead to considerable complexity. Managing this network, preventing errors, and minimizing latency are some of the challenges that the 5th generation of mobile networks will bring. Therefore, the use of artificial intelligence and machine learning is a good way to solve these challenges. in other say, in such a situation, proper management of the 5G network must be done using powerful tools such as artificial intelligence. Various researches in this field are currently being carried out. Research that enables automated management and servicing and reduces human error as much as possible. In this paper, we will review the artificial intelligence techniques used in communications networks. Creating a robust and efficient communications network using artificial intelligence techniques is a great incentive for future research. The importance of this issue is such that the sixth generation (6G) of cellular communications; There is a lot of emphasis on the use of artificial intelligence.
Mustafa M. Al-Saeedi, Ahmed A. Hashim, Omer Al-Bayati, Ali Salim Rasheed, Rasool Hasan Finjan
Indonesian Journal of Electrical Engineering and Computer Science, Volume 24, pp 386-393;

This paper proposes a dual band reconfigurable microstrip slotted antenna for supporting the wireless local area network (WLAN) and worldwide interoperability for microwave access (WiMAX) applications, providing coverage where both directive and omni-directive radiations are needed. The design consists of a feedline, a ground plane with two slots and two gaps between them to provide the switching capability and a 1.6 mm thick flame retardant 4 (FR4) substrate (dielectric constant Ɛ=4.3, loss tangent δ=0.019), modeling an antenna size of 30x35x1.6 mm3. The EM simulation, which was carried out using the connected speech test (CST) studio suite 2017, generated dual wide bands of 40% (2-3 GHz) with -55 dB of S11 and 24% (5.2-6.6 GHz) higher than its predecessors with lower complexity and -60 dB of S11 in addition to the radiation pattern versatility while maintaining lower power consumption. Moreover, the antenna produced omnidirectional radiation patterns with over than 40% bandwith at 2.4 GHz and directional radiation patterns with 24% bandwith at the 5.8 GHz band. Furthermore, a comprehensive review of previously proposed designs has also been made and compared with current work.
John Joshua Federis Montañez
Indonesian Journal of Electrical Engineering and Computer Science, Volume 24, pp 90-98;

Standard laboratory soil testing is deemed to be expensive and time-consuming. Utilizing a soil test kit is considered to be a cost-efficient and time-saving way of soil testing. This project study aims to develop a prototype that detects soil parameters (i.e., soil pH, nitrogen, phosphorus, and potassium) and gives crop and fertilizer recommendations after the soil sample has undergone a soil treatment test kit and its acceptability for possible users. The prototype development primarily used image processing to detect the needed parameters that lead to crop and fertilizer recommendations. In the evaluation of the effectiveness of the prototype, 50 trials were conducted per parameter. All of the said parameters were recorded as highly effective except for nitrogen Low, which is interpreted as effective only. There were 30 possible users invited to assess the acceptability of the prototype. A survey based on the technology acceptance model was administered to the 30 respondents garnering a 4.85 weighted mean interpreted as excellent. The prototype was proven effective and accepted as a device that can detect soil pH and primary macronutrient levels. It gives the appropriate crop and fertilizer recommendations based on the gathered data.
Pawat Chimlek, Sutasinee Jitanan
Indonesian Journal of Electrical Engineering and Computer Science, Volume 24, pp 279-286;

Lime is a commercially important fruit in Thailand whose sale price depends on the fruit’s size; hence, farmers must grade limes by size before distribution. However, as lime grading machines are very expensive and each province has different size grading limits, grading is often performed manually, which is time-consuming and error-prone. Agricultural production systems for automatic selection and grading use image processing techniques for extracting key features. Therefore, this study proposes techniques to extract features of limes and to develop analytical methods for grading them. This method can reduce time and cost, and increase accuracy and flexibility for selecting different lime sizes according to each province’s size criteria. To verify our method, we classified limes according to criteria from four Thailand provinces as sample data in an experiment. The focal image feature was the radius or diameter of the lime and the grading conditions were defined by the maximum comparison ratio of the fruit’s radius in pixels to the measured radius of the actual lime in centimeters. The average grading accuracy was 99.59%, which outperformed that of mechanical grading. The processing time was 1.70 seconds per individual fruit.
Abdullahi Adeleke, Noor Azah Samsudin, Mohd Hisyam Abdul Rahim, Shamsul Kamal Ahmad Khalid, Riswan Efendi
Indonesian Journal of Electrical Engineering and Computer Science, Volume 24, pp 484-490;

