Articles

Access the latest knowledge in applied science, electrical engineering, computer science and information technology, education, and health.

Advanced Search
Filter Icon

Filters article

Years

FAQ Arrow
Single Year
Range Year
0
0

Source Title

FAQ Arrow

Authors

FAQ Arrow

29,939 Article Results

New proposed method for traceability dissemination of capacitance measurements

10.11591/ijece.v11i3.pp1969-1975
Heba A. M. Hamed , A. Eliwa Gad , M. Helmy A. Raouf
Capacitance measurements at the National Institute of Standards (NIS), Egypt, are traceable to the Bureau International des Poids et Mesures (BIPM). It calibrates the main NIS standard capacitors, AH11A. In this paper, traceability of the BIPM capacitance measurements could be used to evaluate a new accurate measurement method through an Ultra-Precision Capacitance Bridge. The new method is carefully described by introducing some necessary equations and a demonstrating chart. Verification of this new method has been realized by comparing its results for the 10 pF and 100 pF capacitance standards with the results obtained by the conventional substitution method at 1 kHz and 1.592 kHz. The relative differences between the two methods are about 0.3 µF/F, which reflect the accuracy of the new measurement method. For higher capacitance ranges, the new measurement method has been applied for the capacitance measurements up to 1 μF at 1 kHz. The relative differences between the two methods are in the range of 5.5 µF/F on the average which proves the acceptable accuracy and the reliability of the new method to be used.
Volume: 11
Issue: 3
Page: 1969-1975
Publish at: 2021-06-01

Comparative analysis of multiple classification models to improve PM10 prediction performance

10.11591/ijece.v11i3.pp2500-2507
Yong-Jin Jung , Kyoung-Woo Cho , Jong-Sung Lee , Chang-Heon Oh
With the increasing requirement of high accuracy for particulate matter prediction, various attempts have been made to improve prediction accuracy by applying machine learning algorithms. However, the characteristics of particulate matter and the problem of the occurrence rate by concentration make it difficult to train prediction models, resulting in poor prediction. In order to solve this problem, in this paper, we proposed multiple classification models for predicting particulate matter concentrations required for prediction by dividing them into AQI-based classes. We designed multiple classification models using logistic regression, decision tree, SVM and ensemble among the various machine learning algorithms. The comparison results of the performance of the four classification models through error matrices confirmed the f-score of 0.82 or higher for all the models other than the logistic regression model.
Volume: 11
Issue: 3
Page: 2500-2507
Publish at: 2021-06-01

Cassini-Huygens mission images classification framework by deep learning advanced approach

10.11591/ijece.v11i3.pp2457-2466
Ashraf AlDabbas , Zoltan Gal
Developing a deep learning (DL) model for image classification commonly demands a crucial architecture organization. Planetary expeditions produce a massive quantity of data and images. However, manually analyzing and classifying flight missions image databases with hundreds of thousands of images is ungainly and yield weak accuracy. In this paper, we speculate an essential topic related to the classification of remotely sensed images, in which the process of feature coding and extraction are decisive procedures. Diverse feature extraction techniques are intended to stimulate a discriminative image classifier. Features extraction is the primary engagement in raw data processing with the purpose of data classification; when it comes across the task of analysis of vast and varied data, these kinds of tasks are considered as time-consuming and hard to be treated with. Most of these classifiers are either, in principle, quite intricate or virtually unattainable to calculate for massive datasets. Stimulated by this perception, we put forward a straightforward, efficient classifier based on feature extraction by analyzing the cell of tensors via layered MapReduce framework beside meta-learning LSTM followed by a SoftMax classifier. Experiment results show that the provided model attains a classification accuracy of 96.7%, which makes the provided model quite valid for diverse image databases with varying sizes.
Volume: 11
Issue: 3
Page: 2457-2466
Publish at: 2021-06-01

JPG, PNG and BMP image compression using discrete cosine transform

10.12928/telkomnika.v19i3.14758
Rostam Affendi; Universiti Teknikal Malaysia Melaka Hamzah , Muttaqin Md; Universiti Teknikal Malaysia Melaka Roslan , Ahmad Fauzan bin; Universiti Teknikal Malaysia Melaka Kadmin , Shamsul Fakhar bin Abd; Universiti Teknikal Malaysia Melaka Gani , Khairul Azha A.; Universiti Teknikal Malaysia Melaka Aziz
This paper proposes image compression using discrete cosine transform (DCT) for the format of joint photographic expert groups (JPEG) or JPG, portable network graphic (PNG) and bitmap (BMP). These three extensions are the most popular types used in current image processing storage. The purpose of image compression is to produce lower memory usage or to reduce memory file. This process removes redundant information of each pixel. The challenge for image compression process is to maintain the quality of images after the compression process. Hence, this article utilizes the DCT technique to sustain the image quality and at the same time reduces the image storage size. The effectiveness of the DCT technique has been reasonable over some real images and the implementation of the technique has been compared with different types of image extensions. Matlab software is an important platform for this project in order to write a program and perform the progress of project phase by phase to achieve the expected results. Based on the tested images, the DCT technique in image compression is capable to reduce the image storage memory in average about 50% of each image tested.
Volume: 19
Issue: 3
Page: 1010-1016
Publish at: 2021-06-01