Machine learning involves the task of training systems to be able to make decisions without being explicitly programmed. Important among machine learning tasks is classification involving the process of training machines to make predictions from predefined labels. Classification is broadly categorized into three distinct groups: single-label (SL), multi-class, and multi-label (ML) classification. This research work presents an application of a multi-label classification (MLC) technique in automating Quranic verses labeling. MLC has been gaining attention in recent years. This is due to the increasing amount of works based on real-world classification problems of multi-label data. In traditional classification problems, patterns are associated with a single-label from a set of disjoint labels. However, in MLC, an instance of data is associated with a set of labels. In this paper, three standard MLC methods: binary relevance (BR), classifier chain (CC), and label powerset (LP) algorithms are implemented with four baseline classifiers: support vector machine (SVM), naïve Bayes (NB), k-nearest neighbors (k-NN), and J48. The research methodology adopts the multi-label problem transformation (PT) approach. The results are validated using six conventional performance metrics. These include: hamming loss, accuracy, one error, micro-F1, macro-F1, and avg. precision. From the results, the classifiers effectively achieved above 70% accuracy mark. Overall, SVM achieved the best results with CC and LP algorithms.
Mohebbanaaz Mohebbanaaz, Y. Padma Sai, L. V. Rajani Kumari
Indonesian Journal of Electrical Engineering and Computer Science, Volume 24, pp 217-225;

Deep learning (DL) has become a topic of study in various applications, including healthcare. Detection of abnormalities in an electrocardiogram (ECG) plays a significant role in patient monitoring. It is noted that a deep neural network when trained on huge data, can easily detect cardiac arrhythmia. This may help cardiologists to start treatment as early as possible. This paper proposes a new deep learning model adapting the concept of transfer learning to extract deep-CNN features and facilitates automated classification of electrocardiogram (ECG) into sixteen types of ECG beats using an optimized support vector machine (SVM). The proposed strategy begins with gathering ECG datasets, removal of noise from ECG signals, and extracting beats from denoised ECG signals. Feature extraction is done using ResNet18 via concept of transfer learning. These extracted features are classified using optimized SVM. These methods are evaluated and tested on the MIT-BIH arrhythmia database. Our proposed model is effective compared to all State of Art Techniques with an accuracy of 98.70%.
Mouhcine El Hassani, Noureddine Falih, Belaid Bouikhalene
Indonesian Journal of Electrical Engineering and Computer Science, Volume 24, pp 269-278;

Classification of information is a vague and difficult to explore area of research, hence the emergence of grouping techniques, often referred to Clustering. It is necessary to differentiate between an unsupervised and a supervised classification. Clustering methods are numerous. Data partitioning and hierarchization push to use them in parametric form or not. Also, their use is influenced by algorithms of a probabilistic nature during the partitioning of data. The choice of a method depends on the result of the Clustering that we want to have. This work focuses on classification using the density-based spatial clustering of applications with noise (DBSCAN) and DENsity-based CLUstEring (DENCLUE) algorithm through an application made in csharp. Through the use of three databases which are the IRIS database, breast cancer wisconsin (diagnostic) data set and bank marketing data set, we show experimentally that the choice of the initial data parameters is important to accelerate the processing and can minimize the number of iterations to reduce the execution time of the application.
Mohammad H. Ismail, Shefa A. Dawwd, Fakhradeen H. Ali
Indonesian Journal of Electrical Engineering and Computer Science, Volume 24, pp 178-188;

An Arabic sign language recognition using two concatenated deep convolution neural network models DenseNet121 & VGG16 is presented. The pre-trained models are fed with images, and then the system can automatically recognize the Arabic sign language. To evaluate the performance of concatenated two models in the Arabic sign language recognition, the red-green-blue (RGB) images for various static signs are collected in a dataset. The dataset comprises 220,000 images for 44 categories: 32 letters, 11 numbers (0:10), and 1 for none. For each of the static signs, there are 5000 images collected from different volunteers. The pre-trained models were used and trained on prepared Arabic sign language data. These models were used after some modification. Also, an attempt has been made to adopt two models from the previously trained models, where they are trained in parallel deep feature extractions. Then they are combined and prepared for the classification stage. The results demonstrate the comparison between the performance of the single model and multi-model. It appears that most of the multi-model is better in feature extraction and classification than the single models. And also show that when depending on the total number of incorrect recognize sign image in training, validation and testing dataset, the best convolutional neural networks (CNN) model in feature extraction and classification Arabic sign language is the DenseNet121 for a single model using and DenseNet121 & VGG16 for multi-model using.
Mohamed Chiny, Marouane Chihab, El Mahdi Juiher, Khaoula Jabari, Omar Bencharef, Younes Chihab
Indonesian Journal of Electrical Engineering and Computer Science, Volume 24, pp 410-419;

With the emergence of social networks and their adoption by a large number of users, the importance of influencers continues to grow and companies are in a frantic race to recruit those most likely to promote their reputation and brand image. However, in the existing literature, there is little work that conducts quantitative studies on this subject in developing countries. For this reason, we conducted a study that attempts to understand the importance of influencers in reshaping public opinion of a company or brand. We chose as a subject of study a large Moroccan company operating in the telecommunications sector that hired a popular influencer among young Moroccans. We then adopted an approach based on scraping and analyzing the occurrences of the influencer's posts on Instagram and the content of the company's website and then publishing a questionnaire to 180 respondents in the age range of most of the followers of the influencer in question. The results suggest that a positive relationship exists between the influencer and brand reputation, meaning that if the person is following the influencer who has published content on the brand, that person is expected to be systematically aware of the brand, and vice versa.
Back to Top Top