Why students tend to compare themselves with each other? The role of mattering and unconditional self-acceptance

10.11591/ijere.v10i2.21238
Shien-Yi Kam , Kususanto Ditto Prihadi
Previous studies suggested that university students who are not able to accept themselves tend to develop negative tendency to compare themselves with each other. This study aimed to investigate the role of unconditional self-acceptance (USA) in explaining the association between mattering and social comparison among Malaysian undergraduate students. Three hundred and seventy undergraduate students were recruited and asked to complete an online version of Unconditional Self-Acceptance questionnaire, Iowa-Netherlands Comparison Orientation Measure and University Mattering Scale. Data analysis was conducted by employing Bootstrap Method with 95% confidence interval and 5000 sampling. The result showed that USA partially mediated the relationship between mattering and social comparison. Mattering and USA were identified as robust protective factors of social comparison among university students.
Volume: 10
Issue: 2
Page: 441-447
Publish at: 2021-06-01

Implementation multiple linear regresion in neural network predict gold price

10.11591/ijeecs.v22.i3.pp1635-1642
Musli Yanto , Sigit Sanjaya , Yulasmi Yulasmi , Dodi Guswandi , Syafri Arlis
The movement of gold prices in the previous period was crucial for investors. However, fluctuations in gold price movements always occur. The problem in this study is how to apply multiple linear regression (MRL) in predicting artificial neural networks (ANN) of gold prices. MRL is mathematical calculation technique used to measure the correlation between variables. The results of the MRL analysis ensure that the network pattern that is formed can provide precise and accurate prediction results. In addition, this study aims to develop a predictive pattern model that already exists. The results of the correlation test obtained by MRL provide a correlation of 62% so that the test results are said to have a significant effect on gold price movements. Then the prediction results generated using an ANN has a mean squared error (MSE) value of 0.004264%. The benefits obtained in this study provide an overview of the gold price prediction pattern model by conducting learning and approaches in testing the accuracy of the use of predictor variables.
Volume: 22
Issue: 3
Page: 1635-1642
Publish at: 2021-06-01

Summarization of COVID-19 news documents deep learning-based using transformer architecture

10.12928/telkomnika.v19i3.18356
Nur; University of Muhammadiyah Malang Hayatin , Kharisma Muzaki; University of Muhammadiyah Malang Ghufron , Galih Wasis; University of Muhammadiyah Malang Wicaksono
Facing the news on the internet about the spreading of Corona virus disease 2019 (COVID-19) is challenging because it is required a long time to get valuable information from the news. Deep learning has a significant impact on NLP research. However, the deep learning models used in several studies, especially in document summary, still have a deficiency. For example, the maximum output of long text provides incorrectly. The other results are redundant, or the characters repeatedly appeared so that the resulting sentences were less organized, and the recall value obtained was low. This study aims to summarize using a deep learning model implemented to COVID-19 news documents. We proposed transformer as base language models with architectural modification as the basis for designing the model to improve results significantly in document summarization. We make a transformer-based architecture model with encoder and decoder that can be done several times repeatedly and make a comparison of layer modifications based on scoring. From the resulting experiment used, ROUGE-1 and ROUGE-2 show the good performance for the proposed model with scores 0.58 and 0.42, respectively, with a training time of 11438 seconds. The model proposed was evidently effective in improving result performance in abstractive document summarization.
Volume: 19
Issue: 3
Page: 754-761
Publish at: 2021-06-01

Clustering using kernel entropy principal component analysis and variable kernel estimator

10.11591/ijece.v11i3.pp2109-2119
Loubna El Fattahi , El Hassan Sbai
Clustering as unsupervised learning method is the mission of dividing data objects into clusters with common characteristics. In the present paper, we introduce an enhanced technique of the existing EPCA data transformation method. Incorporating the kernel function into the EPCA, the input space can be mapped implicitly into a high-dimensional of feature space. Then, the Shannon’s entropy estimated via the inertia provided by the contribution of every mapped object in data is the key measure to determine the optimal extracted features space. Our proposed method performs very well the clustering algorithm of the fast search of clusters’ centers based on the local densities’ computing. Experimental results disclose that the approach is feasible and efficient on the performance query.
Volume: 11
Issue: 3
Page: 2109-2119
Publish at: 2021-06-01

Amazigh-Sys: Intelligent system for recognition of amazigh words

10.11591/ijai.v10.i2.pp482-489
Rachid Ammari , Lahbib Zenkouar
Amazigh-sys is an intelligent morphological analysis system for Amazigh language based on xerox’s finite-state transducer (XFST). Our system can process simultaneously five lexical units. This paper begins with the development of Amazigh lexicon (AMAlex) for attested nouns, verbs, pronouns, prepositions, and adverbs and the characteristics relating to each lemma. A set of rules are added to define the inflectional behavior and morphosyntactic links of each entry as well as the relationship between the different lexical units. The use of finite-state technology ensures the bidirectionality of our system (analysis and generation). Amazigh-sys is the first general morphological analysis system for Amazigh based on xerox finite state able to process and recognize all lexical units and ensures a high recognition rate of input words. This contribution facilitates the implementation of other applications related to the automatic processing of the Amazigh language.
Volume: 10
Issue: 2
Page: 482-489
Publish at: 2021-06-01

Investigation on the application of ZnO nanostructures to improve the optical performance of white light-emitting diodes

10.12928/telkomnika.v19i3.16714
My Hanh Nguyen; Industrial University of Ho Chi Minh City Thi , Phung Ton; Industrial University of Ho Chi Minh City That , Hoang Van; Thu Dau Mot University Ngoc
Though combining blue LED chips with yellow phosphor has been the most common method in white light-emitting diode (WLED) production, the attained angular correlated color temperature (CCT) uniformity is still poor. Thus, this article proposes to add ZnO nanostructures to WLED packages to promote the color uniformity of the WLEDs. The outcomes of the research demonstrate that utilizing ZnO at different amount can affect the scattering energy and the CCT deviations in WLEDs packages in different extents. Particularly, adding the node-like (N-ZnO), sheet-like (S-ZnO), and rod-like (R-ZnO) leads to the corresponding decreases of CCT deviations from 3455.49 K to 96.30 K, 40.03 K, and 60.09 K, respectively. Meanwhile, with 0.25% N-ZnO, 0.75% S-ZnO, and 0.25 % R-ZnO, WLED devices can achieve both better CCT homogeneity and lower reduction in luminous flux. The results of this article can be a valuable document for the manufacturer to use as reference in improving their WLED products.
Volume: 19
Issue: 3
Page: 963-967
Publish at: 2021-06-01

Dynamic bandwidth allocation algorithm for long reach passive optical network

10.12928/telkomnika.v19i3.18787
Siti Hasunah; Universiti Teknologi Malaysia Mohammad , Nadiatulhuda; Universiti Teknologi Malaysia Zulkifli , Sevia Mahdaliza; Universiti Teknologi Malaysia Idrus
Next generation broadband access networks are gaining more interests from many key players in this field. The demands for longer reach and higher bandwidth are among the driving factors for such network as it can reach wider area up to 100 km, even beyond; has enhanced bandwidth capacity and transmission speed, but with low cost and energy consumption. One promising candidate is long reach passive optical network, a simplified network with reduced number of network elements, equipment interfaces, and even nodes; which leads to a significant reduction in the network’s capital expenditure and operational expenditure. Outcome of an extended reach often results in increased propagation delay of dynamic bandwidth allocation messages exchange between the optical line terminals and optical network units, leading to the degradations of bandwidth allocation and quality of service support. Therefore, an effective bandwidth allocation algorithm with appropriate service interval setup for a long reach network is proposed to ensure the delay is maintained under ITU-T G.987.1 standard requirement. An existing algorithm is improved in terms of service interval so that it can perform well beyond 100 km. Findings show that the improved algorithm can reduce the mean delay of high priority traffic classes for distance up to 140 km.
Volume: 19
Issue: 3
Page: 738-746
Publish at: 2021-06-01

Parallel classification and optimization of telco trouble ticket dataset

10.12928/telkomnika.v19i3.18159
Fauzy Bin Che; Multimedia University Yayah , Khairil Imran; Multimedia University Ghauth , Choo-Yee; Multimedia University Ting
In the big data age, extracting applicable information using traditional machine learning methodology is very challenging. This problem emerges from the restricted design of existing traditional machine learning algorithms, which do not entirely support large datasets and distributed processing. The large volume of data nowadays demands an efficient method of building machine-learning classifiers to classify big data. New research is proposed to solve problems by converting traditional machine learning classification into a parallel capable. Apache Spark is recommended as the primary data processing framework for the research activities. The dataset used in this research is related to the telco trouble ticket, identified as one of the large volume datasets. The study aims to solve the data classification problem in a single machine using traditional classifiers such as W-J48. The proposed solution is to enable a conventional classifier to execute the classification method using big data platforms such as Hadoop. This study’s significant contribution is the output matrix evaluation, such as accuracy and computational time taken from both ways resulting from hyper-parameter tuning and improvement of W-J48 classification accuracy for the telco trouble ticket dataset. Additional optimization and estimation techniques have been incorporated into the study, such as grid search and cross-validation method, which significantly improves classification accuracy by 22.62% and reduces the classification time by 21.1% in parallel execution inside the big data environment.
Volume: 19
Issue: 3
Page: 872-885
Publish at: 2021-06-01

Hybrid DSS for recommendations of halal culinary tourism West Sumatra

10.11591/ijai.v10.i2.pp273-283
Mardison Mardison , Agung Ramadhanu , Larissa Navia Rani , Sofika Enggari
Decision support system (DSS) is a system that design to support managers in deciding on multiple criteria and multiple attributes. This study combines two methods in the DSS, that are analytical hierarchy process (AHP) method and simple additive weighting (SAW) method. This combination of two DSS method named hybrid DSS. The AHP method is using to find the weighting or priorities of criteria in DSS and then the value will use by SAW method using to find the decision. The decision of this DSS is the recommendation of halal culinary tourism in West Sumatra Indonesia. The purpose of this study is to provide updates from previous studies, related to adding indicators of halal culinary tourism and other information updates. The number of potential culinary tourism attractions and tourism, the problems that exist in the real field, is still lack of culinary information in West Sumatra. As a result, many tourists find it difficult to find the best and economical culinary. The SAW and AHP methods become the hybrid DSS method that will be able to classify and provide information on halal tourism in West Sumatra that is precise, accurate, consistent, and validated.
Volume: 10
Issue: 2
Page: 273-283
Publish at: 2021-06-01

Enhancing the performance of cancer text classification model based on cancer hallmarks

10.11591/ijai.v10.i2.pp316-323
Noha Ali , Ahmed H. AbuEl-Atta , Hala H. Zayed
Deep learning (DL) algorithms achieved state-of-the-art performance in computer vision, speech recognition, and natural language processing (NLP). In this paper, we enhance the convolutional neural network (CNN) algorithm to classify cancer articles according to cancer hallmarks. The model implements a recent word embedding technique in the embedding layer. This technique uses the concept of distributed phrase representation and multi-word phrases embedding. The proposed model enhances the performance of the existing model used for biomedical text classification. The result of the proposed model overcomes the previous model by achieving an F-score equal to 83.87% using an unsupervised technique that trained on PubMed abstracts called PMC vectors (PMCVec) embedding. Also, we made another experiment on the same dataset using the recurrent neural network (RNN) algorithm with two different word embeddings Google news and PMCVec which achieving F-score equal to 74.9% and 76.26%, respectively.
Volume: 10
Issue: 2
Page: 316-323
Publish at: 2021-06-01

Realistic mathematics education: Mathematical reasoning and communication skills in rural contexts

10.11591/ijere.v10i2.20640
Anderson Leonardo Palinussa , Juliana Selvina Molle , Magy Gaspersz
Mathematics learning has always been a problem in the world of education in Indonesia especially in the Province of Maluku, which is a thousand island area. The geographical position of Maluku, which is an area of the archipelago, is quite extensive, affecting the quality of students in mathematics. One approach that is recommended to overcome mathematical problems of rural island-based students is realistic mathematics education (RME). The purpose of this study was to analyze the effect of RME on mathematical reasoning and communication skills in a rural context. The research design used was quasi experiment. The sample size was 130 students from several junior high schools in Central Maluku Regency. The instrument developed was in the form of problem descriptions to measure students' mathematical reasoning and communication skills. The findings prove that RME has a significant influence on students' mathematical reasoning and communication skills. Thus, RME can be recommended in improving students' mathematical reasoning and communication skills in the island-based rural context.
Volume: 10
Issue: 2
Page: 522-534
Publish at: 2021-06-01
1 2 3
...
1995 1996
Show 970 of 1996

Discover Our Library

Embark on a journey through our expansive collection of articles and let curiosity lead your path to innovation.

Explore Now
Library 3D Ilustration